diff --git a/AGENTS.md b/AGENTS.md
index a133fcce60..ada6e7151b 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -90,6 +90,12 @@ packages/    Harness packages, grouped by role at packages/<group>/<pkg>/.
     hook-protocol/  shared Claude Code / Codex hook wire-protocol core (library,
                     not a plugin): matcher primitive, exit-code/stdout codec,
                     runHook (via ctx.bash), most-restrictive merge, hook/* events
+    hooks-claude/   bridge plugin: runs a Claude Code hooks.json / settings on the
+                    interception seams (CC dialect — env + ${CLAUDE_PLUGIN_ROOT}
+                    substitution, per-event stdin payloads, outcome→Decision map)
+    hooks-codex/    bridge plugin: runs a Codex hooks.json on the seams (Codex
+                    dialect — a 5-event, regex-only, block-only, no-substitution
+                    subset of the CC protocol)
   session-persistence/   persistence capability family
     session-persistence/         durable persistence seam + write coordinator
     session-persistence-jsonl/    JSONL-sidecar backend
diff --git a/docs/module-graph.md b/docs/module-graph.md
index 7623603b5a..452639a90f 100644
--- a/docs/module-graph.md
+++ b/docs/module-graph.md
@@ -62,6 +62,11 @@ graph TD
   agent-loop --> session-persistence
   agent-loop --> system-prompt
   agent-loop --> tools
+  hooks-codex --> agent
+  hooks-codex --> hook-protocol
+  hooks-codex --> llm
+  hooks-codex --> session
+  hooks-codex --> tools
   subagent --> agent
   subagent --> llm
   subagent --> tools
@@ -89,6 +94,12 @@ graph TD
   agent-core --> system-prompt
   agent-core --> tool-bash
   agent-core --> tools
+  hooks-claude --> agent
+  hooks-claude --> hook-protocol
+  hooks-claude --> llm
+  hooks-claude --> session
+  hooks-claude --> subagent
+  hooks-claude --> tools
   subagent-acp --> agent
   subagent-acp --> llm
   subagent-acp --> subagent
@@ -150,12 +161,14 @@ graph TD
 | `ui-stdio` | `agent`, `llm`, `session` |
 | `acp` | `agent`, `llm`, `session`, `session-persistence`, `tools` |
 | `agent-loop` | `agent`, `llm`, `session`, `session-persistence`, `system-prompt`, `tools` |
+| `hooks-codex` | `agent`, `hook-protocol`, `llm`, `session`, `tools` |
 | `subagent` | `agent`, `llm`, `tools` |
 | `tool-bash` | `agent`, `bash`, `llm`, `tools` |
 | `tool-fs` | `fs`, `llm`, `session`, `system-prompt`, `tools` |
 | `tool-todo` | `agent`, `session`, `tools` |
 | `tool-web` | `llm`, `system-prompt`, `tools`, `web` |
 | `agent-core` | `agent`, `agent-loop`, `invariants`, `llm`, `session`, `system-prompt`, `tool-bash`, `tools` |
+| `hooks-claude` | `agent`, `hook-protocol`, `llm`, `session`, `subagent`, `tools` |
 | `subagent-acp` | `agent`, `llm`, `subagent` |
 | `subagent-inprocess` | `agent`, `llm`, `session`, `subagent` |
 | `subagent-mock` | `agent`, `llm`, `subagent` |
diff --git a/docs/rfc/README.md b/docs/rfc/README.md
index 70e7886911..0a549a7045 100644
--- a/docs/rfc/README.md
+++ b/docs/rfc/README.md
@@ -90,6 +90,7 @@ Do NOT write one for a mechanical or local choice (a variable name, a one-file r
 | [Interception seams — the typed-Decision surface a hook programs against](implemented/feature/2026-06-30-interception-seams.md) | 2026-06-30 |
 | [Subagent lifecycle enrichment — lastAssistantMessage (observe-only)](implemented/feature/2026-06-30-subagent-observe-enrich.md) | 2026-06-30 |
 | [dsh-hook-protocol — the shared Claude Code / Codex hook wire-protocol core](implemented/feature/2026-06-30-hook-protocol-lib.md) | 2026-06-30 |
+| [dsh-hooks-claude + dsh-hooks-codex — the Claude Code / Codex hook bridges](implemented/feature/2026-06-30-hook-bridges.md) | 2026-06-30 |
 
 ### Simplification
 
diff --git a/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md b/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
new file mode 100644
index 0000000000..3bedd73b34
--- /dev/null
+++ b/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
@@ -0,0 +1,69 @@
+# RFC: dsh-hooks-claude + dsh-hooks-codex — the Claude Code / Codex hook bridges
+
+Status: implemented (accepted 2026-06-30)
+
+<!-- XXX: legacy ADR/RFC body format, not yet normalized to a unified RFC template. -->
+
+## Context
+
+The harness's extension surface is its typed interception seams ([the interception-seams RFC](2026-06-30-interception-seams.md)): a "native hook" is just an ordinary cordis plugin subscribing to `agent/session-start`, `agent/prompt-submit`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation`, `subagent/start`, `subagent/end`. But users arrive with **existing** Claude Code (CC) and Codex hook configs — a `hooks.json` (or a settings file's `hooks` key) full of shell-command hooks — and want those to run unmodified. This RFC introduces the two **bridge plugins** that translate that external shell-hook protocol onto the typed seams, built on the shared wire-protocol library ([the hook-protocol-lib RFC](2026-06-30-hook-protocol-lib.md)).
+
+The framing that shapes the whole design: **a bridge is a faithfulness adapter, not a power tool.** Anything a bridge does (block a tool, inject context, force continuation, observe a subagent) a native cordis plugin does more powerfully — typed returns, full `ctx`, no serialization boundary. The bridge's only reason to exist is to run an UNMODIFIED external CC/Codex hook with byte-faithful semantics. That keeps each bridge thin: parse the config, pick a matcher mode, build the per-event payload, call `runHook` + `mergeHookOutputs` from the shared lib, map the neutral outcome onto a seam Decision.
+
+## Decision
+
+Two independent plugins in the `packages/hooks/` group, each a function/namespace plugin (`name`/`inject`/`Config`/`apply`, NO default export — see [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md)) injecting only `bash`:
+
+- **`dsh-hooks-claude`** — the CC dialect. Seven hook points: `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, `SubagentStop`. Owns CC's per-event stdin payloads (a base of `session_id`/`cwd`/`hook_event_name` plus per-event fields), CC's env + `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the literal-or-regex matcher mode. A CC hook's stdin carries a **trailing newline**.
+- **`dsh-hooks-codex`** — the Codex dialect: a deliberate SUBSET. Five hook points (`PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop` — no subagent/notification/compaction), an always-regex matcher, snake_case payloads with `turn_id`/`model`/`permission_mode` extras written WITHOUT a trailing newline, no env and no `${…}` substitution, and a block-only decision model (a Codex hook can never pre-approve, so `allow`/`ask` are not honored). A tool call's payload carries the real `tool_name` (the value the matcher tests, so a config's tool matcher fires) in Codex's `tool_input: { command }` shape.
+
+### Outcome → Decision mapping
+
+Each bridge maps the neutral `MergedHookOutcome` from the shared lib onto the seam's typed Decision:
+
+| Seam | CC | Codex |
+|---|---|---|
+| `agent/session-start` (emit) | additionalContext → `agent.inject()` | plain-stdout output → additionalContext → `agent.inject()` |
+| `agent/prompt-submit` | `deny`→`block`; context-only→delegate+fold | `block`→`block`; context-only→delegate+fold |
+| `tools/pre-execute` | `deny`→`deny`; `ask`→`ask` | `block`→`deny` (no allow/ask) |
+| `tools/post-execute` | `deny`→`block`+feedback; context-only→delegate+fold | same |
+| `agent/turn-continuation` | blocking Stop → `continue` (reason = next-step steering) | same |
+| `subagent/start` (emit) | additionalContext → inject into the live child | — (not a Codex event) |
+| `subagent/end` (emit) | observe-only | — |
+
+### Context source is always the plugin (the mislabel guard)
+
+`agent.inject()` defaults a missing `MessageSource` to `{ kind: 'user' }` — which would record plugin-injected context as if the user had typed it. So every bridge `inject()` and every `HookContext` passes an explicit `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }` source. A test asserts the resulting `context/message.source` is the plugin, never `user`.
+
+### Adding context is not a veto — delegate, then fold
+
+A hook that only attaches `additionalContext` (no block/deny) is NOT a decision the bridge should return on its own: returning `allow`/`accept` from a waterfall listener WITHOUT calling `next()` short-circuits every later `agent/prompt-submit` / `tools/post-execute` listener, so a policy/sandbox plugin registered after the bridge would never see the prompt. So on the context-only path each bridge **delegates via `next()`** and then **folds** its `additionalContext` onto the downstream decision (`concatContext`). The fold differs by seam because the two Decision unions differ: `tools/post-execute` — a downstream `block`/`accept` both carry an `additionalContext` field, so the bridge context rides along either way (a downstream block wins AND keeps the context; a downstream accept keeps its content rewrite and gains the context). `agent/prompt-submit` — a downstream `allow` gains the bridge context (and keeps its own content rewrite / additionalContext), but `PromptDecision.block` carries no context field, so a downstream block drops the bridge context — which is correct: a blocked prompt never reaches the model, so context attached to it is moot. Only a real `deny`/`block` from the hook itself short-circuits. Tests assert a later listener can still block a prompt a context-only hook allowed, and that both contexts survive when the downstream also adds one.
+
+### CLAUDE_PROJECT_DIR defaults to the session workspace
+
+Claude Code always exports `CLAUDE_PROJECT_DIR`, and common unmodified hooks reference `$CLAUDE_PROJECT_DIR` for project-relative paths. An explicit `config.projectDir` wins; when it is omitted (the default ACP wiring configures only `configPath`), the bridge defaults the env var per-run to the agent's session workspace — the same `session.header.cwd` the hook already runs in — rather than leaving it empty. So a stock project-relative hook works in the default setup.
+
+### Containment
+
+The config is parsed ONCE at load; a read/parse failure logs and registers nothing rather than crashing boot (a typo'd path must not take the agent down). Only `type: 'command'` hooks run — a `prompt`/`agent`/HTTP hook (CC) or an `async: true` / non-command hook (Codex) is parsed-and-skipped with a warning. The emit-listener paths (`session-start`, `subagent/start`) run detached, with their `inject` contained in a `.catch` that logs (a throwing inject must not break session boot or the loop).
+
+### Where hooks run, and where their config comes from
+
+Two different cwds, kept distinct on purpose. The hooks **themselves** run in the agent's **session workspace**: for the agent-scoped points the bridge threads the session's `cwd` (`session/new.cwd`, on the session header) to `runHook` as the process working directory, so a hook's `pwd` / relative-file read / marker write operates in the user's project tree, not the server's launch directory. The **config path**, by contrast, is **process-level**: `configPath` is resolved and parsed once at load against the process launch cwd, so a single `hooks.json` applies to the whole process — there is no per-session config discovery that reads a project-local `hooks.json` from each `session/new.cwd` (`TODO(per-session-hook-config)`). This is an honest limitation of the current cut: the example `cordis.yml` documents that its `./hooks.json` is process-level, not per-project.
+
+## Deferred (faithful-but-degraded)
+
+- **Tool-input rewrite.** A CC/Codex `updatedInput` is logged + warned, not honored — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)), because the pre-execution args are read by `tool/call` audit + `assistant/message` history + ACP/tool-bash presentation, so an honest rewrite is a design unit, not a field.
+- **Stop loop-guard** (`TODO(stop-loop-guard)`). CC/Codex break an infinite force-continue with `stop_hook_active` (true once a Stop hook fired this run) plus a max-consecutive cap; both are deferred. Today `stop_hook_active` is always `false`, so a Stop hook that unconditionally blocks would force-continue every step — a hook author must self-limit until the guard lands.
+- **Permission `ask`** degrades to `deny` at the `tools/pre-execute` seam (`FIXME(permissions)` in the interception-seams RFC) — there is no interactive permission prompt yet.
+- **Hook `continue:false` (hard halt).** A hook can ask to halt the whole run (CC/Codex `continue:false`); the shared merge folds it into `MergedHookOutcome.stop`/`stopReason`, but no bridge acts on it (`TODO(hook-continue-false)`) — the interception seams have no "hard-halt the agent" primitive yet (a Decision blocks/steers a single point, not the run). Deferred with the loop-guard work; the halt request is recorded in the `hook/result` log, and the hook keeps its per-point effect (decision/context) meanwhile.
+- **Config discovery.** The path is explicit in `cordis.yml` and process-level (see above); the full multi-layer CC/Codex precedence walk, per-session project-local discovery, and the trust/hash model are not reimplemented (`TODO(per-session-hook-config)`).
+- **Session-start / subagent-start context is best-effort, not gated (`TODO(session-start-gating)`).** `agent/session-start` is a synchronous emit and the bridge runs its hook on a detached `.then`, so the injected `additionalContext` is not guaranteed to land before the first turn reaches the model — a slow hook can miss the first request (the context then arrives as a later injection). `subagent/start` is sharper: an in-process provider may have already queued the child's prompt before the listener runs, and a short-lived child can finish before the detached inject fires. Making startup context a gated/awaited primitive is a loop-level change deferred to the interception seams; today the contract is "injected as soon as the hook resolves", not "before the first request". The bridge tests do NOT wait on the injection where they assert the guaranteed-timing behavior, so they document the real (best-effort) timing rather than masking it.
+
+### Multiple hooks on one point run serially, not concurrently
+
+The reference engines run a point's matched hooks concurrently and fold the results. These bridges run them **serially** (`await` per hook inside the match loop) and fold with the same most-restrictive merge. Serial is deliberate: it keeps each hook's `hook/invoked`/`hook/result` pair adjacent and in a deterministic order in the session log, and the fold is order-independent for the decision (`deny > ask > allow`) so the outcome matches. The cost is latency (hook *N* waits for hook *N−1*) and that per-hook timeouts are not overlapped — acceptable for the hook counts real configs use; revisit if a config ever fans out enough for the wall-clock to matter.
+
+## Consequences
+
+The bridges are thin and readable standalone: the correctness-critical halves (matcher semantics, exit-code contract, merge precedence) live in the shared `dsh-hook-protocol`, so each bridge is just config-parse + payload-build + outcome-map. Each is covered at per-file 100% — config-parse branches as unit tests, and the seam mappings end-to-end through the REAL loop + REAL `dsh-bash-local` + REAL shell scripts from a temp `hooks.json` (a scripted mock MODEL is the only stand-in), plus a real-Loader export-shape guard so a stray default export can't silently drop `inject`. Because the seams already carry typed Decisions, a future native plugin needs none of this bridge machinery — it returns a Decision directly.
diff --git a/examples/AGENTS.md b/examples/AGENTS.md
index c5a797f5df..c7219d3a18 100644
--- a/examples/AGENTS.md
+++ b/examples/AGENTS.md
@@ -21,6 +21,6 @@ A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_P
 |---|---|---|
 | `echo-agent` | `tests/echo.e2e.ts` — boots the real `cordis.yml`, drives the echo tool round-trip and the direct canned reply | **N/A — keyless by nature** (the `mock-echo` model has no real provider) |
 | `coding-agent` | `tests/keyless-smoke.e2e.ts` — boots the full real tree (dummy key, no prompt → no model call), asserts banner + clean exit | `tests/{full-loop,coding-task,resume,compaction,todo-write}.e2e.ts` — real model + real bash + real todo_write, world-verified |
-| `acp-agent` | `pnpm run test:snapshot` — boots the real ACP subprocess and replays a recorded session keyless; `tests/acp.e2e.ts` also asserts stdout purity without a key | `tests/acp.e2e.ts` — real ACP prompt, verifies a file the agent wrote |
+| `acp-agent` | `pnpm run test:snapshot` — boots the real ACP subprocess and replays a recorded session keyless (incl. `hook-prompt-block`, where a `UserPromptSubmit` hook blocks the prompt); `tests/acp.e2e.ts` also asserts stdout purity without a key | `tests/acp.e2e.ts` — real ACP prompt, verifies a file the agent wrote; `tests/hooks.e2e.ts` — a real `PreToolUse` hook blocks bash, verifies the file is NOT written |
 
 See [the root AGENTS.md](../AGENTS.md) for repo-wide conventions and [docs/architecture.md](../docs/architecture.md) for the design.
diff --git a/examples/acp-agent/cordis.snapshot.yml b/examples/acp-agent/cordis.snapshot.yml
index 8a6f17d012..42f4435623 100644
--- a/examples/acp-agent/cordis.snapshot.yml
+++ b/examples/acp-agent/cordis.snapshot.yml
@@ -99,3 +99,16 @@
 
 - id: tool-fs
   name: '@deepseek-ai/dsh-tool-fs'
+
+# The Claude Code hook bridge. `configPath` is read ONCE at load and resolves
+# `./hooks.json` against the PROCESS cwd (not per-session) — in these snapshot
+# runs the harness launches the subprocess with process cwd = the scenario's temp
+# workspace, so a scenario that ships `workspace/hooks.json` (copied into that cwd
+# before the run) exercises the hooks path end-to-end; every other scenario has no
+# such file, so the parse fails-soft and the bridge registers nothing (a silent
+# no-op — the ACP app loads no logger exporter, so the warning never reaches
+# stdout). Hooks themselves run in the session cwd (the bridge passes it as workdir).
+- id: hooks-claude
+  name: '@deepseek-ai/dsh-hooks-claude'
+  config:
+    configPath: ./hooks.json
diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml
index 35c3176f34..d4f4cec1e8 100644
--- a/examples/acp-agent/cordis.yml
+++ b/examples/acp-agent/cordis.yml
@@ -112,3 +112,18 @@
 
 - id: tool-fs
   name: '@deepseek-ai/dsh-tool-fs'
+
+# The Claude Code hook bridge. `configPath` is PROCESS-LEVEL: it is read ONCE at
+# load and the relative `./hooks.json` resolves against the ACP server's launch
+# cwd, NOT each `session/new.cwd`. So a single `hooks.json` next to where the
+# server starts applies to every session; a project-local, per-session hooks.json
+# is NOT discovered (per-session config resolution is a TODO — see the bridge
+# README). With no file present the parse fails-soft and the bridge registers
+# nothing (a silent no-op). Hooks THEMSELVES run in the session cwd (the bridge
+# passes it as the workdir); only WHERE the config is read from is process-level.
+# stdout is the ACP JSON-RPC channel — the bridge's warnings go through ctx.logger
+# (no exporter here), never to stdout.
+- id: hooks-claude
+  name: '@deepseek-ai/dsh-hooks-claude'
+  config:
+    configPath: ./hooks.json
diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts
index cd14e8dc2e..6b345a2a60 100644
--- a/examples/acp-agent/tests/acp.snapshot.ts
+++ b/examples/acp-agent/tests/acp.snapshot.ts
@@ -29,12 +29,22 @@ interface Scenario {
   name: string
   /** Whether the scenario drives at least one model turn (so a JSONL golden applies). */
   hasModelTurn: boolean
+  /**
+   * Whether the run persists a comparable session log to diff against the
+   * `session.jsonl` fixture. Defaults to {@link hasModelTurn} (a model turn
+   * always produces a log worth comparing). Set it independently for a scenario
+   * that produces a non-trivial log WITHOUT a model turn — e.g. a prompt blocked
+   * by a `UserPromptSubmit` hook, which opens a `rejected` turn carrying `hook/*`
+   * events but never calls the model.
+   */
+  comparesLog?: boolean
   /**
    * Whether `test:snapshot:record` regenerates this scenario's `session.jsonl`
    * from the LIVE API. `recorded` scenarios are model-driven and reproducible;
    * `authored` scenarios (a hand-written `replay.override.json` sidecar drives
    * replay — e.g. a provider error or a cancel, which the live API can't be
-   * coaxed into deterministically) are NEVER re-recorded.
+   * coaxed into deterministically — or a deterministic hook scenario whose
+   * derived empty script needs no sidecar) are NEVER re-recorded.
    */
   recorded: boolean
   /**
@@ -68,6 +78,11 @@ const SCENARIOS: Scenario[] = [
   { name: 'subagent-multi', hasModelTurn: true, recorded: true, childSessions: 2 },
   { name: 'subagent-fork', hasModelTurn: true, recorded: true, childSessions: 1 },
   { name: 'subagent-mixed', hasModelTurn: true, recorded: true, childSessions: 2 },
+  // A UserPromptSubmit hook blocks the prompt before any step runs: no model
+  // call (keyless, authored — its derived script is empty so it needs no
+  // sidecar), but it persists a `rejected` turn carrying `hook/*` events, so its
+  // log IS compared. The hooks.json riding in workspace/ drives the bridge.
+  { name: 'hook-prompt-block', hasModelTurn: false, comparesLog: true, recorded: false },
 ]
 
 /** The sibling child-fixture paths for a scenario (`session.1.jsonl` …). */
@@ -146,12 +161,15 @@ for (const scenario of SCENARIOS) {
       await expect(normalizeStdout(result.rawStdout, ctx))
         .toMatchFileSnapshot(join(dir, 'stdout.golden.jsonl'))
 
-      if (scenario.hasModelTurn) {
+      // A model turn always produces a log worth comparing; a hook scenario can
+      // produce one without a model turn (a `rejected` turn carrying `hook/*`).
+      const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn
+      if (comparesLog) {
         // The harvested logs (primary-first) must match their committed fixtures
         // 1:1. Each side passes through normalizeSessionLog, scrubbed against ITS
         // OWN volatile values — the live run's via `ctx`, the committed fixture's
         // via its own header (a committed file cannot share the live run's ids).
-        expect(result.sessionLogs.length, 'a model scenario must persist a session log').toBe(childSessions + 1)
+        expect(result.sessionLogs.length, 'this scenario must persist a session log').toBe(childSessions + 1)
         const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)]
         for (let i = 0; i < fixtureFiles.length; i++) {
           const harvested = (result.sessionLogs[i] as HarvestedLog).content
diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts
new file mode 100644
index 0000000000..40a8d37457
--- /dev/null
+++ b/examples/acp-agent/tests/hooks.e2e.ts
@@ -0,0 +1,122 @@
+import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
+import { Readable, Writable } from 'node:stream'
+import { mkdtemp, rm, writeFile, access } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { afterEach, describe, expect, it } from 'vitest'
+import {
+  ClientSideConnection,
+  ndJsonStream,
+  PROTOCOL_VERSION,
+  type Agent as AcpAgent,
+  type Client,
+  type RequestPermissionRequest,
+  type RequestPermissionResponse,
+  type SessionNotification,
+} from '@agentclientprotocol/sdk'
+
+/**
+ * With-key e2e: the Claude Code hook bridge running against the REAL acp-agent
+ * subprocess and the REAL model. The example `cordis.yml` loads `dsh-hooks-claude`
+ * with a PROCESS-LEVEL `configPath` of `./hooks.json`, resolved once at load
+ * against the ACP server's launch cwd (NOT per-session); this test sets that
+ * launch cwd to the temp workspace and writes a `hooks.json` there with a
+ * PreToolUse hook that BLOCKS every bash command, then asks the live model to
+ * write a file — and verifies the WORLD (the file never appears on disk),
+ * proving the hook actually intercepted execution rather than the agent merely
+ * claiming it couldn't. (The hook itself then runs in the session cwd.)
+ * Key-gated; owns and disposes its subprocess.
+ *
+ * A keyless companion lives in acp.e2e.ts (stdout purity + session/new); the
+ * full hook-fires-end-to-end transcript is the keyless `hook-prompt-block`
+ * snapshot scenario. This one closes the "green plumbing, broken product" gap:
+ * only a real model deciding to call bash exercises the PreToolUse seam live.
+ */
+
+const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url))
+const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
+const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
+const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
+
+interface Spawned {
+  child: ChildProcessWithoutNullStreams
+  client: ClientSideConnection
+  updates: SessionNotification['update'][]
+  stderr: string[]
+}
+
+function spawnAcpAgent(cwd: string): Spawned {
+  const child = spawn(
+    process.execPath,
+    ['--import', tsxLoader, binScript, configPath],
+    { cwd, env: { ...process.env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] },
+  )
+  const stderr: string[] = []
+  child.stderr.setEncoding('utf8')
+  child.stderr.on('data', (chunk: string) => stderr.push(chunk))
+
+  const updates: SessionNotification['update'][] = []
+  const stream = ndJsonStream(
+    Writable.toWeb(child.stdin) as WritableStream<Uint8Array>,
+    Readable.toWeb(child.stdout) as ReadableStream<Uint8Array>,
+  )
+  const makeClient = (_agent: AcpAgent): Client => ({
+    sessionUpdate(params: SessionNotification): Promise<void> {
+      updates.push(params.update)
+      return Promise.resolve()
+    },
+    requestPermission(_params: RequestPermissionRequest): Promise<RequestPermissionResponse> {
+      return Promise.resolve({ outcome: { outcome: 'cancelled' } })
+    },
+  })
+  const client = new ClientSideConnection(makeClient, stream)
+  return { child, client, updates, stderr }
+}
+
+let spawned: Spawned | undefined
+let workdir: string | undefined
+
+afterEach(async () => {
+  if (spawned) {
+    spawned.child.kill('SIGKILL')
+    spawned = undefined
+  }
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
+})
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook blocks bash (real model)', () => {
+  it('denies every bash command, so the requested file is never written (verified on disk)', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'acp-hooks-e2e-'))
+    // A PreToolUse hook that blocks EVERY tool (exit 2, no matcher = match-all).
+    // The session cwd is `workdir`, and the bridge resolves `./hooks.json` from
+    // the process cwd (the launch dir = workdir), so this is the config it loads.
+    await writeFile(join(workdir, 'hooks.json'), JSON.stringify({
+      hooks: { PreToolUse: [{ hooks: [{ type: 'command', command: 'echo "bash blocked by policy" >&2; exit 2' }] }] },
+    }))
+
+    spawned = spawnAcpAgent(workdir)
+    const { client, updates } = spawned
+
+    await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await client.newSession({ cwd: workdir, mcpServers: [] })
+
+    const res = await client.prompt({
+      sessionId,
+      prompt: [{ type: 'text', text: 'Use the bash tool to write the exact text HOOK_FAIL into a file named proof.txt in the current directory. Then stop.' }],
+    })
+    // The turn completes normally (the block is a tool-result error fed back to
+    // the model, not a turn failure).
+    expect(['end_turn', 'max_tokens']).toContain(res.stopReason)
+
+    // Verify the WORLD: the hook denied execution, so the file must NOT exist —
+    // a keyword probe a "cheating" agent could fake in prose cannot pass this.
+    await expect(access(join(workdir, 'proof.txt'))).rejects.toThrow()
+
+    // The client still saw a tool_call stream (the model TRIED), and its result
+    // carried the hook's block reason back as an error.
+    const toolCalls = updates.filter(u => u.sessionUpdate === 'tool_call' || u.sessionUpdate === 'tool_call_update')
+    expect(toolCalls.length).toBeGreaterThan(0)
+  }, 180_000)
+})
diff --git a/examples/acp-agent/tests/snapshot-normalize.spec.ts b/examples/acp-agent/tests/snapshot-normalize.spec.ts
index b220344bb9..bfe29af8a5 100644
--- a/examples/acp-agent/tests/snapshot-normalize.spec.ts
+++ b/examples/acp-agent/tests/snapshot-normalize.spec.ts
@@ -90,4 +90,21 @@ describe('normalizeSessionLog', () => {
     const out = normalizeSessionLog(`${header({ id: ctx.sessionIds[0] })}\n`, ctx)
     expect(out).toContain('{{sessionId}}')
   })
+
+  it('zeroes a hook/result durationMs (run-to-run noise) but keeps its decision', () => {
+    const ev = JSON.stringify({
+      type: 'hook/result', seq: 2, time: 5,
+      data: { turn: 1, point: 'UserPromptSubmit', handlerId: 'h', decision: 'block', exitCode: 2, durationMs: 37 },
+    })
+    const out = normalizeSessionLog(`${header({})}\n${ev}\n`, ctx)
+    expect(out).toContain('"durationMs":0')
+    expect(out).not.toContain('37')
+    expect(out).toContain('"decision":"block"') // the decision is the behavior — kept
+  })
+
+  it('leaves a non-hook event durationMs untouched (only hook/result is scrubbed)', () => {
+    const ev = JSON.stringify({ type: 'tool/result', seq: 2, time: 5, data: { durationMs: 88 } })
+    const out = normalizeSessionLog(`${header({})}\n${ev}\n`, ctx)
+    expect(out).toContain('"durationMs":88')
+  })
 })
diff --git a/examples/acp-agent/tests/snapshot-normalize.ts b/examples/acp-agent/tests/snapshot-normalize.ts
index db0d493535..8150057fa4 100644
--- a/examples/acp-agent/tests/snapshot-normalize.ts
+++ b/examples/acp-agent/tests/snapshot-normalize.ts
@@ -8,7 +8,8 @@
  * Scrubbed: `randomUUID()` session ids → `{{sessionId}}`; the temp `mkdtemp`
  * cwd → `{{cwd}}` (it appears in terminal-card `_meta` and the log header);
  * JSON-RPC request `id` → a stable per-transcript sequence; the log's per-event
- * `time` (epoch ms) and header `createdAt` → 0. NOT scrubbed: the log's `seq`
+ * `time` (epoch ms) and header `createdAt` → 0; a `hook/result` event's
+ * `durationMs` (wall-clock hook runtime) → 0. NOT scrubbed: the log's `seq`
  * (deterministic — `seq = log.length`, part of the event-log contract).
  *
  * See docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
@@ -97,6 +98,13 @@ export function normalizeSessionLog(rawLog: string, ctx: NormalizeContext): stri
     } else if ('time' in record) {
       // Event line: zero the epoch-ms timestamp; keep seq (deterministic).
       record.time = 0
+      // A hook/result carries the hook's wall-clock runtime (`data.durationMs`),
+      // which is run-to-run noise like `time` — zero it so the golden reflects
+      // the hook's decision/exit, not how long the shell took.
+      if (record.type === 'hook/result' && record.data !== null && typeof record.data === 'object') {
+        const data = record.data as Record<string, unknown>
+        if ('durationMs' in data) data.durationMs = 0
+      }
     }
     return scrubValue(record, ctx) as Record<string, unknown>
   })
diff --git a/examples/acp-agent/tests/snapshots/hook-prompt-block/input.json b/examples/acp-agent/tests/snapshots/hook-prompt-block/input.json
new file mode 100644
index 0000000000..1995199566
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/hook-prompt-block/input.json
@@ -0,0 +1,7 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "Delete everything in the repo." }
+  ]
+}
diff --git a/examples/acp-agent/tests/snapshots/hook-prompt-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-prompt-block/session.jsonl
new file mode 100644
index 0000000000..b5f81fdaea
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/hook-prompt-block/session.jsonl
@@ -0,0 +1,6 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
+{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"hook/invoked","seq":1,"time":0,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"claude","handlerId":"claude:UserPromptSubmit:1"}}
+{"type":"hook/result","seq":2,"time":0,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"claude:UserPromptSubmit:1","decision":"block","exitCode":2,"stderrSummary":"blocked by policy hook","durationMs":0}}
+{"type":"prompt/blocked","seq":3,"time":0,"data":{"content":[{"type":"text","text":"Delete everything in the repo."}],"source":{"kind":"user"},"reason":"blocked by policy hook"}}
+{"type":"turn/end","seq":4,"time":0,"data":{"turn":1,"reason":{"kind":"rejected","reason":"blocked by policy hook"}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-prompt-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-prompt-block/stdout.golden.jsonl
new file mode 100644
index 0000000000..6f6e5b662f
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/hook-prompt-block/stdout.golden.jsonl
@@ -0,0 +1,3 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}}
diff --git a/examples/acp-agent/tests/snapshots/hook-prompt-block/workspace/hooks.json b/examples/acp-agent/tests/snapshots/hook-prompt-block/workspace/hooks.json
new file mode 100644
index 0000000000..ee3da88fb1
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/hook-prompt-block/workspace/hooks.json
@@ -0,0 +1,11 @@
+{
+  "hooks": {
+    "UserPromptSubmit": [
+      {
+        "hooks": [
+          { "type": "command", "command": "echo 'blocked by policy hook' >&2; exit 2" }
+        ]
+      }
+    ]
+  }
+}
diff --git a/packages/README.md b/packages/README.md
index a570d4c995..2233123772 100644
--- a/packages/README.md
+++ b/packages/README.md
@@ -116,6 +116,8 @@ The rule: **extension** plugins depend on interfaces, never on the concrete loop
 | `tool-subagent/` | `subagent` | Model-facing `subagent` delegation tool over `ctx.subagents` | (registers on `ctx.tools`) |
 | `tool-todo/` | `todo` | Model-facing `todo_write` tool; writes the whole task list to the session log (`todo/write`) | (registers on `ctx.tools`) |
 | `hook-protocol/` | `hooks` | Shared Claude Code / Codex hook wire-protocol library: matcher, codec, `runHook`, merge, `hook/*` events | (none — library, no service) |
+| `hooks-claude/` | `hooks` | Bridge: runs a Claude Code `hooks.json` / settings on the interception seams | (registers event listeners) |
+| `hooks-codex/` | `hooks` | Bridge: runs a Codex `hooks.json` (a subset of the CC protocol) on the seams | (registers event listeners) |
 | `brand/` | `util` | Type-only `Branded<B>` nominal-typing primitive (no runtime code, no harness deps) | (none — type-only) |
 
 Each package has its own `README.md` with purpose, service API, events, extension points, and deliberate non-goals (TODOs).
diff --git a/packages/hooks/hooks-claude/README.md b/packages/hooks/hooks-claude/README.md
new file mode 100644
index 0000000000..ce1c6b090a
--- /dev/null
+++ b/packages/hooks/hooks-claude/README.md
@@ -0,0 +1,54 @@
+# @deepseek-ai/dsh-hooks-claude
+
+A cordis plugin that runs a user's existing **Claude Code** hook config (a `hooks.json`, or a settings file's `hooks` key) on the harness's canonical interception seams. It is the **CC dialect** half of the hooks subsystem: it owns CC's per-event stdin payloads, CC's env + `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the mapping from a hook's neutral outcome onto the harness's typed Decisions. The dialect-agnostic primitives (matcher, exit-code/stdout codec, `ctx.bash` execution, most-restrictive merge, the `hook/*` events) come from [`@deepseek-ai/dsh-hook-protocol`](../hook-protocol/README.md).
+
+A native cordis plugin could do everything this bridge does — more powerfully, with typed returns and no serialization boundary. **The bridge exists only to run UNMODIFIED external CC hooks faithfully**; anything bespoke should be a native plugin on the same seams (see [the interception-seams RFC](../../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)).
+
+## Config
+
+```ts
+import type { Config } from '@deepseek-ai/dsh-hooks-claude'
+const config: Config = {
+  configPath: '/path/to/hooks.json', // required: a hooks.json or a settings file with a `hooks` key
+  pluginRoot: '/path/to/plugin',     // optional: replaces ${CLAUDE_PLUGIN_ROOT} in command strings
+  projectDir: '/path/to/project',    // optional: replaces ${CLAUDE_PROJECT_DIR} AND sets the hook env var; defaults to the session cwd when omitted
+  defaultTimeoutMs: 600_000,         // optional: per-hook timeout when a hook sets none (CC default)
+}
+```
+
+In a `cordis.yml`:
+
+```yaml
+- dsh-hooks-claude:
+    configPath: ./.claude/hooks.json
+    pluginRoot: ./.claude/plugins/my-plugin
+    projectDir: .
+```
+
+The config is parsed **once** at load. `configPath` is **process-level**: a relative path resolves against the process's launch cwd at load time, so a single config applies to the whole process — there is no per-session (`session/new.cwd`) config discovery yet (`TODO(per-session-hook-config)`). A read/parse failure is contained — the bridge logs a warning and registers nothing rather than crashing boot (a typo'd path must not take the agent down). Only `type: 'command'` hooks run; a `prompt`/`agent`/HTTP hook is parsed-and-skipped with a warning.
+
+The hooks **themselves** run in the agent's session workspace: for the agent-scoped points the bridge passes the session's `cwd` (the `session/new.cwd`) as the hook process's working directory, so a hook's `pwd`/relative-path/marker operates in the user's project tree, not the server launch dir.
+
+## Hook points → seam Decisions
+
+| CC hook | Harness seam | Mapping |
+|---|---|---|
+| `SessionStart` | `agent/session-start` (emit) | additionalContext → `agent.inject()` into the new session (cannot block) |
+| `UserPromptSubmit` | `agent/prompt-submit` (waterfall) | `deny` → `PromptDecision.block`; additionalContext-only → delegate via `next()` then fold context onto the downstream decision (a later listener can still block/rewrite) |
+| `PreToolUse` | `tools/pre-execute` (waterfall) | `deny` → `PreToolDecision.deny`; `ask` → `PreToolDecision.ask` |
+| `PostToolUse` | `tools/post-execute` (waterfall) | `deny` → `block` with feedback; additionalContext-only → delegate via `next()` then fold context onto the downstream decision |
+| `Stop` | `agent/turn-continuation` (waterfall) | a blocking Stop hook forces `continue`, feeding its reason as next-step steering |
+| `SubagentStart` | `subagent/start` (emit) | additionalContext → `agent.inject()` into the live child |
+| `SubagentStop` | `subagent/end` (emit) | observe-only |
+
+The matcher subject is the tool name (`PreToolUse`/`PostToolUse`), the session source (`SessionStart`), or a constant `agent_type` of `general-purpose` (`SubagentStart`/`SubagentStop` — the harness subagent seam carries no per-kind label, so the bridge reports Claude Code's own Task-tool default; a default/`*`/empty `agent_type` matcher fires, a specific-kind matcher does not); `UserPromptSubmit`/`Stop` ignore matchers. Multiple file-configured hooks on one point run **serially, in config order**, and fold most-restrictively (`deny > ask > allow`, see `dsh-hook-protocol`); serial keeps each hook's `hook/invoked`/`hook/result` pair adjacent in the log, and the fold is order-independent for the decision (see the RFC's "run serially, not concurrently" note).
+
+## Context source
+
+Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-claude' }` source. `agent.inject()` defaults a missing source to `{ kind: 'user' }`, which would mislabel plugin context as a user prompt — so the bridge always names itself.
+
+## Deferred (faithful-but-degraded)
+
+- **`updatedInput` (tool-input rewrite)** is logged + warned, **not honored** — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)).
+- **`systemMessage`** (a hook's user-facing warning) is logged + warned, **not surfaced** — there is no user-message channel on these seams yet (only model-facing `additionalContext`). The shared merge collects it; the bridge does not yet render it.
+- **Stop loop-guard.** CC breaks an infinite force-continue with `stop_hook_active` (true once a Stop hook has fired this run) plus a max-consecutive cap; both are deferred (`TODO(stop-loop-guard)`). Today `stop_hook_active` is always `false`, so a Stop hook that unconditionally blocks would force-continue every step — a hook author must self-limit until the guard lands.
diff --git a/packages/hooks/hooks-claude/package.json b/packages/hooks/hooks-claude/package.json
new file mode 100644
index 0000000000..5cc39f9999
--- /dev/null
+++ b/packages/hooks/hooks-claude/package.json
@@ -0,0 +1,49 @@
+{
+  "name": "@deepseek-ai/dsh-hooks-claude",
+  "description": "Bridge plugin: run a Claude Code hooks.json / settings hook config on the DeepSeek Harness interception seams",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "dependencies": {
+    "schemastery": "^3.18.0"
+  },
+  "peerDependencies": {
+    "@deepseek-ai/dsh-agent": "^0.0.1",
+    "@deepseek-ai/dsh-hook-protocol": "^0.0.1",
+    "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-session": "^0.0.1",
+    "@deepseek-ai/dsh-subagent": "^0.0.1",
+    "@deepseek-ai/dsh-tools": "^0.0.1",
+    "cordis": "^4.0.0-rc.6"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-agent-loop": "workspace:^",
+    "@deepseek-ai/dsh-bash": "workspace:^",
+    "@deepseek-ai/dsh-bash-local": "workspace:^",
+    "@deepseek-ai/dsh-hook-protocol": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "@deepseek-ai/dsh-subagent": "workspace:^",
+    "@deepseek-ai/dsh-system-prompt": "workspace:^",
+    "@deepseek-ai/dsh-tools": "workspace:^",
+    "cordis": "^4.0.0-rc.6"
+  }
+}
diff --git a/packages/hooks/hooks-claude/src/config.ts b/packages/hooks/hooks-claude/src/config.ts
new file mode 100644
index 0000000000..d78486e58a
--- /dev/null
+++ b/packages/hooks/hooks-claude/src/config.ts
@@ -0,0 +1,100 @@
+/**
+ * Parse a Claude Code hook config file into the shared {@link MatcherGroup}
+ * shape, faithfully to CC's `hooks.json` / settings `hooks` key format.
+ *
+ * A CC config maps each event name to an array of matcher groups, each holding
+ * an array of typed hooks. Only `type: 'command'` hooks run here; other types
+ * (`prompt`/`agent`/`http`) are PARSED but skipped with a warning (faithful-but-
+ * degraded — the same stance Codex takes). The `command` string undergoes
+ * `${CLAUDE_PLUGIN_ROOT}` substitution at parse time so the runner sees a literal.
+ *
+ * @module @deepseek-ai/dsh-hooks-claude/config
+ */
+
+import type { MatcherGroup } from '@deepseek-ai/dsh-hook-protocol'
+
+/** A parsed CC config: event name → its matcher groups (command hooks only). */
+export type ClaudeHookConfig = Record<string, MatcherGroup[]>
+
+/** A skipped non-command hook, surfaced so the bridge can warn about it. */
+export interface SkippedHook {
+  event: string
+  type: string
+}
+
+/** The outcome of parsing one config file: the runnable groups + what was skipped. */
+export interface ParsedClaudeConfig {
+  config: ClaudeHookConfig
+  skipped: SkippedHook[]
+}
+
+/** Substitution variables applied to each `command` string at parse time. */
+export interface SubstitutionVars {
+  /** Replaces `${CLAUDE_PLUGIN_ROOT}` — the plugin's root dir. */
+  pluginRoot?: string
+  /** Replaces `${CLAUDE_PROJECT_DIR}` — the project root. */
+  projectDir?: string
+}
+
+/** A plain (non-null, non-array) object, else undefined. */
+function asObject(value: unknown): Record<string, unknown> | undefined {
+  return typeof value === 'object' && value !== null && !Array.isArray(value)
+    ? value as Record<string, unknown>
+    : undefined
+}
+
+/** Apply `${CLAUDE_PLUGIN_ROOT}` / `${CLAUDE_PROJECT_DIR}` substitution to a command string. */
+export function substituteCommand(command: string, vars: SubstitutionVars): string {
+  let out = command
+  if (vars.pluginRoot !== undefined) out = out.split('${CLAUDE_PLUGIN_ROOT}').join(vars.pluginRoot)
+  if (vars.projectDir !== undefined) out = out.split('${CLAUDE_PROJECT_DIR}').join(vars.projectDir)
+  return out
+}
+
+/**
+ * Parse a raw Claude Code config object (the value under the `hooks` key, or a
+ * `hooks.json` whose top level IS that map) into runnable {@link MatcherGroup}s.
+ * Non-command hooks and malformed entries are dropped (recorded in `skipped` /
+ * silently ignored) rather than throwing — a bad hook config must not crash boot.
+ * `vars` are substituted into every surviving `command`.
+ */
+export function parseClaudeConfig(raw: unknown, vars: SubstitutionVars = {}): ParsedClaudeConfig {
+  const config: ClaudeHookConfig = {}
+  const skipped: SkippedHook[] = []
+  // Accept either `{ hooks: { … } }` (a settings file) or the bare event map.
+  const root = asObject(raw)
+  const hooksMap = root ? asObject(root.hooks) ?? root : undefined
+  if (!hooksMap) return { config, skipped }
+
+  for (const [event, rawGroups] of Object.entries(hooksMap)) {
+    if (!Array.isArray(rawGroups)) continue
+    const groups: MatcherGroup[] = []
+    for (const rawGroup of rawGroups) {
+      const group = asObject(rawGroup)
+      if (!group || !Array.isArray(group.hooks)) continue
+      const commands: MatcherGroup['hooks'] = []
+      for (const rawHook of group.hooks) {
+        const hook = asObject(rawHook)
+        if (!hook) continue
+        const type = typeof hook.type === 'string' ? hook.type : 'command'
+        if (type !== 'command') {
+          skipped.push({ event, type })
+          continue
+        }
+        if (typeof hook.command !== 'string') continue
+        commands.push({
+          command: substituteCommand(hook.command, vars),
+          ...typeof hook.timeout === 'number' ? { timeoutSec: hook.timeout } : {},
+        })
+      }
+      if (commands.length === 0) continue
+      groups.push({
+        ...typeof group.matcher === 'string' ? { matcher: group.matcher } : {},
+        hooks: commands,
+      })
+    }
+    if (groups.length > 0) config[event] = groups
+  }
+
+  return { config, skipped }
+}
diff --git a/packages/hooks/hooks-claude/src/index.ts b/packages/hooks/hooks-claude/src/index.ts
new file mode 100644
index 0000000000..6151a11c44
--- /dev/null
+++ b/packages/hooks/hooks-claude/src/index.ts
@@ -0,0 +1,413 @@
+/**
+ * `dsh-hooks-claude` — a bridge plugin that runs a user's existing Claude Code
+ * hook config (`hooks.json` / a settings file's `hooks` key) on the harness's
+ * canonical interception seams. It is the CC DIALECT half of the hooks
+ * subsystem: it owns CC's per-event stdin payloads, CC's env +
+ * `${CLAUDE_PLUGIN_ROOT}` substitution, and the mapping from a hook's neutral
+ * outcome onto the harness's typed Decisions. The dialect-agnostic primitives
+ * (matcher, exit-code/stdout codec, `ctx.bash` execution, most-restrictive
+ * merge, the `hook/*` events) come from `@deepseek-ai/dsh-hook-protocol`.
+ *
+ * A native cordis plugin could do everything this bridge does — more powerfully,
+ * with typed returns and no serialization boundary. The bridge exists only to
+ * run UNMODIFIED external CC hooks faithfully; anything bespoke should be a
+ * native plugin on the same seams.
+ *
+ * Scope: the seven in-scope hook points (`SessionStart`, `UserPromptSubmit`,
+ * `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, `SubagentStop`). Only
+ * `type: 'command'` hooks run; the matcher group config + exit-code/stdout
+ * protocol are byte-faithful to CC. `updatedInput` (tool-input rewrite) is
+ * logged + warned, not honored (deferred — see the interception-seams RFC).
+ *
+ * @module @deepseek-ai/dsh-hooks-claude
+ */
+
+import { readFileSync } from 'node:fs'
+import type { Context } from 'cordis'
+import z from 'schemastery'
+import type { Agent, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent'
+import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
+import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
+import {
+  appendHookInvoked,
+  appendHookResult,
+  matchesMatcher,
+  mergeHookOutputs,
+  runHook,
+  type HookOutput,
+  type MatcherGroup,
+  type MergedHookOutcome,
+} from '@deepseek-ai/dsh-hook-protocol'
+// Side-effect type import: pulls in the `subagent/start` + `subagent/end` event
+// declarations (declaration-merged into cordis `Events` by dsh-subagent) so the
+// SubagentStart/SubagentStop listeners below type-check.
+import type {} from '@deepseek-ai/dsh-subagent'
+import { parseClaudeConfig, type ClaudeHookConfig } from './config.ts'
+
+export const name = 'hooks-claude'
+// `bash` is required to run hooks; the rest are read opportunistically via
+// ctx.get so a deployment can load this bridge without every seam present.
+export const inject = ['bash']
+
+/** Plugin config: where the CC hook config lives + substitution roots. */
+export interface Config {
+  /**
+   * Path to a `hooks.json` or a settings file whose `hooks` key holds the config.
+   * PROCESS-LEVEL: read once at load, a relative path resolves against the process
+   * launch cwd, so one config applies to the whole process.
+   * TODO(per-session-hook-config): per-session discovery of a project-local
+   * `hooks.json` from each `session/new.cwd` is not yet implemented.
+   */
+  configPath: string
+  /**
+   * Replaces `${CLAUDE_PLUGIN_ROOT}` in command strings (the plugin's root dir).
+   */
+  pluginRoot?: string
+  /**
+   * Replaces `${CLAUDE_PROJECT_DIR}` in command strings AND is exported as the
+   * `CLAUDE_PROJECT_DIR` env var for hook processes. When omitted, the env var
+   * defaults per-run to the agent's session workspace (`session.header.cwd`, the
+   * same dir the hook runs in) — Claude Code always exports this var, and common
+   * unmodified hooks reference `$CLAUDE_PROJECT_DIR` for project-relative paths.
+   */
+  projectDir?: string
+  /** Default per-hook timeout in ms when a hook sets none (CC default: 600000). */
+  defaultTimeoutMs?: number
+}
+
+export const Config: z<Config> = z.object({
+  configPath: z.string().required(),
+  pluginRoot: z.string(),
+  projectDir: z.string(),
+  defaultTimeoutMs: z.number().default(600_000),
+})
+
+/** A stable per-handler id so an invoked/result pair correlates in the log. */
+let handlerCounter = 0
+function nextHandlerId(point: string): string {
+  return `claude:${point}:${++handlerCounter}`
+}
+
+/** The `{kind:'plugin'}` source stamped on every context this bridge injects. */
+const PLUGIN_SOURCE: MessageSource = { kind: 'plugin', plugin: 'hooks-claude' }
+
+/** Truncate a stderr blob for the `hook/result` summary field. */
+function summarize(stderr: string): string | undefined {
+  const t = stderr.trim()
+  if (t.length === 0) return undefined
+  return t.length > 500 ? t.slice(0, 500) + '…' : t
+}
+
+export function apply(ctx: Context, config: Config): void {
+  // --- Parse the config ONCE at load. A read/parse failure is contained: the
+  // bridge logs and registers nothing rather than crashing boot (a typo'd path
+  // must not take the agent down). ---
+  let parsed: ClaudeHookConfig = {}
+  try {
+    const raw: unknown = JSON.parse(readFileSync(config.configPath, 'utf8'))
+    const result = parseClaudeConfig(raw, {
+      ...config.pluginRoot !== undefined ? { pluginRoot: config.pluginRoot } : {},
+      ...config.projectDir !== undefined ? { projectDir: config.projectDir } : {},
+    })
+    parsed = result.config
+    for (const s of result.skipped) {
+      ctx.logger.warn(`hooks-claude: skipping unsupported "${s.type}" hook on ${s.event} (only command hooks run)`)
+    }
+  } catch (error: unknown) {
+    ctx.logger.warn(`hooks-claude: could not load hook config "${config.configPath}": ${String(error)} — no hooks registered`)
+    return
+  }
+
+  const defaultTimeoutMs = config.defaultTimeoutMs ?? 600_000
+
+  /**
+   * Run every command hook configured for `point` whose matcher selects
+   * `matchQuery`, with the per-event `payload` on stdin, and fold the results.
+   * Writes a `hook/invoked`/`hook/result` pair per hook into the session when one
+   * is available (the mid-turn points always have an open turn). Returns the
+   * merged outcome (a neutral, already-most-restrictive view) for the caller to
+   * map onto its seam decision. `matchQuery` is the event's matcher subject
+   * (tool name, session source, …); `''` for events that ignore matchers.
+   */
+  async function runPoint(
+    point: string,
+    matchQuery: string,
+    payload: unknown,
+    opts: { agent?: Agent; turn?: number; signal?: AbortSignal },
+  ): Promise<MergedHookOutcome> {
+    const groups: MatcherGroup[] = parsed[point] ?? []
+    const outputs: HookOutput[] = []
+    // Run the hook in the AGENT'S session workspace (the `session/new` cwd on the
+    // session header), not the executor default (the ACP server's launch dir).
+    // A hook that does `pwd`, reads a relative file, or writes a marker must
+    // operate in the user's project tree. Absent for a no-agent run (falls back
+    // to the executor default).
+    const workdir = opts.agent?.session.header.cwd
+    // CLAUDE_PROJECT_DIR: an explicit config value wins; otherwise default it to
+    // the session workspace (the same dir the hook RUNS in). Claude Code always
+    // exports this var, and common unmodified hooks reference `$CLAUDE_PROJECT_DIR`
+    // (shell expansion at run time) for project-relative paths — leaving it empty
+    // in the default ACP wiring (no `projectDir` configured) would break them even
+    // though the bridge already knows the workspace. Absent only for a no-agent run
+    // with no configured projectDir (nothing to point at).
+    const projectDir = config.projectDir ?? workdir
+    const hookEnv = projectDir !== undefined ? { CLAUDE_PROJECT_DIR: projectDir } : undefined
+    for (const group of groups) {
+      if (!matchesMatcher(group.matcher, matchQuery, 'claude')) continue
+      for (const hook of group.hooks) {
+        const handlerId = nextHandlerId(point)
+        const session = opts.agent?.session
+        if (session && opts.turn !== undefined) {
+          appendHookInvoked(session, {
+            turn: opts.turn, point, dialect: 'claude', handlerId,
+            ...group.matcher !== undefined ? { matcher: group.matcher } : {},
+          })
+        }
+        const { output, durationMs } = await runHook(ctx.bash, hook, {
+          payload,
+          ...hookEnv ? { env: hookEnv } : {},
+          ...workdir !== undefined ? { cwd: workdir } : {},
+          ...opts.signal ? { signal: opts.signal } : {},
+          defaultTimeoutMs,
+          trailingNewline: true,
+          // Discard a `hookSpecificOutput` block whose `hookEventName` names a
+          // different event than the one firing (the schemas key it by event).
+          expectedEventName: point,
+        }, () => performance.now())
+        outputs.push(output)
+        if (output.updatedInput !== undefined) {
+          ctx.logger.warn(`hooks-claude: ${point} hook requested updatedInput, which is not yet honored (ignored)`)
+        }
+        if (output.systemMessage !== undefined) {
+          ctx.logger.warn(`hooks-claude: ${point} hook emitted a systemMessage, which is not yet surfaced (ignored)`)
+        }
+        if (session && opts.turn !== undefined) {
+          const stderrSummary = summarize(output.stderr)
+          appendHookResult(session, {
+            turn: opts.turn, point, handlerId,
+            decision: output.decision ?? (output.continue === false ? 'stop' : 'pass'),
+            ...output.exitCode !== undefined ? { exitCode: output.exitCode } : {},
+            ...stderrSummary !== undefined ? { stderrSummary } : {},
+            durationMs,
+          })
+        }
+      }
+    }
+    return mergeHookOutputs(outputs)
+  }
+
+  // TODO(hook-continue-false): the merge computes `merged.stop`/`stopReason` from
+  // a hook's `continue:false`, but no seam below honors it — there is no
+  // "hard-halt the whole agent" primitive on the interception seams yet (a
+  // Decision can block/deny/steer a single point, not stop the run). Honoring it
+  // needs that primitive; deferred with the loop-guard work. Until then a
+  // `continue:false` hook still has its per-point effect (its decision/context),
+  // and the halt request is recorded in the `hook/result` log but not acted on.
+
+  /** Build a HookContext from accumulated additionalContext strings, or undefined when none. */
+  function contextFrom(merged: MergedHookOutcome): HookContext | undefined {
+    if (merged.additionalContext.length === 0) return undefined
+    const content: ContentBlock[] = merged.additionalContext.map(text => ({ type: 'text', text }))
+    return { content, source: PLUGIN_SOURCE }
+  }
+
+  /**
+   * Concatenate this bridge's {@link HookContext} (`ours`, always present at the
+   * call sites) with a downstream listener's optional one, so folding our
+   * additionalContext onto a delegated decision drops neither. The merged block
+   * carries a single `source` — this bridge's — because a `HookContext` holds one
+   * `MessageSource` and the seam cannot represent mixed provenance; the rendered
+   * `context/message` only distinguishes by `source.kind` ('plugin'), so a
+   * downstream plugin's text is still correctly framed as plugin context, not a
+   * user prompt.
+   */
+  function concatContext(ours: HookContext, theirs: HookContext | undefined): HookContext {
+    if (!theirs) return ours
+    return { content: [...ours.content, ...theirs.content], source: ours.source }
+  }
+
+  // --- SessionStart: emit (cannot block). Inject any additionalContext into the
+  // agent. The matcher subject is the source.
+  // TODO(session-start-gating): `agent/session-start` is a SYNCHRONOUS emit and
+  // this hook runs on a detached `.then`, so the injected context is BEST-EFFORT
+  // — it is not guaranteed to land before the first turn reaches the model. A
+  // slow hook can miss the first request (the context then arrives as a later
+  // injection turn). Gating startup on the hook is a loop-level change deferred
+  // to the interception seams; today the contract is "injected as soon as the
+  // hook resolves", not "before the first request". ---
+  ctx.on('agent/session-start', (agent, source) => {
+    void runPoint('SessionStart', source, sessionStartPayload(agent, source), { agent })
+      .then((merged) => {
+        const context = contextFrom(merged)
+        if (context) agent.inject(context.content, { source: context.source })
+      })
+      .catch((error: unknown) => {
+        ctx.logger.warn(`hooks-claude: SessionStart hook failed: ${String(error)}`)
+      })
+  })
+
+  // --- UserPromptSubmit → PromptDecision. The prompt text is the payload; no
+  // matcher subject (CC ignores matchers for this event). ---
+  ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise<PromptDecision> => {
+    const turn = lastTurn(agent)
+    const merged = await runPoint('UserPromptSubmit', '', promptPayload(agent, content), { agent, turn })
+    if (merged.decision === 'deny') {
+      return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' }
+    }
+    // Our hooks did not block. DELEGATE (attaching context alone is not a veto):
+    // a later `agent/prompt-submit` listener must still get to block or rewrite.
+    // Then fold our additionalContext onto its decision — a downstream block wins
+    // (a dropped prompt makes the context moot; `block` carries no context field).
+    const downstream = await next()
+    const ours = contextFrom(merged)
+    if (!ours || downstream.kind !== 'allow') return downstream
+    return {
+      kind: 'allow',
+      ...downstream.content !== undefined ? { content: downstream.content } : {},
+      additionalContext: concatContext(ours, downstream.additionalContext),
+    }
+  })
+
+  // --- PreToolUse → PreToolDecision. Matcher subject is the tool name. ---
+  ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
+    const turn = lastTurn(exec.agent)
+    const merged = await runPoint('PreToolUse', exec.name, preToolPayload(exec), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
+    if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' }
+    if (merged.decision === 'ask') return { kind: 'ask', ...merged.reason !== undefined ? { reason: merged.reason } : {} }
+    return next()
+  })
+
+  // --- PostToolUse → PostToolDecision. Matcher subject is the tool name. ---
+  ctx.on('tools/post-execute', async (exec, result, next): Promise<PostToolDecision> => {
+    const turn = lastTurn(exec.agent)
+    const merged = await runPoint('PostToolUse', exec.name, postToolPayload(exec, result), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
+    const context = contextFrom(merged)
+    if (merged.decision === 'deny') {
+      return { kind: 'block', feedback: [{ type: 'text', text: merged.reason ?? 'blocked by PostToolUse hook' }], ...context ? { additionalContext: context } : {} }
+    }
+    // Our hooks did not block. DELEGATE so a later listener can still block/replace,
+    // then fold our context onto its decision (a downstream block carries it too).
+    const downstream = await next()
+    if (!context) return downstream
+    if (downstream.kind === 'block') {
+      return { ...downstream, additionalContext: concatContext(context, downstream.additionalContext) }
+    }
+    return {
+      kind: 'accept',
+      ...downstream.content !== undefined ? { content: downstream.content } : {},
+      additionalContext: concatContext(context, downstream.additionalContext),
+    }
+  })
+
+  // --- Stop → ContinuationDecision. CC's Stop hook can force the conversation to
+  // CONTINUE (block the stop) with stderr/reason as the continuation. No matcher.
+  // TODO(stop-loop-guard): CC breaks an infinite force-continue with
+  // `stop_hook_active` (set true once a Stop hook has already fired this run) plus
+  // a max-consecutive cap; both are deferred. Today `stop_hook_active` is always
+  // false, so a Stop hook that unconditionally blocks would force-continue every
+  // step — a hook author must self-limit until the guard lands. ---
+  ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise<ContinuationDecision> => {
+    const merged = await runPoint('Stop', '', stopPayload(agent), { agent, turn })
+    if (merged.decision === 'deny') {
+      // A blocking Stop hook forces continuation. It carries its reason as
+      // next-step steering; a blocking hook that emitted no reason (exit 2, empty
+      // stderr) still forces the turn to continue — the block is what matters, so
+      // fall back to a generic steering line rather than letting the turn stop.
+      const text = merged.reason ?? 'continue: blocked by Stop hook'
+      return { action: 'continue', reason: { content: [{ type: 'text', text }], source: PLUGIN_SOURCE } }
+    }
+    return next()
+  })
+
+  // --- SubagentStart / SubagentStop: observe-only emits (the subagent seam is
+  // observe-only this cut). A SubagentStart hook's additionalContext is injected
+  // into the live child; SubagentStop only observes. Both look the live child up
+  // so the hook runs in the child's session workspace and the payload carries
+  // the child's session_id/cwd (see subagentPayload). The matcher subject is the
+  // CC-default `agent_type` (SUBAGENT_TYPE) — the harness seam carries no
+  // per-kind label, so a config's default/`*`/empty agent_type matcher fires and
+  // a specific-kind matcher does not (documented in the RFC). ---
+  ctx.on('subagent/start', (info) => {
+    const child = ctx.get('agents')?.get(info.id)
+    void runPoint('SubagentStart', SUBAGENT_TYPE, subagentPayload('SubagentStart', info, child), { ...child ? { agent: child } : {} })
+      .then((merged) => {
+        const context = contextFrom(merged)
+        if (context && child) child.inject(context.content, { source: context.source })
+      })
+      .catch((error: unknown) => { ctx.logger.warn(`hooks-claude: SubagentStart hook failed: ${String(error)}`) })
+  })
+  ctx.on('subagent/end', (info) => {
+    // Look up the child (still recoverable: `subagent/end` fires from the
+    // service's detached `.then` BEFORE the tool caller's `await run.result`
+    // disposes it) so the hook runs in the child's cwd, not the server default.
+    // No `.then`/inject follows (SubagentStop only observes), and no `turn` is
+    // passed (so no `hook/*` log records), so runPoint has nothing that can
+    // reject — no `.catch` is needed. Fire-and-forget.
+    const child = ctx.get('agents')?.get(info.id)
+    void runPoint('SubagentStop', SUBAGENT_TYPE, subagentPayload('SubagentStop', info, child), { ...child ? { agent: child } : {} })
+  })
+}
+
+/**
+ * The `agent_type` value the bridge reports for SubagentStart/Stop. The harness
+ * subagent seam carries no per-kind label, so the bridge uses Claude Code's own
+ * Task-tool default — a hooks.json with a default/`*`/empty `agent_type` matcher
+ * fires; a config matching a specific kind (e.g. `code-reviewer`) does not.
+ */
+const SUBAGENT_TYPE = 'general-purpose'
+
+// --- Per-event stdin payloads (the CC DIALECT shape). Field names match CC's
+// hook input schema; this is the part a bridge owns. ---
+
+/** The last (open or just-closed) turn number in the agent's log, or 0. */
+function lastTurn(agent: Agent | undefined): number {
+  if (!agent) return 0
+  const last = [...agent.session.events].findLast(e => e.type === 'turn/start')
+  /* v8 ignore next -- the `: 0` arm is a defensive fallback: lastTurn is only
+     called from the mid-turn seams (prompt-submit/pre-/post-execute/continuation),
+     which always run inside an open turn, so `last` is always a turn/start here. */
+  return last?.type === 'turn/start' ? last.data.turn : 0
+}
+
+/** Flatten content blocks to the text a hook payload carries (the common case). */
+function blocksToText(content: ContentBlock[]): string {
+  return content.filter((b): b is Extract<ContentBlock, { type: 'text' }> => b.type === 'text').map(b => b.text).join('')
+}
+
+function base(agent: Agent | undefined, event: string): Record<string, unknown> {
+  return {
+    session_id: agent?.session.header.id ?? '',
+    cwd: agent?.session.header.cwd ?? process.cwd(),
+    hook_event_name: event,
+  }
+}
+
+function sessionStartPayload(agent: Agent, source: string): Record<string, unknown> {
+  return { ...base(agent, 'SessionStart'), source }
+}
+function promptPayload(agent: Agent, content: ContentBlock[]): Record<string, unknown> {
+  return { ...base(agent, 'UserPromptSubmit'), prompt: blocksToText(content) }
+}
+function preToolPayload(exec: ToolExecution): Record<string, unknown> {
+  return { ...base(exec.agent, 'PreToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId }
+}
+function postToolPayload(exec: ToolExecution, result: ToolExecutionResult): Record<string, unknown> {
+  return { ...base(exec.agent, 'PostToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId, tool_response: blocksToText(result.content) }
+}
+function stopPayload(agent: Agent): Record<string, unknown> {
+  return { ...base(agent, 'Stop'), stop_hook_active: false }
+}
+/**
+ * Build a SubagentStart/SubagentStop payload from the CC base (the child's
+ * `session_id`/`cwd` when the child agent is available) plus the subagent-hook
+ * fields. `agent_type` is the CC-default {@link SUBAGENT_TYPE}; `stop_hook_active`
+ * is present on SubagentStop only (the loop-guard flag, always false this cut).
+ */
+function subagentPayload(event: 'SubagentStart' | 'SubagentStop', info: { id: string }, child: Agent | undefined): Record<string, unknown> {
+  return {
+    ...base(child, event),
+    agent_id: info.id,
+    agent_type: SUBAGENT_TYPE,
+    ...event === 'SubagentStop' ? { stop_hook_active: false } : {},
+  }
+}
diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts
new file mode 100644
index 0000000000..3e36231e66
--- /dev/null
+++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts
@@ -0,0 +1,365 @@
+import { afterEach, describe, expect, it } from 'vitest'
+import { mkdtempSync, rmSync, writeFileSync, chmodSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { Context } from 'cordis'
+import Loader from '@cordisjs/plugin-loader'
+import LlmService from '@deepseek-ai/dsh-llm'
+import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude'
+import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
+
+/**
+ * Full-loop bridge tests: a scripted mock MODEL drives the REAL agent loop + REAL
+ * bash executor, and the REAL `dsh-hooks-claude` bridge runs REAL shell hook
+ * scripts written to a temp dir — only the model is mocked (the "prefer the real
+ * implementation" rule). Each test writes a `hooks.json` + executable scripts,
+ * loads the bridge pointed at them, and asserts the hook's effect on the loop.
+ */
+
+const dirs: string[] = []
+afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) })
+
+/** Write a hooks.json + named executable scripts into a fresh temp dir. */
+function writeConfig(hooks: unknown, scripts: Record<string, string> = {}): string {
+  const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+  dirs.push(dir)
+  writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks }))
+  for (const [name, body] of Object.entries(scripts)) {
+    const path = join(dir, name)
+    writeFileSync(path, body)
+    chmodSync(path, 0o755)
+  }
+  return dir
+}
+
+async function harness(configDir: string, adapter: MockAdapter): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(AgentLoop, { agents: [] })
+  await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+  await ctx.plugin(HooksClaude, { configPath: join(configDir, 'hooks.json') })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+
+function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = ctx.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') { dispose(); resolve() }
+    })
+  })
+}
+
+function events(agent: ReactLoopAgent): SessionEvent[] {
+  return [...agent.session.events]
+}
+
+/**
+ * Poll `predicate` until it returns true or the deadline passes. Detached
+ * emit-listener hooks (session-start, subagent) fire on a `.then` the test can't
+ * await directly; polling for the observable EFFECT is robust under load, where a
+ * single fixed sleep flakes ("async state is not synchronous state").
+ */
+async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise<void> {
+  const deadline = Date.now() + timeout
+  while (!predicate()) {
+    if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline')
+    await new Promise(r => setTimeout(r, interval))
+  }
+}
+
+describe('hooks-claude bridge — UserPromptSubmit', () => {
+  it('a UserPromptSubmit hook that exits 2 blocks the prompt (rejected turn)', async () => {
+    // The UserPromptSubmit hook exits 2 (blocking) with a reason on stderr.
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    const block = join(dir, 'block.sh')
+    writeFileSync(block, '#!/usr/bin/env bash\necho "prompt denied by policy" >&2\nexit 2\n')
+    chmodSync(block, 0o755)
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { UserPromptSubmit: [{ hooks: [{ type: 'command', command: block }] }] } }))
+
+    const adapter = new MockAdapter([textResponse('should not run')])
+    const ctx = await harness(dir, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'do something' }])
+    await waitForIdle(ctx, agent)
+
+    // The prompt was blocked: model never called, turn ended rejected.
+    expect(adapter.requests).toHaveLength(0)
+    const turnEnd = events(agent).findLast(e => e.type === 'turn/end')
+    expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('rejected')
+    // The hook ran and was recorded.
+    expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'UserPromptSubmit')).toBe(true)
+    expect(events(agent).some(e => e.type === 'hook/result' && e.data.decision === 'block')).toBe(true)
+  })
+
+  it('a UserPromptSubmit hook printing additionalContext injects it for the model', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    const ctxScript = join(dir, 'ctx.sh')
+    writeFileSync(ctxScript, '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"remember: be brief"}}\'\n')
+    chmodSync(ctxScript, 0o755)
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { UserPromptSubmit: [{ hooks: [{ type: 'command', command: ctxScript }] }] } }))
+
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(dir, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    // The injected context reached the model and is recorded with the plugin source.
+    expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('remember: be brief')
+    const ctxMsg = events(agent).find(e => e.type === 'context/message')
+    expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'hooks-claude' })
+  })
+})
+
+describe('hooks-claude bridge — PreToolUse', () => {
+  it('a matching PreToolUse hook that exits 2 denies the tool (isError result), tool never runs', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    const deny = join(dir, 'deny.sh')
+    writeFileSync(deny, '#!/usr/bin/env bash\necho "danger tool blocked" >&2\nexit 2\n')
+    chmodSync(deny, 0o755)
+    // Matcher "danger" (literal) selects only the danger tool.
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { PreToolUse: [{ matcher: 'danger', hooks: [{ type: 'command', command: deny }] }] } }))
+
+    const adapter = new MockAdapter([toolCallResponse('c1', 'danger', {}), textResponse('done')])
+    const ctx = await harness(dir, adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'use danger' }])
+    await waitForIdle(ctx, agent)
+
+    expect(ran).toBe(false)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('danger tool blocked'))).toBe(true)
+  })
+
+  it('a PreToolUse hook whose matcher does NOT match leaves the tool alone', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    const deny = join(dir, 'deny.sh')
+    writeFileSync(deny, '#!/usr/bin/env bash\nexit 2\n')
+    chmodSync(deny, 0o755)
+    // Matcher only targets "danger" — the "safe" tool is untouched.
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { PreToolUse: [{ matcher: 'danger', hooks: [{ type: 'command', command: deny }] }] } }))
+
+    const adapter = new MockAdapter([toolCallResponse('c1', 'safe', {}), textResponse('done')])
+    const ctx = await harness(dir, adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'use safe' }])
+    await waitForIdle(ctx, agent)
+
+    expect(ran).toBe(true)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(false)
+  })
+})
+
+describe('hooks-claude bridge — PostToolUse', () => {
+  it('a PostToolUse hook that blocks (exit 2) turns the result into an isError with feedback', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    const block = join(dir, 'block.sh')
+    writeFileSync(block, '#!/usr/bin/env bash\necho "output rejected, retry" >&2\nexit 2\n')
+    chmodSync(block, 0o755)
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { PostToolUse: [{ hooks: [{ type: 'command', command: block }] }] } }))
+
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(dir, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    const result = events(agent).find(e => e.type === 'tool/result')
+    // PostToolUse blocks AFTER the tool ran: the result is rewritten to isError + feedback.
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('output rejected, retry'))).toBe(true)
+  })
+
+  it('a PostToolUse hook printing additionalContext attaches it after the tool result', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    const s = join(dir, 'ctx.sh')
+    writeFileSync(s, '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"note: tool was slow"}}\'\n')
+    chmodSync(s, 0o755)
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] } }))
+
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(dir, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    const log = events(agent)
+    const resultIdx = log.findIndex(e => e.type === 'tool/result')
+    const ctxIdx = log.findIndex(e => e.type === 'context/message')
+    expect(ctxIdx).toBeGreaterThan(resultIdx) // context appended AFTER the tool result
+    const ctxMsg = log[ctxIdx]
+    expect(ctxMsg?.type === 'context/message' && ctxMsg.data.content.some(b => b.type === 'text' && b.text.includes('tool was slow'))).toBe(true)
+  })
+
+  it('a PreToolUse permissionDecision:ask degrades to ask (the tool is gated, not run)', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    const s = join(dir, 'ask.sh')
+    writeFileSync(s, '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"ask","permissionDecisionReason":"needs approval"}}\'\n')
+    chmodSync(s, 0o755)
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] } }))
+
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(dir, adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    // `ask` degrades to deny today (FIXME permissions): the tool does not run and the result is isError.
+    expect(ran).toBe(false)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('needs approval'))).toBe(true)
+  })
+})
+
+describe('hooks-claude bridge — SessionStart', () => {
+  it('a SessionStart hook injects additionalContext the first request sees', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    const s = join(dir, 'start.sh')
+    writeFileSync(s, '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"project uses tabs"}}\'\n')
+    chmodSync(s, 0o755)
+    // matcher 'startup' selects the startup source.
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: { SessionStart: [{ matcher: 'startup', hooks: [{ type: 'command', command: s }] }] } }))
+
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(dir, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    // session-start fires async (detached .then → agent.inject); wait for the
+    // injected context/message to actually land before sending, rather than a
+    // fixed sleep that flakes under load.
+    await waitFor(() => events(agent).some(e => e.type === 'context/message'
+      && e.data.content.some(b => b.type === 'text' && b.text.includes('project uses tabs'))))
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('project uses tabs')
+  })
+})
+
+describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => {
+  it('runs SubagentStart and SubagentStop hooks when the subagent lifecycle events fire', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-'))
+    dirs.push(dir)
+    // Each hook touches a marker file so we can assert it ran (these events are
+    // observe-only — there is no decision to assert, only the side effect).
+    const startMarker = join(dir, 'start-ran')
+    const stopMarker = join(dir, 'stop-ran')
+    const startHook = join(dir, 'start.sh')
+    const stopHook = join(dir, 'stop.sh')
+    writeFileSync(startHook, `#!/usr/bin/env bash\ntouch "${startMarker}"\n`)
+    writeFileSync(stopHook, `#!/usr/bin/env bash\ntouch "${stopMarker}"\n`)
+    chmodSync(startHook, 0o755)
+    chmodSync(stopHook, 0o755)
+    writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks: {
+      SubagentStart: [{ hooks: [{ type: 'command', command: startHook }] }],
+      SubagentStop: [{ hooks: [{ type: 'command', command: stopHook }] }],
+    } }))
+
+    const adapter = new MockAdapter([])
+    const ctx = await harness(dir, adapter)
+    // Drive the observe-only lifecycle events directly (no real child needed — the
+    // bridge just listens). The agents registry is absent here, so SubagentStart's
+    // child lookup yields undefined and it simply runs the hook.
+    ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') })
+    ctx.emit('subagent/end', { provider: 'inproc', id: AgentId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] })
+
+    // Both hooks run async (detached .then); poll for their marker files rather
+    // than a fixed sleep that flakes under load.
+    const { existsSync } = await import('node:fs')
+    await waitFor(() => existsSync(startMarker) && existsSync(stopMarker))
+    expect(existsSync(startMarker)).toBe(true)
+    expect(existsSync(stopMarker)).toBe(true)
+  })
+})
+
+describe('hooks-claude bridge — load resilience', () => {
+  it('a missing config file registers no hooks and does not crash the loop', async () => {
+    const adapter = new MockAdapter([textResponse('fine')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+    await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' })
+    ctx.llm.registerAdapter(['mock'], adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    // The turn ran normally — no hooks, no crash.
+    expect(adapter.requests).toHaveLength(1)
+  })
+
+  it('disposing the bridge fiber removes its listeners (HMR safety)', async () => {
+    // A BLOCKING UserPromptSubmit hook: if the listener leaked past dispose it
+    // would veto the prompt (0 model requests) and log a hook/invoked. Build the
+    // ctx WITHOUT the harness's own bridge mount so this is the ONLY mount, then
+    // dispose it — a leaked listener fails the test (a no-op `true` hook would
+    // pass even leaked, so it proved nothing).
+    const dir = writeConfig({ UserPromptSubmit: [{ hooks: [{ type: 'command', command: 'exit 2' }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+    const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') })
+    await fiber.dispose()
+    ctx.llm.registerAdapter(['mock'], adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone
+    expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) // no hook ran
+  })
+
+  it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/apply', () => {
+    // Postmortem 0001 guard: this plugin HAS `inject = ['bash']`, so a stray
+    // `export default apply` would collapse the module via `unwrapExports`
+    // (`exports.default ?? exports`), DROP `inject`, and crash at load with
+    // "cannot get property … without inject". Guard the shape directly.
+    expect('default' in HooksClaude).toBe(false)
+    expect(HooksClaude.name).toBe('hooks-claude')
+    expect(HooksClaude.inject).toEqual(['bash'])
+    const loader = Object.create(Loader.prototype) as Loader
+    const unwrapped = loader.unwrapExports(HooksClaude) as Record<string, unknown>
+    expect(unwrapped).toBe(HooksClaude)
+    expect(unwrapped.name).toBe('hooks-claude')
+    expect(unwrapped.inject).toEqual(['bash'])
+    expect(typeof unwrapped.apply).toBe('function')
+  })
+})
diff --git a/packages/hooks/hooks-claude/tests/config.spec.ts b/packages/hooks/hooks-claude/tests/config.spec.ts
new file mode 100644
index 0000000000..f635ef0fd9
--- /dev/null
+++ b/packages/hooks/hooks-claude/tests/config.spec.ts
@@ -0,0 +1,66 @@
+import { describe, expect, it } from 'vitest'
+import { parseClaudeConfig, substituteCommand } from '@deepseek-ai/dsh-hooks-claude/src/config.ts'
+
+describe('substituteCommand', () => {
+  it('replaces CLAUDE_PLUGIN_ROOT and CLAUDE_PROJECT_DIR (all occurrences)', () => {
+    expect(substituteCommand('${CLAUDE_PLUGIN_ROOT}/x.sh', { pluginRoot: '/p' })).toBe('/p/x.sh')
+    expect(substituteCommand('${CLAUDE_PROJECT_DIR}/a ${CLAUDE_PROJECT_DIR}/b', { projectDir: '/proj' })).toBe('/proj/a /proj/b')
+    expect(substituteCommand('${CLAUDE_PLUGIN_ROOT}-${CLAUDE_PROJECT_DIR}', { pluginRoot: '/p', projectDir: '/d' })).toBe('/p-/d')
+  })
+  it('leaves the command untouched when no vars are supplied', () => {
+    expect(substituteCommand('${CLAUDE_PLUGIN_ROOT}/x', {})).toBe('${CLAUDE_PLUGIN_ROOT}/x')
+  })
+})
+
+describe('parseClaudeConfig', () => {
+  it('parses a bare event map and a settings-style { hooks: … } wrapper identically', () => {
+    const groups = { PreToolUse: [{ matcher: 'Bash', hooks: [{ type: 'command', command: 'x.sh' }] }] }
+    const bare = parseClaudeConfig(groups)
+    const wrapped = parseClaudeConfig({ hooks: groups })
+    expect(bare.config).toEqual(wrapped.config)
+    expect(bare.config.PreToolUse).toEqual([{ matcher: 'Bash', hooks: [{ command: 'x.sh' }] }])
+  })
+
+  it('carries timeout → timeoutSec and substitutes the command', () => {
+    const { config } = parseClaudeConfig(
+      { Stop: [{ hooks: [{ type: 'command', command: '${CLAUDE_PLUGIN_ROOT}/s.sh', timeout: 30 }] }] },
+      { pluginRoot: '/p' },
+    )
+    expect(config.Stop).toEqual([{ hooks: [{ command: '/p/s.sh', timeoutSec: 30 }] }])
+  })
+
+  it('skips non-command hooks (recorded) and keeps the command ones in the same group', () => {
+    const { config, skipped } = parseClaudeConfig({
+      PreToolUse: [{ hooks: [
+        { type: 'prompt', prompt: 'hi' },
+        { type: 'command', command: 'ok.sh' },
+        { type: 'http', url: 'http://x' },
+      ] }],
+    })
+    expect(config.PreToolUse).toEqual([{ hooks: [{ command: 'ok.sh' }] }])
+    expect(skipped).toEqual([{ event: 'PreToolUse', type: 'prompt' }, { event: 'PreToolUse', type: 'http' }])
+  })
+
+  it('treats a hook with no `type` as a command (CC default)', () => {
+    const { config } = parseClaudeConfig({ Stop: [{ hooks: [{ command: 'd.sh' }] }] })
+    expect(config.Stop).toEqual([{ hooks: [{ command: 'd.sh' }] }])
+  })
+
+  it('drops malformed entries without throwing: non-array groups, non-object group/hook, missing command, empty groups', () => {
+    expect(parseClaudeConfig({ PreToolUse: 'nope' }).config).toEqual({})
+    expect(parseClaudeConfig({ PreToolUse: [42, { hooks: 'no' }, { hooks: [7, { type: 'command' }] }] }).config).toEqual({})
+    // a group whose only hook lacks a command string drops the whole (empty) group
+    expect(parseClaudeConfig({ Stop: [{ hooks: [{ type: 'command', command: 5 }] }] }).config).toEqual({})
+  })
+
+  it('returns empty for a non-object / null / array top level', () => {
+    expect(parseClaudeConfig(null).config).toEqual({})
+    expect(parseClaudeConfig(42).config).toEqual({})
+    expect(parseClaudeConfig([1, 2]).config).toEqual({})
+  })
+
+  it('omits the matcher key when the group has none (match-all)', () => {
+    const { config } = parseClaudeConfig({ Stop: [{ hooks: [{ type: 'command', command: 's.sh' }] }] })
+    expect('matcher' in config.Stop![0]!).toBe(false)
+  })
+})
diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts
new file mode 100644
index 0000000000..63e2f611ce
--- /dev/null
+++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts
@@ -0,0 +1,674 @@
+import { afterEach, describe, expect, it, vi } from 'vitest'
+import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { Context } from 'cordis'
+import LlmService from '@deepseek-ai/dsh-llm'
+import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude'
+import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
+
+/** Targeted branch coverage for the CC bridge: option arms, warn paths, no-agent
+ * fallbacks, contextFrom-empty, and the detached-listener catch handlers. */
+
+const dirs: string[] = []
+afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) })
+
+function dir(): string { const d = mkdtempSync(join(tmpdir(), 'dsh-hc-cov-')); dirs.push(d); return d }
+function sh(d: string, name: string, body: string): string {
+  const p = join(d, name); writeFileSync(p, body); chmodSync(p, 0o755); return p
+}
+function hooks(d: string, h: unknown): string {
+  writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json')
+}
+
+type HarnessOpts = { pluginRoot?: string; projectDir?: string }
+async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(AgentLoop, { agents: [] })
+  await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+  await ctx.plugin(HooksClaude, { configPath, ...opts })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+  return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) })
+}
+function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] }
+/** Poll until `predicate` holds or the deadline passes — robust to detached
+ * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */
+async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise<void> {
+  const deadline = Date.now() + timeout
+  while (!predicate()) {
+    if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline')
+    await new Promise(r => setTimeout(r, interval))
+  }
+}
+
+describe('hooks-claude coverage — config option arms + substitution + skip warning', () => {
+  it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => {
+    const d = dir()
+    // ${CLAUDE_PLUGIN_ROOT} resolves to d; the script writes its own cwd-independent marker.
+    const marker = join(d, 'ran')
+    sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`)
+    const path = hooks(d, {
+      PreToolUse: [{ hooks: [
+        { type: 'prompt', prompt: 'skipme' }, // skipped → warn loop
+        { type: 'command', command: '${CLAUDE_PLUGIN_ROOT}/h.sh' }, // substituted
+      ] }],
+    })
+    const warn = vi.fn()
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d })
+    ctx.logger.warn = warn as never
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(existsSync(marker)).toBe(true) // substituted command ran
+  })
+
+  it('warns and honors updatedInput as a no-op (input rewrite deferred)', async () => {
+    const d = dir()
+    const s = sh(d, 'u.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"allow","updatedInput":{"command":"rewritten"}}}\'\n')
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const warn = vi.fn()
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', { command: 'original' }), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.logger.warn = warn as never
+    let sawArgs: unknown
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    // updatedInput is NOT honored — the tool ran with the ORIGINAL args.
+    expect((sawArgs as { command?: string }).command).toBe('original')
+    expect(warn).toHaveBeenCalledWith(expect.stringContaining('updatedInput'))
+  })
+})
+
+describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () => {
+  it('a clean exit-0 hook with no output is a no-op (contextFrom empty → next())', async () => {
+    const d = dir()
+    const s = sh(d, 'noop.sh', '#!/usr/bin/env bash\nexit 0\n')
+    const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('ran')])
+    const ctx = await harness(path, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    // The prompt proceeded unchanged; no context/message injected.
+    expect(adapter.requests).toHaveLength(1)
+    expect(events(agent).some(e => e.type === 'context/message')).toBe(false)
+  })
+
+  it('a PreToolUse hook fires for a no-agent direct tool call (no session/turn to record into)', async () => {
+    const d = dir()
+    const s = sh(d, 'deny.sh', '#!/usr/bin/env bash\necho "no" >&2\nexit 2\n')
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const ctx = await harness(path, new MockAdapter([]))
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } }))
+    // Call execute() directly with NO agent — the bridge's no-agent/no-turn path.
+    const { CallId } = await import('@deepseek-ai/dsh-llm')
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: {} })
+    expect(ran).toBe(false)
+    expect(result.isError).toBe(true)
+  })
+
+  it('a long stderr is truncated in the hook/result summary', async () => {
+    const d = dir()
+    // Emit >500 chars of stderr then exit 2.
+    const s = sh(d, 'long.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n')
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true)
+  })
+})
+
+describe('hooks-claude coverage — Stop continuation + subagent inject/catch', () => {
+  it('a Stop hook that blocks (exit 2) forces the turn to continue (CC dialect)', async () => {
+    const d = dir()
+    const marker = join(d, 'fired')
+    const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\necho "continue please" >&2\nexit 2\n`)
+    const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
+    const ctx = await harness(path, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(2)
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('continue please')
+  })
+
+  it('a Stop hook that blocks with EMPTY stderr still forces continuation (no reason required)', async () => {
+    // Regression: a blocking Stop hook (exit 2) with no stderr yields decision
+    // 'deny' + reason undefined; the turn must STILL force-continue (the block is
+    // what matters), not silently stop. Self-limit to one block so it can't loop.
+    const d = dir()
+    const marker = join(d, 'fired')
+    const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`)
+    const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
+    const ctx = await harness(path, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    // A second model request ran → the empty-reason block forced continuation.
+    expect(adapter.requests).toHaveLength(2)
+    // The steering carried the fallback reason (no stderr to use).
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook')
+  })
+
+  it('SubagentStart additionalContext is injected into a REGISTERED live child', async () => {
+    const d = dir()
+    const s = sh(d, 'sa.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SubagentStart","additionalContext":"child guidance"}}\'\n')
+    const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] })
+    const ctx = await harness(path, new MockAdapter([]))
+    // Register a fake child agent under the id the event carries.
+    const injected: string[] = []
+    const child = { id: AgentId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters<typeof ctx.agents.register>[0]
+    ctx.agents.register(child)
+    ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-x') })
+    await waitFor(() => injected.includes('child guidance'))
+    expect(injected).toContain('child guidance')
+  })
+
+  it('a throwing SubagentStart/SubagentStop hook run is contained (logged)', async () => {
+    const d = dir()
+    // A hook command that does not exist makes runHook resolve a non-blocking
+    // error (not a throw), so to hit the .catch we make the .then throw: register
+    // a child whose inject throws for SubagentStart.
+    const s = sh(d, 'sa.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SubagentStart","additionalContext":"x"}}\'\n')
+    const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] })
+    const ctx = await harness(path, new MockAdapter([]))
+    const warn = vi.fn(); ctx.logger.warn = warn as never
+    const child = { id: AgentId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters<typeof ctx.agents.register>[0]
+    ctx.agents.register(child)
+    ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-y') })
+    await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed')))
+    expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed'))
+  })
+})
+
+describe('hooks-claude coverage — default reasons + sparse payloads', () => {
+  it('PreToolUse deny with EMPTY stderr uses the default reason', async () => {
+    const d = dir()
+    const s = sh(d, 'deny.sh', '#!/usr/bin/env bash\nexit 2\n') // exit 2, no stderr
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true)
+  })
+
+  it('PostToolUse deny with EMPTY stderr + no context uses the default feedback', async () => {
+    const d = dir()
+    const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n')
+    const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true)
+  })
+
+  it('SubagentStop with no registered child runs the hook cleanly (fire-and-forget)', async () => {
+    const d = dir()
+    // The agents registry has no entry for the id, so the child lookup yields
+    // undefined and the payload falls back to base(undefined) — assert the
+    // observe-only SubagentStop run still executes the hook without crashing.
+    const marker = join(d, 'stopran')
+    const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`)
+    const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] })
+    const ctx = await harness(path, new MockAdapter([]))
+    ctx.emit('subagent/end', { provider: 'p', id: AgentId('child-z'), stopReason: 'completed' })
+    await waitFor(() => existsSync(marker))
+    expect(existsSync(marker)).toBe(true)
+  })
+})
+
+describe('hooks-claude coverage — more default/sparse arms', () => {
+  it('UserPromptSubmit deny with EMPTY stderr uses the default block reason', async () => {
+    const d = dir()
+    const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n')
+    const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('no')])
+    const ctx = await harness(path, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const turnEnd = events(agent).findLast(e => e.type === 'turn/end')
+    expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind === 'rejected' && turnEnd.data.reason.reason).toContain('blocked by UserPromptSubmit hook')
+  })
+
+  it('a PreToolUse ask with NO reason omits the reason (false arm)', async () => {
+    const d = dir()
+    const s = sh(d, 'ask.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"ask"}}\'\n')
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    // ask (no reason) → degrades to deny with the registry's generic message.
+    expect(ran).toBe(false)
+    expect(events(agent).some(e => e.type === 'tool/result' && e.data.isError)).toBe(true)
+  })
+
+  it('a recorded clean exit-0 hook with no stderr omits exitCode-extra/stderrSummary fields', async () => {
+    const d = dir()
+    const s = sh(d, 'noop.sh', '#!/usr/bin/env bash\nexit 0\n')
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0)
+    expect(res?.type === 'hook/result' && 'stderrSummary' in res.data).toBe(false)
+  })
+})
+
+describe('hooks-claude coverage — schema-bypass default + unspawnable hook', () => {
+  it('a direct apply() (schema bypass) defaults the timeout and runs', async () => {
+    const d = dir()
+    const marker = join(d, 'ran')
+    const s = sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`)
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+    // Direct apply with only configPath — bypasses schemastery's defaults, so the
+    // runtime `defaultTimeoutMs ?? 600_000` fallback is exercised.
+    HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') })
+    ctx.llm.registerAdapter(['mock'], adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(existsSync(marker)).toBe(true)
+  })
+
+  it('a non-zero non-2 hook exit (e.g. a command-not-found 127) is a non-blocking error; the tool still runs', async () => {
+    const d = dir()
+    // `bash -c` of a missing program exits 127 — a non-blocking error (not 0, not
+    // 2 → no decision), so the tool proceeds; the hook/result records exit 127.
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: '/nonexistent/definitely/not/a/command' }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(ran).toBe(true)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && res.data.exitCode).toBe(127)
+  })
+
+  it('a PostToolUse deny with empty stderr + no context uses the default feedback (no context arm)', async () => {
+    const d = dir()
+    const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n')
+    const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
+  })
+})
+
+describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => {
+  it('a {"continue":false} hook is RECORDED as decision "stop" but does not halt the run (TODO(hook-continue-false))', async () => {
+    // Honoring `continue:false` (hard-halt the whole run) is deferred — there is
+    // no such primitive on the interception seams yet. So this asserts the LOG
+    // faithfully records the halt request (decision "stop"), AND that the run is
+    // NOT actually halted: the tool still runs and the turn completes normally.
+    const d = dir()
+    const s = sh(d, 'stop.sh', '#!/usr/bin/env bash\necho \'{"continue":false,"stopReason":"halt"}\'\n')
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded
+    expect(ran).toBe(true) // NOT honored: the tool still ran (halt is deferred)
+    const turnEnd = events(agent).findLast(e => e.type === 'turn/end')
+    expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('completed') // ran to completion
+  })
+
+  it('a PostToolUse hook that BOTH blocks AND attaches additionalContext', async () => {
+    const d = dir()
+    const s = sh(d, 'b.sh', '#!/usr/bin/env bash\necho \'{"decision":"block","reason":"bad","hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"context too"}}\'\n')
+    const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true)
+    // additionalContext also injected (the block + context arm).
+    expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('context too')))).toBe(true)
+  })
+
+  it('a PreToolUse hook whose hookSpecificOutput names a DIFFERENT event does NOT deny the tool', async () => {
+    // The block's hookEventName (UserPromptSubmit) mismatches the firing event
+    // (PreToolUse), so its permissionDecision:"deny" is discarded — the tool runs.
+    const d = dir()
+    const s = sh(d, 'x.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","permissionDecision":"deny"}}\'\n')
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran
+  })
+
+  it('defaults CLAUDE_PROJECT_DIR to the session workspace when no projectDir is configured', async () => {
+    // The default ACP wiring sets no projectDir. A stock CC hook that references
+    // $CLAUDE_PROJECT_DIR (shell expansion) must still get the session workspace,
+    // not an empty string. The hook echoes the var as additionalContext.
+    const d = dir()
+    const workspace = dir()
+    const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\nprintf \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"dir=%s"}}\' "$CLAUDE_PROJECT_DIR"\n')
+    const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('ran')])
+    const ctx = await harness(path, adapter) // NB: no projectDir
+    // The factory create() path honors meta.cwd (the plain agentLoop.create() does not).
+    const { SessionId } = await import('@deepseek-ai/dsh-session')
+    const handle = ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } })
+    handle.agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, handle.agent as ReactLoopAgent)
+    expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message'
+      && e.data.content.some(b => b.type === 'text' && b.text.includes(`dir=${workspace}`)))).toBe(true)
+    await handle.dispose()
+  })
+
+  it('a context-only UserPromptSubmit hook DELEGATES so a later listener can still block', async () => {
+    // A hook that only adds context must NOT short-circuit the waterfall: a
+    // downstream agent/prompt-submit listener (a policy plugin) must still get to
+    // block the prompt. The bridge delegates via next() and folds its context.
+    const d = dir()
+    const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"bridge ctx"}}\'\n')
+    const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('should not run')])
+    const ctx = await harness(path, adapter)
+    // A later listener that blocks every prompt (registered AFTER the bridge).
+    const { AgentId: AId } = await import('@deepseek-ai/dsh-agent')
+    ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' }))
+    const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    // the downstream block won: the model was never called, no user/message was
+    // recorded, and the (sole, fully-blocked) prompt closed the turn `rejected`
+    expect(adapter.requests).toHaveLength(0)
+    expect(events(agent).some(e => e.type === 'user/message')).toBe(false)
+    const turnEnd = events(agent).findLast(e => e.type === 'turn/end')
+    expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toMatchObject({ kind: 'rejected', reason: 'policy veto' })
+  })
+
+  it('folds the bridge additionalContext WITH a downstream listener that also adds context', async () => {
+    // Both the bridge hook and a later prompt-submit listener attach context; the
+    // request must see BOTH (concatContext keeps the downstream one too).
+    const d = dir()
+    const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"from-bridge"}}\'\n')
+    const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(path, adapter)
+    ctx.on('agent/prompt-submit', async () => ({
+      kind: 'allow' as const,
+      content: [{ type: 'text' as const, text: 'rewritten-prompt' }],
+      additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } },
+    }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const req = JSON.stringify(adapter.requests[0]!.messages)
+    expect(req).toContain('from-bridge')
+    expect(req).toContain('from-downstream')
+    expect(req).toContain('rewritten-prompt') // downstream content rewrite preserved
+    // the original prompt was replaced by the downstream rewrite
+    const userMsg = events(agent).find(e => e.type === 'user/message')
+    expect(userMsg?.type === 'user/message' && userMsg.data.content.some(b => b.type === 'text' && b.text === 'rewritten-prompt')).toBe(true)
+  })
+
+  it('folds the bridge PostToolUse context onto a downstream ACCEPT that replaces content', async () => {
+    // The bridge hook adds context; a later post-execute listener accepts with a
+    // content rewrite. Both the rewrite and the bridge context survive.
+    const d = dir()
+    const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n')
+    const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true)
+    expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
+  })
+
+  it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => {
+    // The bridge hook only adds context; a later post-execute listener blocks the
+    // result. The block wins AND carries the bridge context (concatContext on the
+    // block arm).
+    const d = dir()
+    const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n')
+    const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true)
+    // the bridge's context still landed (folded onto the block)
+    expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
+  })
+
+})
+
+describe('hooks-claude coverage — executor reject + no-open-turn', () => {
+  it('when the bash executor REJECTS a hook run, the hook/result omits exitCode (non-blocking)', async () => {
+    const d = dir()
+    const s = sh(d, 'h.sh', '#!/usr/bin/env bash\nexit 0\n')
+    const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(path, adapter)
+    // Force the executor to reject (an infrastructure fault) so runHook's catch
+    // yields a HookOutput with exitCode undefined → the `exitCode` spread false arm.
+    const bash = ctx.bash
+    bash.run = (() => Promise.reject(new Error('executor down')))
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false)
+  })
+
+})
+
+describe('hooks-claude coverage — detached-listener catch handlers', () => {
+  it('a throwing SessionStart inject is contained (logged, agent still runs)', async () => {
+    const d = dir()
+    const s = sh(d, 'start.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"x"}}\'\n')
+    const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(path, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    // Make inject throw, forcing the SessionStart .catch path.
+    const original = agent.inject.bind(agent)
+    let threw = false
+    agent.inject = (() => { threw = true; throw new Error('inject boom') })
+    await waitFor(() => threw)
+    expect(threw).toBe(true)
+    agent.inject = original
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(1) // loop survived the thrown inject
+  })
+})
+
+describe('hooks-claude coverage — hook runs in the session cwd, not the server cwd', () => {
+  it('runs an agent-scoped hook in the session workspace even when the executor default differs', async () => {
+    // The bug: the bridge passed no workdir, so hooks ran in the executor default
+    // (the server launch dir), not session/new.cwd. Here the executor default and
+    // the session cwd are DIFFERENT temp dirs; a PreToolUse hook writes `pwd` to a
+    // marker and we assert it ran in the SESSION cwd.
+    const serverDir = dir()
+    const sessionDir = dir()
+    const marker = join(sessionDir, 'where')
+    // The hook is invoked with cwd = session dir, so a relative marker path lands there.
+    hooks(serverDir, { PreToolUse: [{ hooks: [{ type: 'command', command: 'pwd > where' }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    // Executor default cwd = serverDir (deliberately NOT the session cwd).
+    await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir })
+    await ctx.plugin(HooksClaude, { configPath: join(serverDir, 'hooks.json') })
+    ctx.llm.registerAdapter(['mock'], adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+
+    const { SessionId } = await import('@deepseek-ai/dsh-session')
+    const handle = ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } })
+    handle.agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, handle.agent as ReactLoopAgent)
+
+    expect(existsSync(marker)).toBe(true) // the marker landed in the SESSION dir
+    const { readFileSync } = await import('node:fs')
+    const where = readFileSync(marker, 'utf8').trim()
+    // `pwd` may resolve symlinks (/var → /private/var etc.), so compare basenames.
+    expect(where.endsWith(sessionDir.split('/').pop()!)).toBe(true)
+    await handle.dispose()
+  })
+
+  it('runs a SubagentStop hook in the CHILD session workspace, not the server cwd', async () => {
+    // SubagentStop looks the child up (recoverable at subagent/end) and runs the
+    // hook in the CHILD's session cwd, not the executor default. Here the executor
+    // default and the child session cwd are DIFFERENT dirs; a SubagentStop hook
+    // writes `pwd` to a relative marker and we assert it landed in the CHILD dir —
+    // which only holds if the listener threaded the child agent into runPoint.
+    const serverDir = dir()
+    const childDir = dir()
+    const marker = join(childDir, 'stopwhere')
+    hooks(serverDir, { SubagentStop: [{ hooks: [{ type: 'command', command: 'pwd > stopwhere' }] }] })
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    // Executor default cwd = serverDir (deliberately NOT the child session cwd).
+    await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir })
+    await ctx.plugin(HooksClaude, { configPath: join(serverDir, 'hooks.json') })
+    ctx.llm.registerAdapter(['mock'], new MockAdapter([]))
+
+    // Register a live child on its own session cwd; emit subagent/end with its id.
+    const { SessionId } = await import('@deepseek-ai/dsh-session')
+    const childHandle = ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } })
+    ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' })
+
+    await waitFor(() => existsSync(marker))
+    expect(existsSync(marker)).toBe(true) // the marker landed in the CHILD dir
+    const { readFileSync } = await import('node:fs')
+    const where = readFileSync(marker, 'utf8').trim()
+    // `pwd` may resolve symlinks (/var → /private/var etc.), so compare basenames.
+    expect(where.endsWith(childDir.split('/').pop()!)).toBe(true)
+    await childHandle.dispose()
+  })
+})
+
+describe('hooks-claude coverage — systemMessage is warned, not surfaced', () => {
+  it('a hook emitting a systemMessage is logged as not-yet-surfaced', async () => {
+    const d = dir()
+    const s = sh(d, 'sm.sh', '#!/usr/bin/env bash\necho \'{"systemMessage":"heads up"}\'\n')
+    const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(path, adapter)
+    const warn = vi.fn(); ctx.logger.warn = warn as never
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage'))
+    // Not surfaced: the systemMessage text never reaches the model request.
+    expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up')
+  })
+})
+
+describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait)', () => {
+  it('does NOT crash or block when the prompt is sent immediately (context is best-effort, may miss the first request)', async () => {
+    // Regression for the documented downgrade: session-start injection is
+    // detached, so a prompt sent immediately need not observe it. This asserts
+    // the SAFE properties (no crash, the turn still runs) WITHOUT waiting for the
+    // inject first — it documents the best-effort timing rather than masking it
+    // by pre-waiting for context/message (which the guaranteed-timing tests do).
+    const d = dir()
+    const s = sh(d, 'start.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"late ctx"}}\'\n')
+    const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(path, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    // Send immediately — do NOT wait for the session-start inject.
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(1) // the turn ran regardless of hook timing
+  })
+})
diff --git a/packages/hooks/hooks-claude/tsconfig.json b/packages/hooks/hooks-claude/tsconfig.json
new file mode 100644
index 0000000000..909db9b5c3
--- /dev/null
+++ b/packages/hooks/hooks-claude/tsconfig.json
@@ -0,0 +1,42 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../../vendor/schemastery"
+    },
+    {
+      "path": "../hook-protocol"
+    },
+    {
+      "path": "../../core/agent"
+    },
+    {
+      "path": "../../core/tools"
+    },
+    {
+      "path": "../../core/session"
+    },
+    {
+      "path": "../../subagent/subagent"
+    },
+    {
+      "path": "../../llm/llm"
+    },
+    {
+      "path": "../../bash/bash"
+    }
+  ]
+}
diff --git a/packages/hooks/hooks-codex/README.md b/packages/hooks/hooks-codex/README.md
new file mode 100644
index 0000000000..72be33f57f
--- /dev/null
+++ b/packages/hooks/hooks-codex/README.md
@@ -0,0 +1,58 @@
+# @deepseek-ai/dsh-hooks-codex
+
+A cordis plugin that runs a user's existing **Codex** `hooks.json` on the harness's canonical interception seams. The **Codex dialect** half of the hooks subsystem. The dialect-agnostic primitives come from [`@deepseek-ai/dsh-hook-protocol`](../hook-protocol/README.md); this bridge owns the Codex-specific payloads, matcher mode, and decision mapping.
+
+Codex's hook protocol is a deliberate **subset** of Claude Code's (same `hooks.json` shape):
+
+- **Five hook points only:** `PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop` — no subagent / notification / compaction hooks.
+- **Regex-only matchers** (no literal fast path; the matcher is always an unanchored regex).
+- **snake_case stdin payloads** with `turn_id`/`model` extras, written **without** a trailing newline.
+- **No env vars and no command substitution** (a literal `${…}` in a command survives verbatim).
+- **A block-only decision model** — `allow`/`ask` are not honored; a hook can only block, never pre-approve.
+
+A native cordis plugin could do everything this bridge does, more powerfully; the bridge exists only to run UNMODIFIED external Codex hooks faithfully (see [the interception-seams RFC](../../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)).
+
+## Config
+
+```ts
+import type { Config } from '@deepseek-ai/dsh-hooks-codex'
+const config: Config = {
+  configPath: '/path/to/.codex/hooks.json', // required
+  model: 'deepseek-v4',                      // optional: stamped on every payload (Codex includes `model`)
+  defaultTimeoutMs: 600_000,                 // optional: per-hook timeout when a hook sets none
+}
+```
+
+In a `cordis.yml`:
+
+```yaml
+- dsh-hooks-codex:
+    configPath: ./.codex/hooks.json
+    model: deepseek-v4
+```
+
+The config is parsed **once** at load. `configPath` is **process-level** — a relative path resolves against the process launch cwd at load time, not per-session (`TODO(per-session-hook-config)`). A read/parse failure is contained (logs + registers nothing). Only sync `type: 'command'` hooks run — a non-command or `async: true` hook is parsed-and-skipped with a warning. A hook accepts `timeout` or the `timeoutSec` alias. Events outside the five Codex points are dropped at parse.
+
+The hooks themselves run in the agent's session workspace: for the agent-scoped points the bridge passes the session's `cwd` as the hook process's working directory, so a hook operates in the user's project tree, not the server launch dir.
+
+## Hook points → seam Decisions
+
+| Codex hook | Harness seam | Mapping |
+|---|---|---|
+| `SessionStart` | `agent/session-start` (emit) | a plain-stdout hook's output → additionalContext → `agent.inject()` |
+| `UserPromptSubmit` | `agent/prompt-submit` (waterfall) | `block` (exit 2) → `PromptDecision.block`; additionalContext-only → delegate via `next()` then fold context onto the downstream decision |
+| `PreToolUse` | `tools/pre-execute` (waterfall) | `block` → `PreToolDecision.deny` (no `allow`/`ask`) |
+| `PostToolUse` | `tools/post-execute` (waterfall) | `block` → `block` with feedback; additionalContext-only → delegate via `next()` then fold context onto the downstream decision |
+| `Stop` | `agent/turn-continuation` (waterfall) | a blocking Stop hook forces `continue` with the reason as next-step steering |
+
+A tool call's payload carries the real `tool_name` (the same value the matcher tests) and Codex's `tool_input: { command }` shape (the `command` arg when present, else `''`). The matcher subject is the tool name (`PreToolUse`/`PostToolUse`) or the session source (`SessionStart`); `UserPromptSubmit`/`Stop` ignore matchers.
+
+## Context source
+
+Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-codex' }` source (`agent.inject()` would otherwise default it to `{ kind: 'user' }`).
+
+## Deferred
+
+**Stop loop-guard** (`TODO(stop-loop-guard)`): as in CC, a Stop hook that unconditionally blocks would force-continue every step (`stop_hook_active` is always `false` here); the loop-guard is deferred. A hook author must self-limit until it lands.
+
+**`systemMessage`**: a hook's user-facing warning is logged + warned, not surfaced — there is no user-message channel on these seams yet (only model-facing `additionalContext`).
diff --git a/packages/hooks/hooks-codex/package.json b/packages/hooks/hooks-codex/package.json
new file mode 100644
index 0000000000..f26b57fe11
--- /dev/null
+++ b/packages/hooks/hooks-codex/package.json
@@ -0,0 +1,47 @@
+{
+  "name": "@deepseek-ai/dsh-hooks-codex",
+  "description": "Bridge plugin: run a Codex hooks.json hook config on the DeepSeek Harness interception seams",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "dependencies": {
+    "schemastery": "^3.18.0"
+  },
+  "peerDependencies": {
+    "@deepseek-ai/dsh-agent": "^0.0.1",
+    "@deepseek-ai/dsh-hook-protocol": "^0.0.1",
+    "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-session": "^0.0.1",
+    "@deepseek-ai/dsh-tools": "^0.0.1",
+    "cordis": "^4.0.0-rc.6"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-agent-loop": "workspace:^",
+    "@deepseek-ai/dsh-bash": "workspace:^",
+    "@deepseek-ai/dsh-bash-local": "workspace:^",
+    "@deepseek-ai/dsh-hook-protocol": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "@deepseek-ai/dsh-system-prompt": "workspace:^",
+    "@deepseek-ai/dsh-tools": "workspace:^",
+    "cordis": "^4.0.0-rc.6"
+  }
+}
diff --git a/packages/hooks/hooks-codex/src/config.ts b/packages/hooks/hooks-codex/src/config.ts
new file mode 100644
index 0000000000..411f058eea
--- /dev/null
+++ b/packages/hooks/hooks-codex/src/config.ts
@@ -0,0 +1,79 @@
+/**
+ * Parse a Codex `hooks.json` into the shared {@link MatcherGroup} shape. Codex's
+ * config format is a SUBSET of Claude Code's: the same event-name → matcher-group
+ * structure and the same `{ type: 'command', command, timeout?/timeoutSec? }`
+ * hook shape, but only five events and NO command-string substitution (Codex sets
+ * no hook env vars and does not expand `${…}`). Non-command hooks (and Codex's
+ * `async: true` commands) are parsed-and-skipped with a warning.
+ *
+ * @module @deepseek-ai/dsh-hooks-codex/config
+ */
+
+import type { MatcherGroup } from '@deepseek-ai/dsh-hook-protocol'
+
+/** The five hook points Codex's engine supports. */
+export const CODEX_EVENTS = ['PreToolUse', 'PostToolUse', 'SessionStart', 'UserPromptSubmit', 'Stop'] as const
+
+/** A parsed Codex config: event name → its matcher groups (command hooks only). */
+export type CodexHookConfig = Record<string, MatcherGroup[]>
+
+/** A skipped non-command (or async) hook, surfaced so the bridge can warn. */
+export interface SkippedHook {
+  event: string
+  reason: string
+}
+
+/** The outcome of parsing one Codex config file. */
+export interface ParsedCodexConfig {
+  config: CodexHookConfig
+  skipped: SkippedHook[]
+}
+
+function asObject(value: unknown): Record<string, unknown> | undefined {
+  return typeof value === 'object' && value !== null && !Array.isArray(value)
+    ? value as Record<string, unknown>
+    : undefined
+}
+
+/**
+ * Parse a raw Codex `hooks.json` object into runnable {@link MatcherGroup}s.
+ * Only the five {@link CODEX_EVENTS} are honored; an unknown event is dropped.
+ * `type !== 'command'` and `async: true` command hooks are skipped (recorded in
+ * `skipped`). Malformed entries are ignored rather than thrown — a bad config
+ * must not crash boot. No command substitution (Codex does none).
+ */
+export function parseCodexConfig(raw: unknown): ParsedCodexConfig {
+  const config: CodexHookConfig = {}
+  const skipped: SkippedHook[] = []
+  const root = asObject(raw)
+  const hooksMap = root ? asObject(root.hooks) ?? root : undefined
+  if (!hooksMap) return { config, skipped }
+
+  for (const event of CODEX_EVENTS) {
+    const rawGroups = hooksMap[event]
+    if (!Array.isArray(rawGroups)) continue
+    const groups: MatcherGroup[] = []
+    for (const rawGroup of rawGroups) {
+      const group = asObject(rawGroup)
+      if (!group || !Array.isArray(group.hooks)) continue
+      const commands: MatcherGroup['hooks'] = []
+      for (const rawHook of group.hooks) {
+        const hook = asObject(rawHook)
+        if (!hook) continue
+        const type = typeof hook.type === 'string' ? hook.type : 'command'
+        if (type !== 'command') { skipped.push({ event, reason: `unsupported "${type}" hook` }); continue }
+        if (hook.async === true) { skipped.push({ event, reason: 'async hook' }); continue }
+        if (typeof hook.command !== 'string') continue
+        // Codex accepts `timeout` or the `timeoutSec` alias.
+        const timeout = typeof hook.timeout === 'number' ? hook.timeout
+          : typeof hook.timeoutSec === 'number' ? hook.timeoutSec : undefined
+        commands.push({ command: hook.command, ...timeout !== undefined ? { timeoutSec: timeout } : {} })
+      }
+      if (commands.length === 0) continue
+      groups.push({ ...typeof group.matcher === 'string' ? { matcher: group.matcher } : {}, hooks: commands })
+    }
+    if (groups.length > 0) config[event] = groups
+  }
+
+  return { config, skipped }
+}
diff --git a/packages/hooks/hooks-codex/src/index.ts b/packages/hooks/hooks-codex/src/index.ts
new file mode 100644
index 0000000000..a704a6af24
--- /dev/null
+++ b/packages/hooks/hooks-codex/src/index.ts
@@ -0,0 +1,313 @@
+/**
+ * `dsh-hooks-codex` — a bridge plugin that runs a user's existing Codex
+ * `hooks.json` on the harness's canonical interception seams. The CODEX DIALECT
+ * half of the hooks subsystem.
+ *
+ * Codex's hook protocol is a deliberate SUBSET of Claude Code's: five hook points
+ * (`PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop` — no
+ * subagent/notification/compaction), regex-only matchers, snake_case stdin
+ * payloads with `turn_id`/`model` extras and NO trailing newline, no env vars and
+ * no command substitution, and a block-only decision model (allow/ask are not
+ * honored — a hook can only block, never pre-approve). The dialect-agnostic
+ * primitives come from `@deepseek-ai/dsh-hook-protocol`; this bridge owns the
+ * Codex-specific payloads + matcher mode + decision mapping.
+ *
+ * @module @deepseek-ai/dsh-hooks-codex
+ */
+
+import { readFileSync } from 'node:fs'
+import type { Context } from 'cordis'
+import z from 'schemastery'
+import type { Agent, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent'
+import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
+import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
+import {
+  appendHookInvoked,
+  appendHookResult,
+  matchesMatcher,
+  mergeHookOutputs,
+  runHook,
+  type HookOutput,
+  type MatcherGroup,
+  type MergedHookOutcome,
+} from '@deepseek-ai/dsh-hook-protocol'
+import { parseCodexConfig, type CodexHookConfig } from './config.ts'
+
+export const name = 'hooks-codex'
+export const inject = ['bash']
+
+/** Plugin config: where the Codex hooks.json lives + the model name for payloads. */
+export interface Config {
+  /**
+   * Path to a Codex `hooks.json`. PROCESS-LEVEL: read once at load, a relative
+   * path resolves against the process launch cwd.
+   * TODO(per-session-hook-config): per-session project-local discovery from each
+   * `session/new.cwd` is not yet implemented.
+   */
+  configPath: string
+  /** The model name stamped on every payload (Codex includes `model` on each event). */
+  model?: string
+  /** Default per-hook timeout in ms when a hook sets none (Codex default: 600000). */
+  defaultTimeoutMs?: number
+}
+
+export const Config: z<Config> = z.object({
+  configPath: z.string().required(),
+  model: z.string().default(''),
+  defaultTimeoutMs: z.number().default(600_000),
+})
+
+let handlerCounter = 0
+function nextHandlerId(point: string): string {
+  return `codex:${point}:${++handlerCounter}`
+}
+
+const PLUGIN_SOURCE: MessageSource = { kind: 'plugin', plugin: 'hooks-codex' }
+
+function summarize(stderr: string): string | undefined {
+  const t = stderr.trim()
+  if (t.length === 0) return undefined
+  return t.length > 500 ? t.slice(0, 500) + '…' : t
+}
+
+export function apply(ctx: Context, config: Config): void {
+  let parsed: CodexHookConfig = {}
+  try {
+    const raw: unknown = JSON.parse(readFileSync(config.configPath, 'utf8'))
+    const result = parseCodexConfig(raw)
+    parsed = result.config
+    for (const s of result.skipped) {
+      ctx.logger.warn(`hooks-codex: skipping ${s.reason} on ${s.event} (only sync command hooks run)`)
+    }
+  } catch (error: unknown) {
+    ctx.logger.warn(`hooks-codex: could not load hook config "${config.configPath}": ${String(error)} — no hooks registered`)
+    return
+  }
+
+  const defaultTimeoutMs = config.defaultTimeoutMs ?? 600_000
+  const model = config.model ?? ''
+
+  async function runPoint(
+    point: string,
+    matchQuery: string,
+    payload: unknown,
+    opts: { agent?: Agent; turn?: number; signal?: AbortSignal; plainStdoutAsContext?: boolean },
+  ): Promise<MergedHookOutcome> {
+    const groups: MatcherGroup[] = parsed[point] ?? []
+    const outputs: HookOutput[] = []
+    // Run the hook in the agent's session workspace (the `session/new` cwd), not
+    // the executor default (the server launch dir) — a hook reading a relative
+    // file or `pwd` must see the user's project tree. Absent for a no-agent run.
+    const workdir = opts.agent?.session.header.cwd
+    for (const group of groups) {
+      // Codex matches with PURE regex (no literal fast path).
+      if (!matchesMatcher(group.matcher, matchQuery, 'codex')) continue
+      for (const hook of group.hooks) {
+        const handlerId = nextHandlerId(point)
+        const session = opts.agent?.session
+        if (session && opts.turn !== undefined) {
+          appendHookInvoked(session, {
+            turn: opts.turn, point, dialect: 'codex', handlerId,
+            ...group.matcher !== undefined ? { matcher: group.matcher } : {},
+          })
+        }
+        const { output, durationMs } = await runHook(ctx.bash, hook, {
+          payload,
+          ...workdir !== undefined ? { cwd: workdir } : {},
+          ...opts.signal ? { signal: opts.signal } : {},
+          defaultTimeoutMs,
+          trailingNewline: false, // Codex writes stdin WITHOUT a trailing newline.
+          // Discard a `hookSpecificOutput` block naming a different event.
+          expectedEventName: point,
+        }, () => performance.now())
+        // Codex's SessionStart/UserPromptSubmit treat a CLEAN hook's PLAIN
+        // (non-JSON) stdout as additionalContext. The codec keeps that raw text on
+        // `output.stdout` but only sets `additionalContext` from a JSON
+        // `hookSpecificOutput`, so fold plain stdout in here and let the shared
+        // merge + contextFrom path carry it. Gated exactly like the codec's own
+        // structured-stdout parse: only on a clean `exitCode === 0` (a non-zero
+        // exit is an error, not context — an `echo x; exit 2` must not inject
+        // `x`), only when stdout is non-JSON (`!startsWith('{')` — a structured
+        // hook's raw JSON is never dumped as prose), and never clobbering an
+        // explicit additionalContext from a JSON block.
+        if (opts.plainStdoutAsContext === true && output.exitCode === 0
+          && output.additionalContext === undefined
+          && output.stdout.length > 0 && !output.stdout.startsWith('{')) {
+          output.additionalContext = output.stdout
+        }
+        outputs.push(output)
+        if (output.systemMessage !== undefined) {
+          ctx.logger.warn(`hooks-codex: ${point} hook emitted a systemMessage, which is not yet surfaced (ignored)`)
+        }
+        if (session && opts.turn !== undefined) {
+          const stderrSummary = summarize(output.stderr)
+          appendHookResult(session, {
+            turn: opts.turn, point, handlerId,
+            decision: output.decision ?? (output.continue === false ? 'stop' : 'pass'),
+            ...output.exitCode !== undefined ? { exitCode: output.exitCode } : {},
+            ...stderrSummary !== undefined ? { stderrSummary } : {},
+            durationMs,
+          })
+        }
+      }
+    }
+    return mergeHookOutputs(outputs)
+  }
+
+  // TODO(hook-continue-false): the merge computes `merged.stop`/`stopReason` from
+  // a hook's `continue:false`, but no seam below honors it — there is no
+  // "hard-halt the whole agent" primitive on the interception seams yet. Deferred
+  // with the loop-guard work; until then a `continue:false` hook keeps its
+  // per-point effect and the halt request is recorded in `hook/result`, not acted on.
+
+  function contextFrom(merged: MergedHookOutcome): HookContext | undefined {
+    if (merged.additionalContext.length === 0) return undefined
+    const content: ContentBlock[] = merged.additionalContext.map(text => ({ type: 'text', text }))
+    return { content, source: PLUGIN_SOURCE }
+  }
+
+  /**
+   * Concatenate this bridge's {@link HookContext} (`ours`, always present at the
+   * call sites) with a downstream listener's optional one, so folding our
+   * additionalContext onto a delegated decision drops neither. The merged block
+   * carries a single `source` — this bridge's — because a `HookContext` holds one
+   * `MessageSource` and the seam cannot represent mixed provenance; the rendered
+   * `context/message` only distinguishes by `source.kind` ('plugin'), so a
+   * downstream plugin's text is still correctly framed as plugin context.
+   */
+  function concatContext(ours: HookContext, theirs: HookContext | undefined): HookContext {
+    if (!theirs) return ours
+    return { content: [...ours.content, ...theirs.content], source: ours.source }
+  }
+
+  // SessionStart: emit. Codex passes a plain-stdout hook's output as additionalContext.
+  // TODO(session-start-gating): a synchronous emit + detached `.then`, so the
+  // injected context is BEST-EFFORT — not guaranteed before the first turn reaches
+  // the model (a slow hook can miss the first request). Gating is a deferred
+  // loop-level change; the contract is "injected as soon as the hook resolves".
+  ctx.on('agent/session-start', (agent, source) => {
+    void runPoint('SessionStart', source, { ...base(agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true })
+      .then((merged) => {
+        const context = contextFrom(merged)
+        if (context) agent.inject(context.content, { source: context.source })
+      })
+      .catch((error: unknown) => { ctx.logger.warn(`hooks-codex: SessionStart hook failed: ${String(error)}`) })
+  })
+
+  // UserPromptSubmit → PromptDecision. Codex can only BLOCK (no allow/ask).
+  ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise<PromptDecision> => {
+    const turn = lastTurn(agent)
+    const merged = await runPoint('UserPromptSubmit', '', { ...turnBase(agent, 'UserPromptSubmit', model), prompt: blocksToText(content) }, { agent, turn, plainStdoutAsContext: true })
+    if (merged.decision === 'deny') return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' }
+    // Context alone is not a veto: DELEGATE so a later prompt-submit listener can
+    // still block/rewrite, then fold our context onto its decision.
+    const downstream = await next()
+    const ours = contextFrom(merged)
+    if (!ours || downstream.kind !== 'allow') return downstream
+    return {
+      kind: 'allow',
+      ...downstream.content !== undefined ? { content: downstream.content } : {},
+      additionalContext: concatContext(ours, downstream.additionalContext),
+    }
+  })
+
+  // PreToolUse → PreToolDecision. Codex blocks only (no allow/ask honored).
+  ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
+    const turn = lastTurn(exec.agent)
+    const merged = await runPoint('PreToolUse', exec.name, preToolPayload(exec, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
+    if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' }
+    return next()
+  })
+
+  // PostToolUse → PostToolDecision (block with feedback, or attach context).
+  ctx.on('tools/post-execute', async (exec, result, next): Promise<PostToolDecision> => {
+    const turn = lastTurn(exec.agent)
+    const merged = await runPoint('PostToolUse', exec.name, postToolPayload(exec, result, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
+    const context = contextFrom(merged)
+    if (merged.decision === 'deny') {
+      return { kind: 'block', feedback: [{ type: 'text', text: merged.reason ?? 'blocked by PostToolUse hook' }], ...context ? { additionalContext: context } : {} }
+    }
+    // Context alone is not a veto: DELEGATE, then fold our context onto the
+    // downstream decision (a downstream block carries it too).
+    const downstream = await next()
+    if (!context) return downstream
+    if (downstream.kind === 'block') {
+      return { ...downstream, additionalContext: concatContext(context, downstream.additionalContext) }
+    }
+    return {
+      kind: 'accept',
+      ...downstream.content !== undefined ? { content: downstream.content } : {},
+      additionalContext: concatContext(context, downstream.additionalContext),
+    }
+  })
+
+  // Stop → ContinuationDecision. A blocking Stop hook forces continuation.
+  // TODO(stop-loop-guard): like CC, a Stop hook that unconditionally blocks would
+  // force-continue every step (`stop_hook_active` is always false here); the
+  // loop-guard (stop_hook_active + a max-consecutive cap) is deferred.
+  ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise<ContinuationDecision> => {
+    const merged = await runPoint('Stop', '', { ...turnBase(agent, 'Stop', model), stop_hook_active: false, last_assistant_message: null }, { agent, turn })
+    if (merged.decision === 'deny') {
+      // A blocking Stop hook forces continuation; a block with no reason (exit 2,
+      // empty stderr) still forces it — fall back to a generic steering line
+      // rather than letting the turn stop.
+      const text = merged.reason ?? 'continue: blocked by Stop hook'
+      return { action: 'continue', reason: { content: [{ type: 'text', text }], source: PLUGIN_SOURCE } }
+    }
+    return next()
+  })
+}
+
+// --- Codex DIALECT payloads: snake_case, model on every event, turn_id on
+// turn-scoped events. ---
+
+function lastTurn(agent: Agent | undefined): number {
+  if (!agent) return 0
+  const last = [...agent.session.events].findLast(e => e.type === 'turn/start')
+  /* v8 ignore next -- the `: 0` arm is a defensive fallback: when an agent is
+     present, lastTurn is only called from the mid-turn seams, which always run
+     inside an open turn, so `last` is always a turn/start here. */
+  return last?.type === 'turn/start' ? last.data.turn : 0
+}
+
+function blocksToText(content: ContentBlock[]): string {
+  return content.filter((b): b is Extract<ContentBlock, { type: 'text' }> => b.type === 'text').map(b => b.text).join('')
+}
+
+/** Base fields on every Codex payload (no turn_id). */
+function base(agent: Agent | undefined, event: string, model: string): Record<string, unknown> {
+  return {
+    session_id: agent?.session.header.id ?? '',
+    transcript_path: null,
+    cwd: agent?.session.header.cwd ?? process.cwd(),
+    hook_event_name: event,
+    model,
+    permission_mode: 'default',
+  }
+}
+
+/** Base + turn_id, for the turn-scoped events (PreToolUse/PostToolUse/UserPromptSubmit/Stop). */
+function turnBase(agent: Agent | undefined, event: string, model: string): Record<string, unknown> {
+  return { ...base(agent, event, model), turn_id: String(lastTurn(agent)) }
+}
+
+/** Extract a `command` string from a tool call's parsed arguments, else ''. */
+function commandOf(args: unknown): string {
+  if (typeof args === 'object' && args !== null && 'command' in args) {
+    const command: unknown = args.command
+    if (typeof command === 'string') return command
+  }
+  return ''
+}
+
+function preToolPayload(exec: ToolExecution, model: string): Record<string, unknown> {
+  // `tool_name` is the REAL tool name (matching the `exec.name` matcher subject);
+  // a hardcoded constant would disagree with what the matcher tests and make a
+  // config's tool matcher never fire. `tool_input` keeps Codex's `{ command }`
+  // shape (its shell payload), derived from the call's `command` arg when present.
+  return { ...turnBase(exec.agent, 'PreToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId }
+}
+
+function postToolPayload(exec: ToolExecution, result: ToolExecutionResult, model: string): Record<string, unknown> {
+  return { ...turnBase(exec.agent, 'PostToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId, tool_response: blocksToText(result.content) }
+}
diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts
new file mode 100644
index 0000000000..0148da104e
--- /dev/null
+++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts
@@ -0,0 +1,173 @@
+import { afterEach, describe, expect, it } from 'vitest'
+import { mkdtempSync, rmSync, writeFileSync, chmodSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { Context } from 'cordis'
+import Loader from '@cordisjs/plugin-loader'
+import LlmService from '@deepseek-ai/dsh-llm'
+import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex'
+import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
+
+/**
+ * Full-loop Codex-bridge tests: scripted mock MODEL + REAL loop + REAL bash +
+ * REAL `dsh-hooks-codex` running REAL shell scripts from a temp `hooks.json`.
+ * Codex dialect specifics exercised here: regex matcher (substring), block-only
+ * decisions, the five-event subset.
+ */
+
+const dirs: string[] = []
+afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) })
+
+function configDir(): string {
+  const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-codex-'))
+  dirs.push(dir)
+  return dir
+}
+function script(dir: string, name: string, body: string): string {
+  const path = join(dir, name)
+  writeFileSync(path, body)
+  chmodSync(path, 0o755)
+  return path
+}
+function writeHooks(dir: string, hooks: unknown): void {
+  writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks }))
+}
+
+async function harness(dir: string, adapter: MockAdapter): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(AgentLoop, { agents: [] })
+  await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+  await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'test-model' })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+
+function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = ctx.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') { dispose(); resolve() }
+    })
+  })
+}
+function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] }
+
+describe('hooks-codex bridge', () => {
+  it('a PreToolUse hook (exit 2) denies a tool the regex matcher matches as a substring', async () => {
+    const dir = configDir()
+    const deny = script(dir, 'deny.sh', '#!/usr/bin/env bash\necho "codex blocked it" >&2\nexit 2\n')
+    // Codex regex matcher: "Bash" is /Bash/ — matches the tool name "Bash".
+    writeHooks(dir, { PreToolUse: [{ matcher: 'Bash', hooks: [{ type: 'command', command: deny }] }] })
+
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')])
+    const ctx = await harness(dir, adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'run ls' }])
+    await waitForIdle(ctx, agent)
+
+    expect(ran).toBe(false)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('codex blocked it'))).toBe(true)
+    // recorded under the codex dialect
+    expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.dialect === 'codex' && e.data.point === 'PreToolUse')).toBe(true)
+  })
+
+  it('a Stop hook (exit 2) forces the turn to continue with the reason as steering', async () => {
+    const dir = configDir()
+    // Block exactly ONCE (a marker file), then allow — without a one-shot guard a
+    // hook that always exits 2 would force-continue forever (the deferred
+    // stop_hook_active loop-guard is the real fix; here we self-limit so the test
+    // exercises the continue path without looping).
+    const marker = join(dir, 'fired')
+    const cont = script(dir, 'cont.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\necho "keep going: address the goal" >&2\nexit 2\n`)
+    writeHooks(dir, { Stop: [{ hooks: [{ type: 'command', command: cont }] }] })
+
+    // Step 1 has no tool calls → would stop; the Stop hook forces step 2.
+    const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')])
+    const ctx = await harness(dir, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    // The Stop hook's reason became next-step steering → a second model request ran.
+    expect(adapter.requests).toHaveLength(2)
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('keep going: address the goal')
+  })
+
+  it('only the five Codex events are honored — a SubagentStop entry is ignored', async () => {
+    const dir = configDir()
+    const s = script(dir, 'x.sh', '#!/usr/bin/env bash\nexit 2\n')
+    // SubagentStop is NOT a Codex event; it must be dropped (no crash, no effect).
+    writeHooks(dir, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] })
+
+    const adapter = new MockAdapter([textResponse('fine')])
+    const ctx = await harness(dir, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    // Ran normally; the unknown event was dropped at parse.
+    expect(adapter.requests).toHaveLength(1)
+  })
+
+  it('a missing config registers no hooks and does not crash', async () => {
+    const dir = configDir() // no hooks.json written
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(dir, adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(1)
+  })
+
+  it('disposing the bridge fiber removes its listeners (HMR safety)', async () => {
+    const dir = configDir()
+    // A BLOCKING UserPromptSubmit hook: if the listener leaked past dispose, it
+    // would veto the prompt (0 model requests) and log a hook/invoked. After a
+    // clean dispose the turn must proceed untouched — this fails loudly on a leak
+    // (a no-op `true` hook would pass even with a leaked listener).
+    const deny = script(dir, 'deny.sh', '#!/usr/bin/env bash\nexit 2\n')
+    writeHooks(dir, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: deny }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+    const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' })
+    await fiber.dispose()
+    ctx.llm.registerAdapter(['mock'], adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone
+    expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) // no hook ran
+  })
+
+  it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/apply', () => {
+    expect('default' in HooksCodex).toBe(false)
+    expect(HooksCodex.name).toBe('hooks-codex')
+    expect(HooksCodex.inject).toEqual(['bash'])
+    const loader = Object.create(Loader.prototype) as Loader
+    const unwrapped = loader.unwrapExports(HooksCodex) as Record<string, unknown>
+    expect(unwrapped).toBe(HooksCodex)
+    expect(unwrapped.name).toBe('hooks-codex')
+    expect(unwrapped.inject).toEqual(['bash'])
+    expect(typeof unwrapped.apply).toBe('function')
+  })
+})
diff --git a/packages/hooks/hooks-codex/tests/config.spec.ts b/packages/hooks/hooks-codex/tests/config.spec.ts
new file mode 100644
index 0000000000..e79d665931
--- /dev/null
+++ b/packages/hooks/hooks-codex/tests/config.spec.ts
@@ -0,0 +1,68 @@
+import { describe, expect, it } from 'vitest'
+import { parseCodexConfig, CODEX_EVENTS } from '@deepseek-ai/dsh-hooks-codex/src/config.ts'
+
+describe('parseCodexConfig', () => {
+  it('honors only the five Codex events, dropping unknown ones', () => {
+    const { config } = parseCodexConfig({
+      PreToolUse: [{ hooks: [{ type: 'command', command: 'a.sh' }] }],
+      SubagentStop: [{ hooks: [{ type: 'command', command: 'b.sh' }] }], // not a Codex event
+      Notification: [{ hooks: [{ type: 'command', command: 'c.sh' }] }], // not a Codex event
+    })
+    expect(Object.keys(config)).toEqual(['PreToolUse'])
+    expect(CODEX_EVENTS).toContain('PreToolUse')
+    expect(CODEX_EVENTS).not.toContain('SubagentStop' as never)
+  })
+
+  it('accepts both timeout and the timeoutSec alias, no substitution', () => {
+    const { config } = parseCodexConfig({
+      Stop: [{ hooks: [{ type: 'command', command: '${NOT_SUBSTITUTED}/s.sh', timeout: 10 }] }],
+      UserPromptSubmit: [{ hooks: [{ type: 'command', command: 'u.sh', timeoutSec: 20 }] }],
+    })
+    // Codex does NO substitution — the literal ${…} survives.
+    expect(config.Stop).toEqual([{ hooks: [{ command: '${NOT_SUBSTITUTED}/s.sh', timeoutSec: 10 }] }])
+    expect(config.UserPromptSubmit).toEqual([{ hooks: [{ command: 'u.sh', timeoutSec: 20 }] }])
+  })
+
+  it('skips non-command and async:true hooks (recorded)', () => {
+    const { config, skipped } = parseCodexConfig({
+      PreToolUse: [{ hooks: [
+        { type: 'prompt' },
+        { type: 'command', command: 'sync.sh' },
+        { type: 'command', command: 'bg.sh', async: true },
+      ] }],
+    })
+    expect(config.PreToolUse).toEqual([{ hooks: [{ command: 'sync.sh' }] }])
+    expect(skipped).toEqual([{ event: 'PreToolUse', reason: 'unsupported "prompt" hook' }, { event: 'PreToolUse', reason: 'async hook' }])
+  })
+
+  it('parses the { hooks: … } wrapper and the bare map identically', () => {
+    const groups = { Stop: [{ hooks: [{ type: 'command', command: 's.sh' }] }] }
+    expect(parseCodexConfig(groups).config).toEqual(parseCodexConfig({ hooks: groups }).config)
+  })
+
+  it('drops malformed entries and a non-object top level without throwing', () => {
+    expect(parseCodexConfig(null).config).toEqual({})
+    expect(parseCodexConfig({ PreToolUse: 'no' }).config).toEqual({})
+    expect(parseCodexConfig({ Stop: [7, { hooks: 'x' }, { hooks: [{ type: 'command', command: 9 }] }] }).config).toEqual({})
+  })
+
+  it('skips a non-object element inside a hooks array, keeping the valid sibling', () => {
+    const { config } = parseCodexConfig({ Stop: [{ hooks: [null, 7, { type: 'command', command: 's.sh' }] }] })
+    expect(config.Stop).toEqual([{ hooks: [{ command: 's.sh' }] }])
+  })
+
+  it('treats a hook with no `type` field as a command (the default)', () => {
+    const { config } = parseCodexConfig({ Stop: [{ hooks: [{ command: 's.sh' }] }] })
+    expect(config.Stop).toEqual([{ hooks: [{ command: 's.sh' }] }])
+  })
+
+  it('omits the matcher key for a match-all group', () => {
+    const { config } = parseCodexConfig({ Stop: [{ hooks: [{ type: 'command', command: 's.sh' }] }] })
+    expect('matcher' in config.Stop![0]!).toBe(false)
+  })
+
+  it('keeps a matcher when present', () => {
+    const { config } = parseCodexConfig({ PreToolUse: [{ matcher: '^Bash$', hooks: [{ type: 'command', command: 'b.sh' }] }] })
+    expect(config.PreToolUse![0]!.matcher).toBe('^Bash$')
+  })
+})
diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts
new file mode 100644
index 0000000000..87032c98ce
--- /dev/null
+++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts
@@ -0,0 +1,540 @@
+import { afterEach, describe, expect, it, vi } from 'vitest'
+import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { Context } from 'cordis'
+import LlmService from '@deepseek-ai/dsh-llm'
+import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex'
+import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
+
+const dirs: string[] = []
+afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) })
+function dir(): string { const d = mkdtempSync(join(tmpdir(), 'dsh-hx-cov-')); dirs.push(d); return d }
+function sh(d: string, name: string, body: string): string {
+  const p = join(d, name); writeFileSync(p, body); chmodSync(p, 0o755); return p
+}
+function hooks(d: string, h: unknown): string {
+  writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json')
+}
+
+async function harness(configPath: string, adapter: MockAdapter): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] })
+  await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+  await ctx.plugin(HooksCodex, { configPath, model: 'm' })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+  return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) })
+}
+function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] }
+/** Poll until `predicate` holds or the deadline passes — robust to detached
+ * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */
+async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise<void> {
+  const deadline = Date.now() + timeout
+  while (!predicate()) {
+    if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline')
+    await new Promise(r => setTimeout(r, interval))
+  }
+}
+
+describe('hooks-codex coverage — decision mapping paths', () => {
+  it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => {
+    const d = dir()
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] })
+    const adapter = new MockAdapter([textResponse('no')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(0)
+    const te = events(agent).findLast(e => e.type === 'turn/end')
+    expect(te?.type === 'turn/end' && te.data.reason.kind).toBe('rejected')
+  })
+
+  it('UserPromptSubmit additionalContext is injected; a no-op hook proceeds', async () => {
+    const d = dir()
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x')
+  })
+
+  it('a context-only UserPromptSubmit hook DELEGATES so a later listener can still block', async () => {
+    // Context alone is not a veto: a downstream agent/prompt-submit listener (a
+    // policy plugin registered after the bridge) must still get to block. The
+    // bridge delegates via next() and folds its context onto the decision.
+    const d = dir()
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"bridge ctx"}}\'\n') }] }] })
+    const adapter = new MockAdapter([textResponse('should not run')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(0)
+    expect(events(agent).some(e => e.type === 'user/message')).toBe(false)
+    const te = events(agent).findLast(e => e.type === 'turn/end')
+    expect(te?.type === 'turn/end' && te.data.reason).toMatchObject({ kind: 'rejected', reason: 'policy veto' })
+  })
+
+  it('folds the bridge additionalContext WITH a downstream listener that also adds context', async () => {
+    const d = dir()
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"from-bridge"}}\'\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.on('agent/prompt-submit', async () => ({
+      kind: 'allow' as const,
+      content: [{ type: 'text' as const, text: 'rewritten-prompt' }],
+      additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } },
+    }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const req = JSON.stringify(adapter.requests[0]!.messages)
+    expect(req).toContain('from-bridge')
+    expect(req).toContain('from-downstream')
+    expect(req).toContain('rewritten-prompt')
+  })
+
+  it('folds the bridge PostToolUse context onto a downstream ACCEPT that replaces content', async () => {
+    const d = dir()
+    hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true)
+    expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
+  })
+
+  it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => {
+    const d = dir()
+    hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const result = events(agent).find(e => e.type === 'tool/result')
+    expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
+    expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true)
+    expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
+  })
+
+  it('SessionStart additionalContext is injected for the first request', async () => {
+    const d = dir()
+    hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    await waitFor(() => events(agent).some(e => e.type === 'context/message'
+      && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx'))))
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('start-ctx')
+  })
+
+  it('PostToolUse block (exit 2) → isError feedback; default reason', async () => {
+    const d = dir()
+    hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'p.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const r = events(agent).find(e => e.type === 'tool/result')
+    expect(r?.type === 'tool/result' && r.data.isError).toBe(true)
+    expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true)
+  })
+
+  it('PostToolUse additionalContext (clean exit) is attached after the result', async () => {
+    const d = dir()
+    hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"post-ctx"}}\'\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true)
+  })
+
+  it('PreToolUse for a tool call WITHOUT a command arg passes an empty command (commandOf non-object/missing arm)', async () => {
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pre.sh', '#!/usr/bin/env bash\ncat >/dev/null\nexit 0\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', {}), textResponse('done')]) // no command arg
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(ran).toBe(true) // clean-exit hook allows; commandOf returned ''
+  })
+
+  it('a clean exit-0 hook records exitCode 0 and omits stderrSummary', async () => {
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'n.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0)
+    expect(res?.type === 'hook/result' && 'stderrSummary' in res.data).toBe(false)
+  })
+
+  it('a long stderr is truncated in the hook/result summary', async () => {
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'l.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true)
+  })
+
+  it('warns on a skipped async hook and a direct apply() defaults the timeout', async () => {
+    const d = dir()
+    const marker = join(d, 'ran')
+    hooks(d, { UserPromptSubmit: [{ hooks: [
+      { type: 'command', command: 'bg.sh', async: true }, // skipped → warn
+      { type: 'command', command: sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) },
+    ] }] })
+    const warn = vi.fn()
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] })
+    await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
+    ctx.logger.warn = warn as never
+    // Direct apply (schema bypass) → defaultTimeoutMs ?? 600_000 + model ?? '' fallbacks.
+    HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') })
+    ctx.llm.registerAdapter(['mock'], adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(existsSync(marker)).toBe(true)
+    expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook'))
+  })
+
+  it('a no-op clean hook proceeds (contextFrom empty → next)', async () => {
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'n.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(ran).toBe(true)
+  })
+
+  it('SessionStart with no additionalContext is a no-op (contextFrom empty)', async () => {
+    const d = dir()
+    // The hook touches a marker so we can wait for it to ACTUALLY FINISH before
+    // asserting absence — a completed turn alone would not prove the detached
+    // session-start hook ran, making the absence check a false pass.
+    const marker = join(d, 'ss-ran')
+    hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    await waitFor(() => existsSync(marker)) // the clean no-output hook has finished
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(events(agent).some(e => e.type === 'context/message')).toBe(false)
+  })
+
+  it('a throwing SessionStart inject is contained (logged)', async () => {
+    const d = dir()
+    hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"x"}}\'\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const warn = vi.fn(); ctx.logger.warn = warn as never
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.inject = (() => { throw new Error('inject boom') })
+    await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed')))
+    expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed'))
+  })
+
+  it('a clean PreToolUse with no decision allows the tool (no deny)', async () => {
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'ok.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(ran).toBe(true)
+  })
+
+  it('a non-matching regex matcher skips the hook (matchesMatcher false → continue)', async () => {
+    const d = dir()
+    // /^Edit$/ does not match the tool name "Bash" → the group is skipped.
+    hooks(d, { PreToolUse: [{ matcher: '^Edit$', hooks: [{ type: 'command', command: sh(d, 'deny.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded
+    expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false)
+  })
+
+  it('a {"continue":false} hook is RECORDED as "stop" but does not halt the run (TODO(hook-continue-false))', async () => {
+    // Honoring `continue:false` is deferred — the seams have no hard-halt
+    // primitive. Assert the LOG records the halt request AND that the run is not
+    // actually halted (the tool still runs, the turn completes).
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"continue":false,"stopReason":"halt"}\'\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded
+    expect(ran).toBe(true) // NOT honored: the tool still ran (halt is deferred)
+  })
+
+  it('PreToolUse deny with EMPTY stderr uses the default reason (?? right arm)', async () => {
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const r = events(agent).find(e => e.type === 'tool/result')
+    expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true)
+  })
+
+  it('PostToolUse block AND additionalContext are surfaced together', async () => {
+    const d = dir()
+    hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'bc.sh', '#!/usr/bin/env bash\necho \'{"decision":"block","reason":"bad","hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"ctx too"}}\'\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const r = events(agent).find(e => e.type === 'tool/result')
+    expect(r?.type === 'tool/result' && r.data.isError).toBe(true)
+    expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true)
+    expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('ctx too')))).toBe(true)
+  })
+
+  it('commandOf reads a non-string command arg as an empty command', async () => {
+    const d = dir()
+    // The tool-call arguments carry `command` as a NUMBER → commandOf's
+    // `typeof command === 'string'` false arm → '' (the payload's tool_input.command).
+    const cap = join(d, 'payload')
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'cap.sh', `#!/usr/bin/env bash\ncat > "${cap}"\nexit 0\n`) }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } }
+    expect(payload.tool_input.command).toBe('')
+  })
+
+  it('a no-agent direct PreToolUse run uses process.cwd() and turn 0 (no session to record)', async () => {
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] })
+    const ctx = await harness(join(d, 'hooks.json'), new MockAdapter([]))
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } }))
+    const { CallId } = await import('@deepseek-ai/dsh-llm')
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'Bash', arguments: { command: 'x' } })
+    expect(ran).toBe(false) // denied
+    expect(result.isError).toBe(true)
+  })
+
+  it('a no-agent direct PostToolUse run attaches context with no session to record', async () => {
+    const d = dir()
+    hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"x"}}\'\n') }] }] })
+    const ctx = await harness(join(d, 'hooks.json'), new MockAdapter([]))
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const { CallId } = await import('@deepseek-ai/dsh-llm')
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'Bash', arguments: { command: 'x' } })
+    expect(result.isError).toBeFalsy()
+    expect(result.additionalContext?.content.some(b => b.type === 'text' && b.text === 'x')).toBe(true)
+  })
+
+  it('when the bash executor REJECTS, the hook/result omits exitCode (non-blocking)', async () => {
+    const d = dir()
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'h.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.bash.run = (() => Promise.reject(new Error('executor down')))
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const res = events(agent).find(e => e.type === 'hook/result')
+    expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false)
+  })
+
+  it('a blocking Stop hook with EMPTY stderr still forces continuation (no reason required)', async () => {
+    // Regression: an exit-2 Stop hook with no stderr yields decision 'deny' +
+    // reason undefined; the turn must STILL force-continue, not silently stop.
+    const d = dir()
+    const marker = join(d, 'fired')
+    hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] })
+    const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook')
+  })
+
+  it('a clean UserPromptSubmit hook that prints PLAIN stdout injects it as context', async () => {
+    // Codex feeds a SessionStart/UserPromptSubmit hook's PLAIN (non-JSON) stdout
+    // as additionalContext (unlike CC, which needs a JSON hookSpecificOutput).
+    const d = dir()
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook')
+  })
+
+  it('a NON-clean SessionStart hook (exit 2) does NOT inject its stdout as context', async () => {
+    // The plain-stdout→context fold is gated on exitCode === 0, matching the
+    // codec's structured-stdout rule. SessionStart is an EMIT (cannot block), so
+    // an `echo stale; exit 2` here is the exact case the gate guards: without it,
+    // the non-clean hook's stdout would wrongly inject "stale". A marker lets us
+    // wait for the detached hook to finish before asserting absence.
+    const d = dir()
+    const marker = join(d, 'ran')
+    hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    await waitFor(() => existsSync(marker)) // the exit-2 hook has finished
+    expect(events(agent).some(e => e.type === 'context/message'
+      && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false)
+  })
+
+  it('a UserPromptSubmit hook with a non-blocking error exit (1) + stdout does NOT inject it', async () => {
+    // Exit 1 is a non-blocking error (no decision), so the prompt is NOT blocked
+    // and the handler falls through to the context path — the gate must still
+    // suppress the error hook's stdout ("stale" never reaches the model).
+    const d = dir()
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran
+    expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale')
+  })
+
+  it('a clean SessionStart hook that prints PLAIN stdout injects it (not JSON)', async () => {
+    const d = dir()
+    hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    await waitFor(() => events(agent).some(e => e.type === 'context/message'
+      && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble'))))
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('session preamble')
+  })
+
+  it('a clean hook that prints JSON is NOT injected as prose (plain-stdout gate)', async () => {
+    // A structured (JSON) stdout must go through the hookSpecificOutput path, not
+    // be dumped verbatim as context — the `!startsWith('{')` gate guards this.
+    const d = dir()
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated')
+  })
+
+  it('the PreToolUse payload carries the REAL tool name (matches the matcher subject)', async () => {
+    // Regression: the payload once hardcoded tool_name "Bash", disagreeing with
+    // the exec.name matcher subject — a config matcher on the real name would
+    // then never fire. Capture the payload and assert tool_name === the real name.
+    const d = dir()
+    const cap = join(d, 'payload')
+    hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'cap.sh', `#!/usr/bin/env bash\ncat > "${cap}"\nexit 0\n`) }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } }
+    expect(payload.tool_name).toBe('shell')
+    expect(payload.tool_input.command).toBe('ls')
+  })
+
+  it('a Codex matcher on the REAL tool name fires (matcher subject === payload tool_name)', async () => {
+    // A regex matcher matching the real tool name must select the hook — proving
+    // the matcher subject and the payload tool_name agree.
+    const d = dir()
+    hooks(d, { PreToolUse: [{ matcher: 'shell', hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    let ran = false
+    ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(ran).toBe(false) // the matcher fired → the hook denied the tool
+    expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true)
+  })
+
+  it('a hook emitting a systemMessage is warned as not-yet-surfaced', async () => {
+    const d = dir()
+    hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'sm.sh', '#!/usr/bin/env bash\necho \'{"systemMessage":"heads up"}\'\n') }] }] })
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(join(d, 'hooks.json'), adapter)
+    const warn = vi.fn(); ctx.logger.warn = warn as never
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
+    expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage'))
+    expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up')
+  })
+
+  it('runs an agent-scoped hook in the session cwd, not the executor default', async () => {
+    // Same regression as the CC bridge: the Codex bridge must thread the session
+    // cwd as the hook workdir. Executor default = serverDir; session cwd =
+    // sessionDir; the PreToolUse hook's `pwd` marker must land in sessionDir.
+    const serverDir = dir()
+    const sessionDir = dir()
+    const marker = join(sessionDir, 'where')
+    hooks(serverDir, { PreToolUse: [{ hooks: [{ type: 'command', command: 'pwd > where' }] }] })
+    const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] })
+    await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir })
+    await ctx.plugin(HooksCodex, { configPath: join(serverDir, 'hooks.json'), model: 'm' })
+    ctx.llm.registerAdapter(['mock'], adapter)
+    ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
+    const { SessionId } = await import('@deepseek-ai/dsh-session')
+    const handle = ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } })
+    handle.agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, handle.agent as ReactLoopAgent)
+    expect(existsSync(marker)).toBe(true)
+    expect(readFileSync(marker, 'utf8').trim().endsWith(sessionDir.split('/').pop()!)).toBe(true)
+    await handle.dispose()
+  })
+})
diff --git a/packages/hooks/hooks-codex/tsconfig.json b/packages/hooks/hooks-codex/tsconfig.json
new file mode 100644
index 0000000000..f936b500aa
--- /dev/null
+++ b/packages/hooks/hooks-codex/tsconfig.json
@@ -0,0 +1,39 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../../vendor/schemastery"
+    },
+    {
+      "path": "../hook-protocol"
+    },
+    {
+      "path": "../../core/agent"
+    },
+    {
+      "path": "../../core/tools"
+    },
+    {
+      "path": "../../core/session"
+    },
+    {
+      "path": "../../llm/llm"
+    },
+    {
+      "path": "../../bash/bash"
+    }
+  ]
+}
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 9894747424..8045aa9cc3 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -370,6 +370,83 @@ importers:
         specifier: ^4.0.0-rc.6
         version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
 
+  packages/hooks/hooks-claude:
+    dependencies:
+      schemastery:
+        specifier: ^3.18.0
+        version: 3.18.0
+    devDependencies:
+      '@deepseek-ai/dsh-agent':
+        specifier: workspace:^
+        version: link:../../core/agent
+      '@deepseek-ai/dsh-agent-loop':
+        specifier: workspace:^
+        version: link:../../core/agent-loop
+      '@deepseek-ai/dsh-bash':
+        specifier: workspace:^
+        version: link:../../bash/bash
+      '@deepseek-ai/dsh-bash-local':
+        specifier: workspace:^
+        version: link:../../bash/bash-local
+      '@deepseek-ai/dsh-hook-protocol':
+        specifier: workspace:^
+        version: link:../hook-protocol
+      '@deepseek-ai/dsh-llm':
+        specifier: workspace:^
+        version: link:../../llm/llm
+      '@deepseek-ai/dsh-session':
+        specifier: workspace:^
+        version: link:../../core/session
+      '@deepseek-ai/dsh-subagent':
+        specifier: workspace:^
+        version: link:../../subagent/subagent
+      '@deepseek-ai/dsh-system-prompt':
+        specifier: workspace:^
+        version: link:../../core/system-prompt
+      '@deepseek-ai/dsh-tools':
+        specifier: workspace:^
+        version: link:../../core/tools
+      cordis:
+        specifier: ^4.0.0-rc.6
+        version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
+
+  packages/hooks/hooks-codex:
+    dependencies:
+      schemastery:
+        specifier: ^3.18.0
+        version: 3.18.0
+    devDependencies:
+      '@deepseek-ai/dsh-agent':
+        specifier: workspace:^
+        version: link:../../core/agent
+      '@deepseek-ai/dsh-agent-loop':
+        specifier: workspace:^
+        version: link:../../core/agent-loop
+      '@deepseek-ai/dsh-bash':
+        specifier: workspace:^
+        version: link:../../bash/bash
+      '@deepseek-ai/dsh-bash-local':
+        specifier: workspace:^
+        version: link:../../bash/bash-local
+      '@deepseek-ai/dsh-hook-protocol':
+        specifier: workspace:^
+        version: link:../hook-protocol
+      '@deepseek-ai/dsh-llm':
+        specifier: workspace:^
+        version: link:../../llm/llm
+      '@deepseek-ai/dsh-session':
+        specifier: workspace:^
+        version: link:../../core/session
+      '@deepseek-ai/dsh-system-prompt':
+        specifier: workspace:^
+        version: link:../../core/system-prompt
+      '@deepseek-ai/dsh-tools':
+        specifier: workspace:^
+        version: link:../../core/tools
+      cordis:
+        specifier: ^4.0.0-rc.6
+        version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
+
   packages/llm/llm:
     devDependencies:
       '@deepseek-ai/dsh-brand':
diff --git a/tsconfig.build.json b/tsconfig.build.json
index 77603f7091..d1a369036e 100644
--- a/tsconfig.build.json
+++ b/tsconfig.build.json
@@ -52,6 +52,8 @@
     { "path": "./packages/subagent/subagent-fork" },
     { "path": "./packages/subagent/subagent-acp" },
     { "path": "./packages/todo/tool-todo" },
-    { "path": "./packages/hooks/hook-protocol" }
+    { "path": "./packages/hooks/hook-protocol" },
+    { "path": "./packages/hooks/hooks-claude" },
+    { "path": "./packages/hooks/hooks-codex" }
   ]
 }
diff --git a/tsconfig.json b/tsconfig.json
index d1b97a86c3..c43e6690c6 100644
--- a/tsconfig.json
+++ b/tsconfig.json
@@ -63,6 +63,8 @@
     { "path": "./packages/subagent/subagent-fork" },
     { "path": "./packages/subagent/subagent-acp" },
     { "path": "./packages/todo/tool-todo" },
-    { "path": "./packages/hooks/hook-protocol" }
+    { "path": "./packages/hooks/hook-protocol" },
+    { "path": "./packages/hooks/hooks-claude" },
+    { "path": "./packages/hooks/hooks-codex" }
   ]
 }