@mmerterden/multi-agent-pipeline 20.28.0 → 20.29.0

package/CHANGELOG.md

@@ -16,6 +16,19 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ## [Unreleased]
 
+## [20.29.0] - 2026-10-24
+
+### Added
+
+- `run-stop-guard` (Stop hook): a session that drives a pipeline run cannot end its turn mid-run without finishing the current phase, recording an attended wait (`waitingFor: "attended-reply"` or `"local-test"`) or recording a halt. It acts only on the run bound to the session (`sessionId` or the new `hostSessionId` that write-state stamps on every phase move), never on a run matched by worktree alone, lets a turn through when it ends asking the user something, when background tasks or session crons are pending, and after three consecutive holds writes the halt itself. It fails open on any internal error and is switched off with `prefs.global.stopGuard.enabled: false`. SubagentStop is never held.
+- `write-state.mjs` accepts `status: "complete"` only on the run's final phase with Phase 4 evidence (a commit sha, PR or publish, or a noted skip) and a passing plan-coverage verdict; otherwise it exits 6 and writes nothing. Phase 5 reads that exit and reports the run completed only on success; the autopilot runner treats it as `stopped-incomplete` and retries.
+- Attended commit evidence check (`prefs.global.attendedCommitGate.mode`: `warn` by default, `block`, `off`), judged only against a live run.
+- `agent-guard`: AI attribution read from the commit message itself (message, `-F` file, heredoc body, or the whole line when the file is written on that line), skipped hooks (`--no-verify` and its prefixes, `commit -n`, `core.hooksPath`, `HUSKY=0`, `GIT_CONFIG_*`), plain secrets on argv (local development DSNs exempt), and an ask for issue close, Closes/Fixes/Resolves in a PR body and Jira transitions; in bypassPermissions and dontAsk a confirmation record written after the user's answer lets the exact command through once.
+- `run-scope-guard`: Figma MCP calls are refused after Phase 1 of a live, non-analysis run bound to the session; `/multi-agent:analysis` records its run at start. Attended edits outside the run's worktree raise a warning.
+- `prefs.global.readOnlyRepos[]`: checkouts that may not be edited, committed or pushed.
+- `/multi-agent:doctor` reports template hooks that are not registered or not executable and preferences that no registered hook enforces. The installer registers the run hooks itself, records them in `multi-agent-hook-manifest.json` after settings.json is written, and does not re-add a hook the user removed.
+
+
 ## [20.28.0] - 2026-10-24
 
 ### Added

package/README.md

@@ -412,7 +412,7 @@ The pipeline runs natively on **Claude Code**, **Copilot CLI** and **Codex CLI**
 
 | Tool        | Flag                 | What it installs                                                                                       |
 | ----------- | -------------------- | ------------------------------------------------------------------------------------------------------ |
-| Claude Code | `--claude` (default) | slash commands + skills + agents + three `PreToolUse` hooks (secret scan, agent-guard, read-size gate) |
+| Claude Code | `--claude` (default) | slash commands + skills + agents + the enforcement hooks (secret scan, agent-guard, read-size gate, run-scope guard, run-stop guard) |
 | Copilot CLI | `--copilot`          | instructions + 66 sub-command skills + scripts                                                         |
 | Codex CLI   | `--codex`            | one router skill + 66 specs as refs + 11 agent TOML + `AGENTS.md` block + `codex mcp add`               |
 
@@ -450,6 +450,19 @@ the one host whose panel spans two vendors, and the triage note says so.
 
 The **secret scan** runs as a `PreToolUse` hook on Claude Code (hard-blocks a commit on a hit) and as a pre-push check elsewhere.
 
+**Hooks per host.** The enforcement hooks are Claude Code's; `install` registers them and `/multi-agent:doctor` (`hook-reachability`) says which are missing from your settings.
+
+| Hook | Claude Code | Codex CLI | Copilot CLI |
+| --- | --- | --- | --- |
+| `pre-commit-check.sh` (secret scan, owned paths, attended build/test evidence, unattended ledger) | PreToolUse `Bash` | none: pre-push check | none: pre-push check |
+| `agent-guard.sh` (attribution, force-push, skipped git hooks, argv secrets, closure confirmations, read-only repos, unattended policy) | PreToolUse `Bash`, file edits, fetch and toolkit tools | none | none |
+| `run-scope-guard.sh` (Figma phase rule, worktree boundary warning) | PreToolUse Figma tools, file edits | none: the phase records its own MCP calls | none |
+| `run-stop-guard.sh` (no silent stop mid-run) | Stop | none: halts stay the phase's own write | none |
+| `edit-syntax-gate.sh` | PostToolUse file edits | PostToolUse `apply_patch` | none: Copilot discards postToolUse output |
+| `check-read-size.sh`, capture hooks | registered | none | none |
+
+Where a host has no equivalent hook the rule is still in the phase documents; it is a request there, not enforcement.
+
 ## Outside a pipeline run
 
 Installing the pipeline is not only useful when you run it. Open an ordinary session and the same three things are available, announced by `rules/outside-the-pipeline.md` which loads with every conversation:

package/docs/facts.json

@@ -1,7 +1,7 @@
 {
   "$comment": "Generated by pipeline/scripts/gen-facts.mjs. Do not hand-edit: the site reads this, and a number edited here instead of at its source is the drift this file removes.",
   "generatedAt": "2026-10-24",
-  "version": "20.28.0",
+  "version": "20.29.0",
   "phaseSchema": 2,
   "phases": [
     {

package/install/claude.mjs

@@ -837,6 +837,93 @@ export function quotePipelineHookCommands(hooks) {
   return changed;
 }
 
+/**
+ * The run-scoped hooks the installer registers beside the two gates above:
+ * run-stop-guard.sh (Stop) and run-scope-guard.sh (Figma MCP
+ * tools, file edits). Each is silent outside a pipeline run and fails open, so
+ * registering them by default changes nothing until a run is active. The same
+ * entries are in install/templates/claude-hooks.json.
+ */
+export const RUN_HOOKS = [
+  {
+    event: "Stop",
+    script: "run-stop-guard.sh",
+    timeout: 15,
+    statusMessage: "Checking the pipeline run is not left mid-phase...",
+  },
+  {
+    event: "PreToolUse",
+    matcher: "mcp__.*[Ff]igma.*",
+    script: "run-scope-guard.sh",
+    timeout: 10,
+    statusMessage: "Checking the Figma call against the run's phase...",
+  },
+  {
+    event: "PreToolUse",
+    matcher: AGENT_GUARD_FILE_MATCHER,
+    script: "run-scope-guard.sh",
+    timeout: 10,
+    statusMessage: "Checking the edit is inside the run's worktree...",
+  },
+];
+
+/**
+ * The record of which RUN_HOOKS an install has registered, under ~/.claude. A
+ * key in it whose hook is no longer in settings.json was removed by the user,
+ * and the next install leaves it removed. uninstall.mjs deletes the file.
+ */
+export const HOOK_MANIFEST = "multi-agent-hook-manifest.json";
+
+/** event|matcher|script, the identity of one RUN_HOOKS entry. */
+export const hookKey = (r) => `${r.event}|${r.matcher || ""}|${r.script}`;
+
+function readHookManifest(path) {
+  try {
+    const doc = JSON.parse(readFileSync(path, "utf-8"));
+    return new Set(Array.isArray(doc?.registered) ? doc.registered : []);
+  } catch {
+    return new Set();
+  }
+}
+
+/** True when an entry of the same event and matcher already runs the script. */
+export function hasHook(hooks, r) {
+  const groups = Array.isArray(hooks?.[r.event]) ? hooks[r.event] : [];
+  return groups.some(
+    (g) =>
+      (g?.matcher || "") === (r.matcher || "") &&
+      Array.isArray(g.hooks) &&
+      g.hooks.some((h) => typeof h?.command === "string" && h.command.includes(r.script)),
+  );
+}
+
+/**
+ * Add one pipeline hook unless an entry of the same event and matcher already
+ * runs its script. Returns true when it changed `hooks`.
+ *
+ * @param {object} hooks  settings.hooks
+ * @param {{event: string, matcher?: string, script: string, timeout: number, statusMessage: string}} r
+ */
+export function ensureHook(hooks, r) {
+  if (!Array.isArray(hooks[r.event])) hooks[r.event] = [];
+  const groups = hooks[r.event];
+  if (hasHook(hooks, r)) return false;
+  const hook = {
+    type: "command",
+    command: pipelineHookCommand(r.script),
+    timeout: r.timeout,
+    statusMessage: r.statusMessage,
+  };
+  // Joined to a group of the same matcher when there is one, so a file edit
+  // shows one group with both guards rather than two groups.
+  const same = groups.find(
+    (g) => (g?.matcher || "") === (r.matcher || "") && Array.isArray(g.hooks),
+  );
+  if (same) same.hooks.push(hook);
+  else groups.push(r.matcher ? { matcher: r.matcher, hooks: [hook] } : { hooks: [hook] });
+  return true;
+}
+
 export function configureSettings(home) {
   console.log("  [Claude Code] Configuring hooks + context management...");
   const SETTINGS_PATH = join(home, ".claude", "settings.json");
@@ -942,6 +1029,26 @@ export function configureSettings(home) {
       settingsChanged = true;
     }
 
+    const manifestPath = join(home, ".claude", HOOK_MANIFEST);
+    const manifest = readHookManifest(manifestPath);
+    let manifestChanged = false;
+    for (const r of RUN_HOOKS) {
+      const key = hookKey(r);
+      const had = manifest.has(key);
+      if (hasHook(settings.hooks, r)) {
+        if (!had) {
+          manifest.add(key);
+          manifestChanged = true;
+        }
+        continue;
+      }
+      // Registered by an earlier install and gone now: the user removed it.
+      if (had) continue;
+      ensureHook(settings.hooks, r);
+      manifest.add(key);
+      settingsChanged = true;
+      manifestChanged = true;
+    }
     if (collapseDuplicateHooks(settings.hooks)) settingsChanged = true;
 
     if (settingsChanged && isDryRun()) {
@@ -953,6 +1060,11 @@ export function configureSettings(home) {
     } else {
       console.log("    -> Hooks + env already configured");
     }
+    // After settings.json, so a failed write never records hooks as
+    // registered and the next install still adds them.
+    if (manifestChanged && !isDryRun()) {
+      writeFile(manifestPath, `${JSON.stringify({ registered: [...manifest].sort() }, null, 2)}\n`);
+    }
   } catch (e) {
     console.log(`    -> Warning: Could not configure settings.json: ${e.message}`);
   }

package/install/templates/claude-hooks.json

@@ -1,5 +1,5 @@
 {
-  "_readme": "Recommended Claude Code hooks for multi-agent-pipeline. `install` registers the pre-commit and agent-guard gates itself (install/claude.mjs configureSettings); /multi-agent:setup offers to merge the rest of this block. Merge the `hooks` object into your ~/.claude/settings.json to make these deterministic PreToolUse gates real (exit 2 blocks the tool call). A PreToolUse matcher is a regex over the TOOL NAME, so each gate registers on a tool name and reads the command from its stdin payload. Three PreToolUse gates ship here: (1) pre-commit-check.sh on Bash, which acts only on a `git commit` and blocks a secret in the staged diff; (2) agent-guard.sh on Bash, on Edit|Write|NotebookEdit, and on WebFetch plus every multi-agent-toolkit tool (WebFetch|mcp__multi-agent-toolkit__.*). Always, it blocks AI/assistant attribution in a commit message and a force-push, delete or mirror push to a protected branch (main/master/develop), including one inside a subshell or a `bash -c` / `eval` line. With MULTI_AGENT_UNATTENDED=1 in the hook's environment it also applies the unattended policy: no push, PR or tracker write, no Keychain read, no fetch outside the host allowlist (curl, WebFetch, the toolkit's web tools, agent_run_steps and open_url), no package install, and no write into a protected path (features/unattended-security.md); (3) check-read-size.sh on Read|Bash, which inspects Read plus the shell commands that read a file whole (cat/head/tail/sed), returns immediately for everything else, and routes an oversized read to a cheap worker instead of the caller's own rung; it is inert until `prefs.global.bulkRead.mode` is set to observe or enforce. Failure behaviour: pre-commit-check.sh and check-read-size.sh fail open on an internal error. agent-guard.sh fails open when attended, so a guard bug cannot break a legitimate tool call, and fails closed under MULTI_AGENT_UNATTENDED=1, where nobody is there to notice a gap. None of the three executes the inspected command, and none needs run-specific arguments. The other deterministic gates (evidence, consensus, intent, learnings) take run-specific arguments and are phase-enforced by the pipeline instead. Three capture hooks ship alongside them and block nothing: (4) SessionEnd runs capture-flush.sh --if-stale, which writes a run's triage findings and durable learnings into the per-repo stores when the run ended before Phase 5, where those writes otherwise happen; the same hook runs note-session.sh, which records the mechanical shape of a session outside the pipeline (tools used, commands that failed, calls the user refused). (5) PreCompact runs capture-flush.sh without --if-stale: a compaction summarizes the conversation mid-phase, so it is the moment unflushed findings are at risk, and both writes are idempotent, so a finished run costs two no-op writes. The staleness test exists only so a session exit does not re-flush a run that already finished. (6) SessionStart runs capture-resume.sh, which prints at most two lines: an unfinished run and how to resume it, and a stale pipeline-observation queue. No capture hook calls a model or reads a payload - note-session.sh keeps a command's first word and an exit code, never an argument or any output - and all exit 0 on every path, because a hook that fails a session over bookkeeping costs more than the bookkeeping. One PostToolUse hook ships as well and blocks nothing: (7) edit-syntax-gate.sh on Edit|Write|MultiEdit parses the file the edit just wrote (swiftc -parse, node --check, py_compile into a temp dir, JSON.parse, bash -n; Kotlin skipped) under a 2 s deadline and, when it no longer parses, hands the model the error as PostToolUse additionalContext; it exits 0 on every path, stays silent when a parser is missing or slow, and is inert until `prefs.global.editSyntaxGate.enabled` is true. These registrations are Claude Code's. On Codex only the syntax gate is offered, from codex-hooks.json through host-hooks.mjs; Copilot CLI gets none, since as of 1.0.45 it discards postToolUse output; the other gates are Claude Code only. multi-agent:setup offers to merge this block.",
+  "_readme": "Recommended Claude Code hooks for multi-agent-pipeline. `install` registers the pre-commit and agent-guard gates and the run-scoped run-stop-guard / run-scope-guard hooks itself (install/claude.mjs configureSettings, RUN_HOOKS); /multi-agent:setup offers to merge the rest of this block. Merge the `hooks` object into your ~/.claude/settings.json to make these deterministic PreToolUse gates real (exit 2 blocks the tool call). A PreToolUse matcher is a regex over the TOOL NAME, so each gate registers on a tool name and reads the command from its stdin payload. Three PreToolUse gates ship here: (1) pre-commit-check.sh on Bash, which acts only on a `git commit` and blocks a secret in the staged diff; (2) agent-guard.sh on Bash, on Edit|Write|NotebookEdit, and on WebFetch plus every multi-agent-toolkit tool (WebFetch|mcp__multi-agent-toolkit__.*). Always, it blocks AI/assistant attribution in a commit message and a force-push, delete or mirror push to a protected branch (main/master/develop), including one inside a subshell or a `bash -c` / `eval` line. With MULTI_AGENT_UNATTENDED=1 in the hook's environment it also applies the unattended policy: no push, PR or tracker write, no Keychain read, no fetch outside the host allowlist (curl, WebFetch, the toolkit's web tools, agent_run_steps and open_url), no package install, and no write into a protected path (features/unattended-security.md); (3) check-read-size.sh on Read|Bash, which inspects Read plus the shell commands that read a file whole (cat/head/tail/sed), returns immediately for everything else, and routes an oversized read to a cheap worker instead of the caller's own rung; it is inert until `prefs.global.bulkRead.mode` is set to observe or enforce. Failure behaviour: pre-commit-check.sh and check-read-size.sh fail open on an internal error. agent-guard.sh fails open when attended, so a guard bug cannot break a legitimate tool call, and fails closed under MULTI_AGENT_UNATTENDED=1, where nobody is there to notice a gap. None of the three executes the inspected command, and none needs run-specific arguments. The other deterministic gates (evidence, consensus, intent, learnings) take run-specific arguments and are phase-enforced by the pipeline instead. Three capture hooks ship alongside them and block nothing: (4) SessionEnd runs capture-flush.sh --if-stale, which writes a run's triage findings and durable learnings into the per-repo stores when the run ended before Phase 5, where those writes otherwise happen; the same hook runs note-session.sh, which records the mechanical shape of a session outside the pipeline (tools used, commands that failed, calls the user refused). (5) PreCompact runs capture-flush.sh without --if-stale: a compaction summarizes the conversation mid-phase, so it is the moment unflushed findings are at risk, and both writes are idempotent, so a finished run costs two no-op writes. The staleness test exists only so a session exit does not re-flush a run that already finished. (6) SessionStart runs capture-resume.sh, which prints at most two lines: an unfinished run and how to resume it, and a stale pipeline-observation queue. No capture hook calls a model or reads a payload - note-session.sh keeps a command's first word and an exit code, never an argument or any output - and all exit 0 on every path, because a hook that fails a session over bookkeeping costs more than the bookkeeping. A run-scoped PreToolUse gate ships too: (2b) run-scope-guard.sh on every Figma MCP tool (mcp__.*[Ff]igma.*) denies a Figma call above phases.json thresholds.mcpAllowedThroughPhase for the run bound to the session, unless the run is in analysis mode, and records each allowed call into telemetry.mcpCalls[]; on Edit|Write|NotebookEdit the same script warns, attended only, when the target is outside the bound run's worktree (additionalContext for the model, systemMessage for the user; the call proceeds). Outside a run it is silent, and it fails open. One PostToolUse hook ships as well and blocks nothing: (7) edit-syntax-gate.sh on Edit|Write|MultiEdit parses the file the edit just wrote (swiftc -parse, node --check, py_compile into a temp dir, JSON.parse, bash -n; Kotlin skipped) under a 2 s deadline and, when it no longer parses, hands the model the error as PostToolUse additionalContext; it exits 0 on every path, stays silent when a parser is missing or slow, and is inert until `prefs.global.editSyntaxGate.enabled` is true. One Stop hook ships as well: (8) run-stop-guard.sh answers {\"decision\":\"block\"} when the session driving an active pipeline run (bound through agent-state.json sessionId or hostSessionId, never by a worktree match) tries to stop while the run is in_progress below its mode's last phase with no haltReason or waitingFor; the reason says to finish the current phase, record the wait, or record a halt. A turn that ends on a question to the user, a session with background tasks or crons, and prefs.global.stopGuard.enabled false are never held, and SubagentStop is not registered: a subagent's stop is the dispatching session's business. After three consecutive blocks it records the halt itself (status paused, haltReason <phase>:stop-guard), which write-state clears when the run advances a phase. It never blocks outside a run and fails open, with a line in <log root>/hook-failures.log, on any error. These registrations are Claude Code's; README \"Hooks per host\" lists which have no equivalent elsewhere. On Codex only the syntax gate is offered, from codex-hooks.json through host-hooks.mjs; Copilot CLI gets none, since as of 1.0.45 it discards postToolUse output; the other gates are Claude Code only. multi-agent:setup offers to merge this block.",
   "hooks": {
     "PreToolUse": [
       {
@@ -27,6 +27,12 @@
             "command": "bash \"$HOME/.claude/scripts/agent-guard.sh\"",
             "timeout": 10,
             "statusMessage": "Checking the edit target..."
+          },
+          {
+            "type": "command",
+            "command": "bash \"$HOME/.claude/scripts/run-scope-guard.sh\"",
+            "timeout": 10,
+            "statusMessage": "Checking the edit is inside the run's worktree..."
           }
         ]
       },
@@ -51,6 +57,17 @@
             "statusMessage": "Checking read size..."
           }
         ]
+      },
+      {
+        "matcher": "mcp__.*[Ff]igma.*",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash \"$HOME/.claude/scripts/run-scope-guard.sh\"",
+            "timeout": 10,
+            "statusMessage": "Checking the Figma call against the run's phase..."
+          }
+        ]
       }
     ],
     "PostToolUse": [
@@ -108,6 +125,18 @@
           }
         ]
       }
+    ],
+    "Stop": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash \"$HOME/.claude/scripts/run-stop-guard.sh\"",
+            "timeout": 15,
+            "statusMessage": "Checking the pipeline run is not left mid-phase..."
+          }
+        ]
+      }
     ]
   }
 }

package/manifest.json

@@ -1,14 +1,14 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "20.28.0",
-  "commit": "c7a8a9c64602a1a4ec976f0fb2a017b66472ddac",
-  "generatedAt": "2026-10-24T12:59:08.424Z",
+  "version": "20.29.0",
+  "commit": "64ae83de4fa2e3571e1437c349a3f6283dbc7b24",
+  "generatedAt": "2026-10-24T18:20:54.711Z",
   "algorithm": "sha256",
-  "fileCount": 1425,
+  "fileCount": 1436,
   "files": {
-    "CHANGELOG.md": "cbd428d3ea3bf8d30ec3ea82fc07363d2ecd1f55b1ecdba74afab70066c17d7b",
+    "CHANGELOG.md": "71560c0097f24a88264b2771f57b7e35b7fbe6653a84a8a977b986e1ec5fa4ca",
     "LICENSE": "8d8c51aaf1e1538b180c69965fa038db71be86798cc3e26a143bebfefe16a43e",
-    "README.md": "6ff747b3a5c72b4528d13bb1162a6520b121e1f47842c617274a50d221baff79",
+    "README.md": "594e2d6539deffe27770a35e30ce600e37b7218044c0044a7f3487c947bf438f",
     "README.tr.md": "89aa799a7d6344fb32e2c08786c6be6d41ecc97892ffda298e90e04afa79b1bd",
     "SECURITY.md": "0eb89553ddcfc56bfe9712315b55a6630ee2f579631aaeccd6ad24f8ac769a0b",
     "docs/FIGMA_PIPELINE.md": "ea01f3ea5fef1a9cb316040a2d416fcf87dd4f2a14b5497aa00994a0b5dc7e6a",
@@ -34,7 +34,7 @@
     "docs/best-practices.md": "f8b75b0d38b5896a6a852bb30a1edddeb24dab8b5b7b1d9313290e1241c72024",
     "docs/ecosystem.md": "20e1b6fce9c8e477ab1fbc1239100e9b51cfa6618501a07761f9c3982a997219",
     "docs/engineering.md": "550528cd47c7d2c921729c68d0782a00ac8e77a4bdfec479f6749f9c3235d188",
-    "docs/facts.json": "de32070be7e53f1ca59629e53bfec54b533d8507e7a94cc3b2a38f87ebd2d870",
+    "docs/facts.json": "ad93671254332c6ad5352292d2b9df05bf2428c7757186a970082b130d52e7b9",
     "docs/features.md": "ae91aa35950e1023b7bf08aefdba9489a885e5c2effb293783768d521cb7de1b",
     "docs/performance.md": "bbf2f3922c25dcba0c1a9e69ef420e3871a729af5b35009a49b48a5d3c5cd151",
     "docs/recovery-guide.md": "59a8f1b66b34cb9ff5507b3d54dac3b9915e184aa044d9c758d18cac818d510e",
@@ -54,18 +54,18 @@
     "install/_usage-lifecycle.mjs": "4b010c4e75d6f8e13b58d80a93cc9407f42ccde781c9ed12dcb8e7faf05e526c",
     "install/_xcode-skills.mjs": "1a7e20f1e6743324b941c5d3ecac9f94c65fff1534ffd9c63b39cbea4f8d101a",
     "install/catalog-history.json": "7dd84d5ea1f61a09f78bf9f3bcf11112d5e8664dc3833d7a589108868152736e",
-    "install/claude.mjs": "106ce353ebc19c8319d057ce342e1f989519510465c798399076b5f3d8727904",
+    "install/claude.mjs": "737fda097077bc06e8fd062d09e43bd289b7fd434fce6e4ccd3ee2a9645f735b",
     "install/codex.mjs": "08925fe9f3ecdf509b37f01105652c847475d20fcde2db0d679b9a7d663ca145",
     "install/copilot.mjs": "41dc394b8a3ae77cfd194ce0ca9bbcafce9bdce349f1f72eeb86569f993e15fe",
     "install/index.mjs": "9bd77803ce0f548082c34bd2ad4dbe5bce4507410398276a39fe8e83b10a6160",
-    "install/templates/claude-hooks.json": "205dc29b59de20d14c11f73fc73f00550eb4d28c0d22bc9944c65723c34f0fa4",
+    "install/templates/claude-hooks.json": "2b1bd365fb79e54ffc8075c67998cd0ede2a026bf1fe6605f21ae3345add7dfb",
     "install/templates/codex-hooks.json": "f35edfb7f7d28a1d3322eed05aa6643e2bfe36e5a3be9714faba834ade8bff02",
     "install/templates/codex-instructions.md": "dd78eb9553e725c039380457245793a5fc748ae37ebf5ccfe11be5ed5b9a4025",
     "install/templates/copilot-instructions.md": "2450ca338960e298a231fde7b0e0a08001cbefc0da94d850a6a686eaee8c9b94",
     "install/templates/multi-agent-autopilot-awake.plist.template": "ddd25c76c56fcbb38a89de8e35637372d70ace993d6bc487a88ca9cfb702fe1f",
     "install/templates/multi-agent-autopilot.plist.template": "122c8a61cd927edd99375d6e3da40f1d42bcceed5b6641785c8b28bb930bc77e",
     "install/unattended-profile-legacy.json": "f52e86b998956f09ad306b1735a6c10b58580d7082d8a55665a4c6bb15c3aa1f",
-    "package.json": "fd1cf9622ee06b89f8a891478cf6b4adf0e65a576861f7270eac66ec7ba23dfe",
+    "package.json": "3a74b9a9f2bd1a2d080405b7606eac528c697934e5946cbc9f096c59f9df5770",
     "pipeline/agents/android-architect.md": "11fb74543cb0ebcf9525ca6654fe95d53da7229e0bf4a1149b31fd9005abc453",
     "pipeline/agents/backend-architect.md": "b02a606c301e4714131aed70ae6d16eeb77fbc819a001e2752cff2488d4246de",
     "pipeline/agents/bulk-reader.md": "6597052cd7d205bac2b1c7633f5232fe1a40730664a913b8eb77efd5a786dc25",
@@ -84,7 +84,7 @@
     "pipeline/commands/multi-agent/SKILL.md": "20e3d9af469af2e347700d1ff4a600e44a69a18f15f374ba107c011e52a1c31a",
     "pipeline/commands/multi-agent/analysis-jira/SKILL.md": "bb3d3c9c3b4a990b5fa5e5907108773d9bc73b39757164315f8f30f51efdefee",
     "pipeline/commands/multi-agent/analysis-resolve/SKILL.md": "48b72f59775ebfaab916afaeb2609e5694c0f7a3ce2bf2689cf25623d9755682",
-    "pipeline/commands/multi-agent/analysis/SKILL.md": "8b92d8832f72e195408d6e8e137956df3a4920074ccc0a4a130f36995aa0f6d9",
+    "pipeline/commands/multi-agent/analysis/SKILL.md": "abc74eaaf016f3d85758fce272aacaee6f772d2a6f8c5b3dbcfe205dda2613ac",
     "pipeline/commands/multi-agent/autopilot-off/SKILL.md": "1574f9801993b8ac301de8d60f49df0036175ca7bf95e1b4682b76b56ae6479f",
     "pipeline/commands/multi-agent/autopilot-on/SKILL.md": "d8f7847004f2bdcf7923527bddfaa17fb9f09a83fd5e3a9d997e0d1871907938",
     "pipeline/commands/multi-agent/autopilot-status/SKILL.md": "73cea063993bb5c6781112f7bba6f6dd2a5014bcdd4400f9f3c48b582f50252d",
@@ -117,7 +117,7 @@
     "pipeline/commands/multi-agent/purge/SKILL.md": "c881805f80d7db909bcf09f1a5c980ebaf0c31d9a8ee9cae4f729387ff4ca19d",
     "pipeline/commands/multi-agent/refactor/SKILL.md": "62501a11a4ff89578f4acddb9fe30becbed80b823beb1433a602db7b57939c54",
     "pipeline/commands/multi-agent/research/SKILL.md": "aab85ea942291b0a68aec5896b0b3f79677684733859a4c4cbb77931c7dacf92",
-    "pipeline/commands/multi-agent/resume/SKILL.md": "190a604ac1e87912ef2519f59199928d2329caa7a611bdc49fe237c43e885975",
+    "pipeline/commands/multi-agent/resume/SKILL.md": "33ed1eb053b58b5c099abe3a9819327aedba6d4d6ab0ff4eaf897c0569c6dd00",
     "pipeline/commands/multi-agent/review-analysis/SKILL.md": "2ba4ee67a56bd5f7041a02fcd227b5475b39f6e6a39b1f693cdf4bd5302c6e17",
     "pipeline/commands/multi-agent/review-issue/SKILL.md": "7ae7fe774c02114840cc21fb303f98c9a36bc2903f1db4cfc2cebe213ca70f1b",
     "pipeline/commands/multi-agent/review-jira/SKILL.md": "db8ecc7ec8c7040aac9c71dcf40dae194a76f146ab227833b909b45580b5347a",
@@ -168,7 +168,7 @@
     "pipeline/contract/fixtures/worktrees-empty.json": "d034639163424160a57767cbdcc10c544fa89154b6876aad35482badba0db58e",
     "pipeline/contract/frozen/toolbox.json": "d52f94ca81f62e4c0d67f0718ce6361f332f289b09fe7cc25c8f5f40feb0ffff",
     "pipeline/contract/manifest.json": "e9163ba923619447f872416d7f57ea48d67dc13c356c9544f24957f4131946bf",
-    "pipeline/contract/types/index.d.ts": "1434e70701023a7274fb13c9dbdf901b2a0d7259e46f3fcf40fe2454300c32a3",
+    "pipeline/contract/types/index.d.ts": "a449a8c0ce433c302c491077092d05b6a3949b3152b499f3d933478ddcb1c615",
     "pipeline/lib/_jira-auth.sh": "b5fd733ac26727eda299976c688456e95611ca40acafd3947c66c445d77f2237",
     "pipeline/lib/account-resolver.sh": "f7bef9beba3f839268509361651be0b1e1f319f2f23821f90ba466fdf185a8f6",
     "pipeline/lib/agent-model-sync.mjs": "2e0264ca8d8fef761563db219d588fed9067847043f960f68f055c186c20b668",
@@ -203,6 +203,7 @@
     "pipeline/lib/figma-screenshot.sh": "b043d1b64188ecae63f814ec100d23cdb13500dbc63b0ffc3186f8dd11663ea8",
     "pipeline/lib/figma-token.sh": "b192b1d3c8f75f1deb81731e95e080372d87fb44779805d05cdb7cb585ee1db0",
     "pipeline/lib/gc-report.sh": "a70a1fbaea4fb6dbb9a56471119e403071b4358fb0d4577b62bb4d5e08eaf87e",
+    "pipeline/lib/hook-registration.mjs": "65987123bdb851c6265f5abc6756783ab57ef4425017e6f85bbf2291d4dbc7a9",
     "pipeline/lib/invoked-directly.mjs": "a7014f252174414c267cc303a992aa9f3986541c5aad188c87cc6809ba3b69bd",
     "pipeline/lib/issue-fetcher.sh": "a074c100d31d08bd04573ae77f51beda4174dc4eaf6781e31000b13117e59da0",
     "pipeline/lib/jira-epic-link.sh": "b5f9ce1067cd8e9f0e547da4e681b71e4ff8c145e9a759fc98f83703dfca4d35",
@@ -223,6 +224,7 @@
     "pipeline/lib/plugin-skill-roots.mjs": "41d4c3d52642915732f859a49097ba54582a88ba729c070fd3b39cd5da8c7789",
     "pipeline/lib/post-pr-review.sh": "8f508753b4b820eb85d490a6458c13279a5f6a69c7175c9f6edc5fdadc5ffb42",
     "pipeline/lib/pr-request-location.mjs": "622ca4705ec8ee00e0a4609657d8ee684fcdc077f3099ab312cf41b5b0c41efd",
+    "pipeline/lib/prefs-value.mjs": "7e7ca201049f2facff57bda5a5e7ee8fa057d0e1e082a212069533159b5f798d",
     "pipeline/lib/redact.mjs": "443034132ec8163e3b923ca2b8d5304d575c02bd7396523ee677f36444adc7f7",
     "pipeline/lib/regular-file.mjs": "084dd2c98a664a1e4a937757cc5e5e5d7e162b6aa422f8c7cfdb27f7834c6cbc",
     "pipeline/lib/repo-cache.sh": "82bbdd3d61746042ad5341554a1077098d4b56f15caf6c5cc092377a273c8f45",
@@ -232,6 +234,7 @@
     "pipeline/lib/require-jq.sh": "a137b4df202515c2b89d5b93c3e28b04c73c8bc2f7c42be9ca9a22926e042918",
     "pipeline/lib/review-watch.sh": "89a53f79aab902a39ab8301cabe6eb54c8dc854af4d97c024c6b3b1f3ab38a75",
     "pipeline/lib/route-state.sh": "4f9ed53b1cdc1a6d32495e8d2794dd9e419825a47b4335e9c84e1af9351afa11",
+    "pipeline/lib/run-completion.mjs": "b5f6a561f0e717c57f3c482023b83df0f54d6045da917cc1bc8026073a9db802",
     "pipeline/lib/run-paths.sh": "2063a1d2f07d6caa391089c1e581fd870a4e9c3caa3b0c25a03f0b4fe4f6d070",
     "pipeline/lib/shadow-git.sh": "d5ade4e8674ea6ba1d95d21a71ce4bcd64a956d76b163155d93181d2cb18a3ee",
     "pipeline/lib/stack-detect.sh": "53242b46482547f861625b9cbf44b65790849bce7e42be3bbd56abac67bc3489",
@@ -261,7 +264,7 @@
     "pipeline/multi-agent-refs/analysis/intake.md": "192a2da33ceaf4a255645960bc7d6883ab2845b9d45b30ada8faafaf4ad82aba",
     "pipeline/multi-agent-refs/analysis/locked.md": "c914d3da5182bfbb3ba613299cf38f12832fda2f17e1968e5a8fd7b32d867bdf",
     "pipeline/multi-agent-refs/analysis/redesign.md": "6314fc1e14e05166efbea4819d5b07adb838d0704bde61b4b69cef637f251d58",
-    "pipeline/multi-agent-refs/analysis/render.md": "c3dc2c4dea9c5094ca538abda20543f7fbbca64d3e15f41c3c9e1eae7a64f095",
+    "pipeline/multi-agent-refs/analysis/render.md": "66c7f64d916a20f0221d3dc9a11a1466fd27d48f4ac46fa86b96452a23270afe",
     "pipeline/multi-agent-refs/analysis/resolve.md": "2e3631a8a9af999e01c66455378020e2134e6ca91bed3a40cd94717da94a34cb",
     "pipeline/multi-agent-refs/analysis/resume.md": "25a430b3a81c877b31c473cb0b708b1b225de3faf4d5f4b2918908df305c6d90",
     "pipeline/multi-agent-refs/analysis/reusable-refs.md": "6058c704a689d20af95a13295fd2e34f8636647f16ab991961ad9b7c0655bd34",
@@ -306,7 +309,7 @@
     "pipeline/multi-agent-refs/features/cost-analysis.md": "382eacef66efa8aa3ec4a2b01e235c5673b26333bbc8974df5a09694f1e5d7f3",
     "pipeline/multi-agent-refs/features/design-conformance.md": "a88ca595827cafa0c87c2facfcf9190dac69485e0596e5c198c6fc1613880452",
     "pipeline/multi-agent-refs/features/dev-critic.md": "08e01edef04b5ac216f8f43332126966d33da7b95625e47a8a6cd8ac105b263f",
-    "pipeline/multi-agent-refs/features/doctor.md": "a0c4cd940579a3fc8c1b89845419d0bbad49e5e87dc9b748fe9b9a8ab06ce075",
+    "pipeline/multi-agent-refs/features/doctor.md": "475de4941be738fb2036873f6126040373f4604b307743d92318d3d35fe43128",
     "pipeline/multi-agent-refs/features/exploratory-testing.md": "ac534fdb9e056b1a3782f9b9e38f0b8823f85e03cb85924513079179e318c45d",
     "pipeline/multi-agent-refs/features/external-context-injection.md": "be9a0e904efd52535fa18a254567c9d0c3fc2ed12fcbc7a116f7879048303df6",
     "pipeline/multi-agent-refs/features/free-models.md": "64afaba7e7a77575f4ed6a10905a01330a83f573907fb1a5d5356ae6c80999a0",
@@ -365,13 +368,13 @@
     "pipeline/multi-agent-refs/phases.md": "77d04389edaa7aaf4e3a0faffebb2d2228b9e635fcb1e91f48b3f7d351f8aff4",
     "pipeline/multi-agent-refs/phases/log-format.md": "62d51e57cca8445ab40f3c0dc29615e4b5c8e4743286bf9ef0173610e81397aa",
     "pipeline/multi-agent-refs/phases/modes.md": "0733e20dce458c09f30343db9149fc93bc5a4c9531670b93952f223811dcb1aa",
-    "pipeline/multi-agent-refs/phases/operations.md": "4718f7f7d1deeb787ae7aaf6fd3be501bb8244e3b35cd5ba11ce6c76d37a64e8",
-    "pipeline/multi-agent-refs/phases/phase-0-init.md": "3817e3be71adbf30a082713895531ef0e7fed29a32b77ce351103f1dfcd8669c",
-    "pipeline/multi-agent-refs/phases/phase-1-plan.md": "de3f3dc16ae8853740540caa5497d2f18f016dcb7ea0bfc280ca5c136259a078",
-    "pipeline/multi-agent-refs/phases/phase-2-dev.md": "75925e51a47449af1a598394d69b6e84ce179a9a5d4a7a5b3d4583c73aa5926c",
-    "pipeline/multi-agent-refs/phases/phase-3-review.md": "4453fd86d62f30ce60a9986c6a609160b953bcb5295052cd2122377981427de9",
-    "pipeline/multi-agent-refs/phases/phase-4-commit.md": "49565e1d4bff37e60b6299787e77456d1b1707e42d03a1797612be0604bd0983",
-    "pipeline/multi-agent-refs/phases/phase-5-report.md": "7fcd37b02dc4da3d04ff9c0eb7f69e7740e1215c07e556b91a10d83582b2f49b",
+    "pipeline/multi-agent-refs/phases/operations.md": "aa84c6af264f038100e0942c4a2b3db545d122d5a27a4211f061e6537f717ad1",
+    "pipeline/multi-agent-refs/phases/phase-0-init.md": "5579f56a9ed054071f0f2201e167617bce7a86ef8a7faf54aebb17bd3fc8d742",
+    "pipeline/multi-agent-refs/phases/phase-1-plan.md": "3062c069b09b82929e266bcf96d50df1e25e168235d5b488a8114a8ccb6d4142",
+    "pipeline/multi-agent-refs/phases/phase-2-dev.md": "237587c469287818e13032e7dfb98a7b8c274b5df2eece5663de3ad95e444af3",
+    "pipeline/multi-agent-refs/phases/phase-3-review.md": "3a663797e370376caa3781fa802477139870d3576ef192729667027b83ae6f2f",
+    "pipeline/multi-agent-refs/phases/phase-4-commit.md": "1f2e3ffaae2043aa1aa3f65cf4bd3cacd142fbf56ec613510f2619ec8f381601",
+    "pipeline/multi-agent-refs/phases/phase-5-report.md": "ff0e41b96af415b05fcf0d561650dab4f47e0e2e54985911a7cd2d456ff71418",
     "pipeline/multi-agent-refs/picker-contract.md": "c03970ad8ebb36ff8742b41cc05b615a907d0cbd363e714a3da687f4aed25bba",
     "pipeline/multi-agent-refs/platform-parity.md": "1fa6189ad94ecd3e8a9f15980f19174dc86468050a6de3afff7aa30de60aa689",
     "pipeline/multi-agent-refs/progress-contract.md": "d1dc3c117aeb880cd44b3439062e9fe7d5e2042ba00c49fd495f70a6bdc1addc",
@@ -409,12 +412,12 @@
     "pipeline/multi-agent-refs/web-guide.md": "714cba0d92fa45bf71fbff21bb2f09c88534ebf785b3a2ea96d18037e2e7f7f9",
     "pipeline/multi-agent-refs/website-deploy.md": "ce819c8b1ef8e8ec3257611379aaf0ab4678e08e0b58bd88c936e98cb8ead609",
     "pipeline/multi-agent-refs/wiki-capture.md": "bfd33cf097b966e61f80c9235d98c8139e4c9ede2e47c14b920a5b910cdc76d8",
-    "pipeline/preferences-template.json": "f8d06d8fb148bd8d3d9042a092bd4aa73e7fdfd122628f7e2f23375946594df7",
+    "pipeline/preferences-template.json": "f28da92a62bebd7fc8a8b71a72dfe3dabaa83ce88fcde796e377fb326c49486f",
     "pipeline/rules/app-store-guidelines.md": "9fc2ac5073a2d6be9fe6f056170bf215ecd14ad4d335062ad046bc3c406e6b59",
     "pipeline/rules/code-review.md": "b18eec5cec31710fe76cdae6f03b53e7403d4f0406274691ab38a4771505a1c5",
     "pipeline/rules/code-style.md": "cd7d8fa872d1d640d143a573a0bdeeb7a9095f62a4d69741a11b4f0cee9d5a48",
     "pipeline/rules/debugging.md": "6ca90aacf1f4bad59000da84a7a8e368eda69af0752ca9ec8e4916408502257a",
-    "pipeline/rules/figma-pipeline.md": "ad300703e42ebf0aa973f56ba7656911b5e78ddbb261e8192a6bd00b8603fdd2",
+    "pipeline/rules/figma-pipeline.md": "334ac80032042cd14cecfcd7dda97c7e8c71771fb244f72d9af2451324c7e083",
     "pipeline/rules/git-conventions.md": "200408fb59e19898096aca998381974f23929760c661741dd76813de902386eb",
     "pipeline/rules/kotlin-android.md": "2344356125cbdd49f703144f3eb573d40fd1ce2d4b5ef404d44da13c052c9236",
     "pipeline/rules/outside-the-pipeline.md": "f5ae881783bb288d803938665489a1135ef7d18e59cd52d85a290c1237450d4a",
@@ -424,7 +427,7 @@
     "pipeline/rules/swiftui-qa.md": "8c4afe9e72413e7bdab655f3d17588469e80ac34cb7ad2a690901fc5b6534818",
     "pipeline/rules/tdd.md": "4c1b3114506aa9794c9bb1e1aee1b1bbb4a993d192342e5697cc00bc2f6ea4a2",
     "pipeline/rules/testing.md": "695be5520b65451f0aa300a9643df2c05e607ff6ad372201ea34798dc5998bd5",
-    "pipeline/schemas/agent-state.schema.json": "96c8a9d57b4ab14332c81a098a9da20828128f5dc1c1924a1bde17d65752087b",
+    "pipeline/schemas/agent-state.schema.json": "0ac2542b975b8bfd015f28c871e90c2a6dd383435031eb8288007ee9a04041a9",
     "pipeline/schemas/analysis-output.schema.json": "41826f4bf7c96778f8cdbcc68531e984087897d438b7b49ac5a93fc29db47916",
     "pipeline/schemas/analysis-spec.schema.json": "43770223266be1c94e2cdea585efb6783043353bc5a374613b554596f46e1bcd",
     "pipeline/schemas/answer-request.schema.json": "29d4211a2a05a230e0707b171b73341d2e56f6b83edb178b731905211aab4e23",
@@ -470,15 +473,15 @@
     "pipeline/schemas/migrations/prefs-2.7.0-to-2.8.0.mjs": "56e3bdd076500825782726eb14f48c1f989c802bbd6374873999a949afee968f",
     "pipeline/schemas/migrations/state-2.0.0-to-2.1.0.mjs": "b7058a8922dfa85a817616ab130d6e962a1e1b8e9ed42b8700ff82747a0f3fec",
     "pipeline/schemas/migrations/state-2.1.0-to-2.2.0.mjs": "96c14fcc6375d630681e69c27dc0cad1783596fa93e1426d1a03d6257f1bd053",
-    "pipeline/schemas/phases.json": "f290b26a6606ab3508fd214881a334534a670f90c5f68e281790585b6c131b17",
-    "pipeline/schemas/phases.schema.json": "804eff7978f7cb6ea061627e2730567df03d56bd3d05f8336c20b9787f404ad8",
+    "pipeline/schemas/phases.json": "97a3b0452a6a19f13324906cd0ac0fc5e035d6e48363daab2402da523de8153a",
+    "pipeline/schemas/phases.schema.json": "d608d40f315d43a2f2a46a62b1663fa85ca245133d4d1c45ad2d85ca419f8bb6",
     "pipeline/schemas/phone-devices.schema.json": "4dcdd5b1fbd863e1b9528fe038ddec1af6ad88cafb020d0f69b5e12720acfec9",
     "pipeline/schemas/phone-signed-request.schema.json": "1785de1b523c52943e24f24d3d21f3fda7e670c177872bbe51d62c100db875a8",
     "pipeline/schemas/plan-critique.schema.json": "f24451157a8920bf0c6f23dd31e1d58ae408ad6f428661743ffbe2186c5b9e80",
     "pipeline/schemas/plan-todos.schema.json": "be4374b7eeb513fb8a7663374defa5b35ae084f72e112faa41b07c46532c50de",
     "pipeline/schemas/planning-output.schema.json": "6aea9b5b8bbf7f9a227215c29cc30a5b642981a02fe2a81eaf9e8a113f7c3947",
     "pipeline/schemas/pr-request.schema.json": "ae75c4856349d62834802b1189af516bb6fb3d36646831b7ff2fa61d938afcd0",
-    "pipeline/schemas/prefs.schema.json": "0d048365d84c0ac19c0a2f86daaffdf502608e24e8d7e784646d5209566f240b",
+    "pipeline/schemas/prefs.schema.json": "836403fb19a53c7721c58ad6849139ee076ae700e69c9331e01582eab57aed9a",
     "pipeline/schemas/repo-profile.schema.json": "1a74ef8330da9a26a5a70955f6f9cbb20eda54a8615efaf86c7993d420a7f04e",
     "pipeline/schemas/repos.schema.json": "a9bf56f25c66201c170912e3389bd73e4a3f61922410f83e31a6c6ba47aee861",
     "pipeline/schemas/research-output.schema.json": "54e3ba1b04fdc20fbaa84333b943a8ab95d1395c7b0e0aedc67929184cb49523",
@@ -490,7 +493,7 @@
     "pipeline/schemas/run-log.schema.json": "3ac10faf0aafb05a8ae89e027b7923aee604cb4bf8daebdbbf4da8c31bc97a1d",
     "pipeline/schemas/run-questions.json": "7928448ac408b8e90df2e24070c7d433691fe861315adb80ea754c7d21db7688",
     "pipeline/schemas/run-questions.schema.json": "d4b5b4c3e297164182dac7e86ba05e350f41085a7f024c6c7adefb0be42c4a8e",
-    "pipeline/schemas/runs-index.schema.json": "ad7d598f39a599031f89339a955fc939624fc127a635c70f5cc4667b9395124f",
+    "pipeline/schemas/runs-index.schema.json": "d000078ef69655a7497934510eca65bb6077ee8e341a4abbe8480f295f1c5f83",
     "pipeline/schemas/scaffold-manifest.schema.json": "4ee8dfacf646a96c62438234bedab9d286d80d1a6d3d4984361d91a7411ce171",
     "pipeline/schemas/scope-check.schema.json": "f96973c59372b36b7d68b9ac4b03490e7da8d54acf29a35947f5f610e82b98ea",
     "pipeline/schemas/secret-patterns.json": "4ae313b7f2529252b71be8b1cbee9bfd954cad6a9d0f30248a2593d1212a4c08",
@@ -514,14 +517,16 @@
     "pipeline/schemas/unattended-profile.schema.json": "a9c0979f0d0742826e410fdbfe1ae1c4a56b05b4e638eec42d4c276d6f48f701",
     "pipeline/schemas/worktrees.schema.json": "4e15c413c00811814eee734d86734ad9e1d34a37737f7df641b389ce5d8d134b",
     "pipeline/scripts/README.md": "4cdf7054cddbe5cdcb08460f68782f2347a26c8c343d8ef8418714464672b36c",
+    "pipeline/scripts/_active-run.mjs": "90510e4474437567fdcf5ea10df9f8634377e97db0233369e5bf83929996d304",
     "pipeline/scripts/_autopilot-config.mjs": "0f42d2791f1d71c4aad5a0735ca56fef1ed27d275b72f99d8ca8f95fcb8aa83a",
     "pipeline/scripts/_autopilot-ops.mjs": "5e84d628482434c8f09dc69601c73ab70e928af15c2f068d998d2f61bd692d1a",
-    "pipeline/scripts/_autopilot-outcomes.mjs": "5b2423814d979ed5c657473290083b296f7245d40507c866e7931b2771001236",
+    "pipeline/scripts/_autopilot-outcomes.mjs": "859c733e5885cc1245fec4ab8d2568aa35a049d4e1391228a6ac063d9257fd06",
     "pipeline/scripts/_code-graph.mjs": "bda1016c83dde84c010016a9e6030e85ff43b5b9d44365b90c761df5089eecb6",
     "pipeline/scripts/_command-contract.mjs": "e97a5c624e0768769da54d4175e9f7655f1de1dcd0832468bc66bf140b0f5a6f",
     "pipeline/scripts/_cost.mjs": "bdf03835af4719b72e4574f2d5ca827e94f9d80e49527a8e9e200a0aa4ecd7a9",
     "pipeline/scripts/_diff-impact.mjs": "cda016ca6071c741a680a3dbc35bb21926465b296defa4fa3677ce550704198a",
     "pipeline/scripts/_fingerprint.mjs": "d8c63b062a3be0e138b6675aa031824fcd96f5517cf0f7b477378913c1db7d73",
+    "pipeline/scripts/_guard_rules.py": "ff556374bf1233cce498cec99b7e6f07f87465b9a8300baf5bc089b7a2788607",
     "pipeline/scripts/_handle-patterns.mjs": "c05934a1eed9d97b3d1f8681916aac53092c6573dba83d798bbec9fc56d0909e",
     "pipeline/scripts/_http-post.mjs": "12cd785bbeebd5a914fc913277a1ab34e3944ce9267317d7454b09bf4a287588",
     "pipeline/scripts/_jsonl.mjs": "9de314d31f5016373c2cb5fcc2707c9d409b8c14da44b349c96c90c54ffa2d37",
@@ -542,8 +547,8 @@
     "pipeline/scripts/_transcript-hosts.mjs": "eae0c6825171121b1bca3d00dcfac1218857b30c2df2d9cfdfcf1d2c929a8a97",
     "pipeline/scripts/_unified-diff.mjs": "3291361f2e635a9de132c6129077130709d16250a489ec979e352fbeb0839347",
     "pipeline/scripts/_worktree-snapshot.mjs": "3fc5ae951d5d6ebc40ab05b4191d85779662e328855592085d2ed0c44a6028a7",
-    "pipeline/scripts/agent-guard.py": "ba8f0c08a80d953d339ea69492efb1fbe8db5d364c2bcb2094a9839cf6dcc081",
-    "pipeline/scripts/agent-guard.sh": "5b57cea687754533c673b66a9dd2281ca06d12ef86bdc0d03fa285fc9e7debf8",
+    "pipeline/scripts/agent-guard.py": "0a4ec72eee76d9d03a68e86bb3a8b7ca815d99c24dd64e3c03dbf681d55814fd",
+    "pipeline/scripts/agent-guard.sh": "0a37b766b95ab4af629e2a302e27969c29823293d44b659c53735e1d6d1aa538",
     "pipeline/scripts/aggregate-metrics.mjs": "c324e349993fb154a885263cf6665af0ff656e9c987b455a263dad8b96cca667",
     "pipeline/scripts/analysis-conform-coverage.mjs": "2b7de99855d1901b1b7803f47d4bb5f75ed5df1b5f4840d55bfc3537e3f65afe",
     "pipeline/scripts/analysis-sources.mjs": "53d843b0504a6cadd7d4a047331ebc34a2868304fcf791617ad0a215396e35a6",
@@ -552,6 +557,7 @@
     "pipeline/scripts/analysis-tickets-writeback.mjs": "8c1f117ac5c6516385e3458462de6bde28c81768853c2d9524118d0155befe8b",
     "pipeline/scripts/anonymize-findings.mjs": "5d7e042793790c1b924d4d952b4f79b7e5f1dd0a3fe936f1ee16a4fa2ba820dd",
     "pipeline/scripts/answer-question.mjs": "b948df9d063f623a7ccd9cc65903c4388018b6b968228f77eb2e229223a61b1c",
+    "pipeline/scripts/argv-secret-scan.mjs": "5878598c12b8e02971d5ff51ae2a5d78479d2e545f69f619166227ae75bb1af8",
     "pipeline/scripts/audit-log-rotate.sh": "5a4ef7d9ac75abbc5a5103fc2202b89707a2f2c00432ece133a132b483cd7450",
     "pipeline/scripts/audit-log.sh": "a2f721f88edb3dde6647c4438a37f419eeafcd37166be022907876799981e13d",
     "pipeline/scripts/autopilot-arming.mjs": "38224fc58dc208e5e2d5793302cb67c6d0ab75be2dc4259cbe55ac87102a59b7",
@@ -560,7 +566,7 @@
     "pipeline/scripts/autopilot-intake.mjs": "a65ac29850de94002bebd5db3f09b406c65f1875b32058cccea6b440f95c7526",
     "pipeline/scripts/autopilot-menubar.swift": "4fa39e603630565ac2cfb5a8b0bcf891dbefb02ce272252b9480605241670ac7",
     "pipeline/scripts/autopilot-publish.mjs": "f300fdb166eaa2107dc87102e1b9cd351346d1c4139200e2305a20861c8149f9",
-    "pipeline/scripts/autopilot-runner.mjs": "b215d87143dda5952bd67e2d123e606da7e3589effee5bbcb8e4f634b6ab38f1",
+    "pipeline/scripts/autopilot-runner.mjs": "f2adce65f08afe6cb319df3a33279983af571de16e4fa4590a4278ac9d7046bf",
     "pipeline/scripts/autopilot-status.sh": "8b9807155cfe5eff09ee3e01a8c3e5d1bbf7554db22de89de438531e4554b32f",
     "pipeline/scripts/base-branch-candidates.mjs": "c73a02033ed9f10c15b3aaf010432f0d4e429a75eba14731e9a64492e3fe3859",
     "pipeline/scripts/bug-bash.mjs": "290f613b0e4c018f79b3800de0579a17971935700216eb99b11676f03c713081",
@@ -582,6 +588,7 @@
     "pipeline/scripts/code-graph-rules/node.json": "062d7337519f5a743da6953d2748e95560729715502a665d19025108ceba4845",
     "pipeline/scripts/code-graph-rules/python.json": "91394dc31a9392e8d02cf46797bf39551fbe483aa2e6b34145cd33aa2460eca9",
     "pipeline/scripts/commands.mjs": "5b20a7d01aa0f205f2605fcfcbdb197bdfeafbdfc1e5164b5ee083ac6ff39cc2",
+    "pipeline/scripts/confirm-command.mjs": "d6dbbd4153b64b020b5cf130f900db3c6a3de57d5c5701cfa578be976bba4a92",
     "pipeline/scripts/confluence-readback.mjs": "4b4d190095346e54875de63df5380c143eb8c2f1a6eebb399d5ae884d8668b18",
     "pipeline/scripts/constitution.mjs": "c1de46e1252a26b301c81ddf3e59cd567d214e5918665c0cd708c69b4b5a37a8",
     "pipeline/scripts/contract-server.mjs": "d8a0a6b604487548dcf3383af15f0646c4018d15e052f223754b5aa9c34b26bc",
@@ -594,17 +601,17 @@
     "pipeline/scripts/decisions-log.mjs": "7e81432b76f3efaa1db3dd23febcf33f37baa1cfcff32a33890dc338504472e2",
     "pipeline/scripts/diff-explain.mjs": "194d0635639607cb1af3de064453162e01c0d59dc0c2e187d21d45bae3bc559c",
     "pipeline/scripts/diff-risk-score.mjs": "70bac656acc6154a13cc20a8174101b133531b9d1963f40f16bb162622d0017d",
-    "pipeline/scripts/doctor.mjs": "5980687d3e45bb62fc1e45766ed86960ed8ed05d2c6119cd8b9550ca7f178319",
+    "pipeline/scripts/doctor.mjs": "892b3ebc471f0c3693023c16bd240953ea889e47a947ef04438908e2ed4ad7dc",
     "pipeline/scripts/edit-syntax-gate.mjs": "e8b4297ef0ce55204670da70ea098708eb93f3b9687d74b7fde7d4e0ed2ea810",
     "pipeline/scripts/edit-syntax-gate.sh": "bc4e2b26f696e71c8f5b27938f41903cc24e36cc85200c4b9e2665e610af0ff6",
     "pipeline/scripts/estimate.mjs": "9847e412dd74ac19a5c3b84bed343f79d25f256022b2df98e3eb1296db45ed3a",
-    "pipeline/scripts/evidence-gate.mjs": "dc3b9bfdd959cf6e577b7fd634a444eb21adb09dab22d4dd7465c7a92d00440c",
+    "pipeline/scripts/evidence-gate.mjs": "f6452999e62d909a9af7d56de1cb9da6919f5db7511793e2c9179625cf2f47a1",
     "pipeline/scripts/explore-findings.mjs": "997cca3ef42a170ff51ee2c382263eff8653affd6bb675877b94b8bba782e717",
     "pipeline/scripts/feedback-send.mjs": "d3ed66e9dacdfb4b5eacf1b244bf66752304fb4fcb144531441b458f3ab806be",
     "pipeline/scripts/find-polluter.mjs": "38a5797acb63f2c9c66c7c29801066f6e8ba1fa9ded680433814a8a86e0cd5ef",
     "pipeline/scripts/finding-fingerprint.mjs": "fa12ab10701db5d2bfff014e41d1cd4c0b2b772aee5fc69205de14b2761b0c83",
     "pipeline/scripts/firebase-app-discovery.sh": "dbbc5710cf12b086a50c3f24a4cf67df431d1eb1a121b98d4dc67023f8633c67",
-    "pipeline/scripts/gate-ledger.mjs": "c5c58ef5fe12aa0c9a3732ae06b76877ce74f004bc1f6058ce0014c5c963628e",
+    "pipeline/scripts/gate-ledger.mjs": "03ee20c491d9f7560756b5b1c83b8269b4b049cb525228716ef23082567535d4",
     "pipeline/scripts/gc-abandoned.sh": "d11dc1a8144fc639b57d668d4801d9bb088c700f6e93fdc78d60f8e6018ec99e",
     "pipeline/scripts/gc-plan.mjs": "f1d212805ef5396f0ae789d997894017a60917b7c55bad5271e29c76cde898af",
     "pipeline/scripts/gc-refs.sh": "04e91087885bac10ee692cc24914342a459bcfc5533574894e40e43587cec325",
@@ -656,13 +663,13 @@
     "pipeline/scripts/phase0-exit-gate.mjs": "068fb9bb32209326f4c4a9d1f82bc1a419808242803d5452028c3dbffe70c9fd",
     "pipeline/scripts/phone-devices.mjs": "f32288cbe56670eecb7d3a4b43f9ebcb4baeac5eeec357322fe19399603d59e3",
     "pipeline/scripts/plan-complexity.mjs": "ac8e4ad857cabc80fe4051bec84490bb91bfdf75d61cfdad93e315d0965f04b8",
-    "pipeline/scripts/plan-coverage-gate.mjs": "1a83bc52584438a9bd5cba96d2ddefed92a6a317d30ee695e67ef6c00b93e5a8",
+    "pipeline/scripts/plan-coverage-gate.mjs": "64c610a0101f10c7bb74cb021dea5d471fd018a11baae03007f834fe6b69b2f7",
     "pipeline/scripts/plan-critique-gate.mjs": "b139394e5f16d11e4997d0bb0b08529f439dbd7fad39781ef4c2475247d8fa97",
     "pipeline/scripts/plan-remote-links.mjs": "81673a25b9b9f19edd15ebd1e198552b658a7ec6d138658ec4e6e5b58213bb3a",
     "pipeline/scripts/plugin-refresh.sh": "687a33199ad963616ab537e32210ec8c967e76ecc42f494ee8a1dc9fe947fc30",
     "pipeline/scripts/pr-request.mjs": "e6f4ded2366c6599bb345b3011ecc771e13b8a1561afa4c9a50bca4edff17456",
     "pipeline/scripts/pr-timeline.mjs": "6a12df12a72f3440796569d3264edb0b3e105be6e4f2e26e958a5a0da340d05c",
-    "pipeline/scripts/pre-commit-check.sh": "6012f0d4f55ef9e6ace2e9cf7e4a85cabce89c08ca5e2c6f625cd8e28bf449c1",
+    "pipeline/scripts/pre-commit-check.sh": "beb51dc3e3ff69ebca266625da95c2060c41ee0173dd2a47deb1ab5e7fa63d78",
     "pipeline/scripts/pre-push-check.sh": "6e9761fed96e3bae111ccd554b44e35917517c6a8ae5dae7236fe8c69e7fe122",
     "pipeline/scripts/probe-evidence-capability.sh": "ac74252eed6b773fdbc7ec475a63606925f1ba7b5e7c6f911329f46fd920eae7",
     "pipeline/scripts/probe-store-key.mjs": "b46dfcf444c95d0bb61de36823314945dacaaacb8f35841d153dcfcde8e4df1a",
@@ -690,6 +697,10 @@
     "pipeline/scripts/run-kill.mjs": "d27c7a91a2088304483155d9967176ef1919aa73694d0c98629181854d696d9c",
     "pipeline/scripts/run-log.mjs": "aeff5b6f461dec4234904495071f3589908d0144eeff7e0f2a1b72f5f3f7f8f6",
     "pipeline/scripts/run-metrics.mjs": "6db53f3814a992c1f23beae7a54c84310be5af8e84dbff5a6768a91169152f02",
+    "pipeline/scripts/run-scope-guard.mjs": "2216c33b123ff19a80bca614d51a7f55d13e572a9278869eda100a48c83bb06d",
+    "pipeline/scripts/run-scope-guard.sh": "ddf83ac9842f6227b341762dbdd87e6b988506c866852e1c5e1345d380a9f31b",
+    "pipeline/scripts/run-stop-guard.mjs": "ea19ccc3b52f00de60c0f8b2a7faed026ba5a1028c58bba07433dc60dd1b89a9",
+    "pipeline/scripts/run-stop-guard.sh": "5c8281e283203e9314c78a26aa0026f81a6ad5afcf06dfdfd7bd9b3f55810d64",
     "pipeline/scripts/run-ui-tests.sh": "7bf3549668d3e460d23dfec859b095d6465c9977051e63b1a2c1abeecd59ed83",
     "pipeline/scripts/runs-index.mjs": "5d8b39bd739d53362f6a2725e56d65d52b38bd50aa60c55bece4dceb188c631e",
     "pipeline/scripts/scaffold-gate.mjs": "e2935957771f1d332b9968a819de49676152c51991e89f4a9cab7467b6d18701",
@@ -723,7 +734,7 @@
     "pipeline/scripts/triage-memory.mjs": "2d8541145f1749593ae5728fb4c9eb3001484edb5e4d37be473aeec34d1dbe7c",
     "pipeline/scripts/ui-tree-dumper.swift": "a09e42ef069eafa08c05afd8333e05b754ef6a7d8b9687712039b0f2c9801273",
     "pipeline/scripts/unattended_policy.py": "851f3982bf8a5d12415caf724146184c50801f9ee2e3654ba2ded593351f71af",
-    "pipeline/scripts/uninstall.mjs": "daa282b3f2aaf35a32741847940f2e944907d2956909ed0ed8f4e8ae15378911",
+    "pipeline/scripts/uninstall.mjs": "cd5d63455411dded14a1b4a1ca6ace0599208b180027331e6d538a573c156b0d",
     "pipeline/scripts/update-check.sh": "9c00647e7ca4249414b2e5af08f61705ab5bd2106b6f66ae8ebce8aa143dc957",
     "pipeline/scripts/update-issue-progress.sh": "c96de68648cb3265b041368af38fdf60dc0b7d8b9c4bf2971271e6dfb8dd4c0a",
     "pipeline/scripts/usage-identity.mjs": "ec22fbf6ec3afe694673c224f53677320f8d5151e9fef77f0804c8f1bb35cc95",
@@ -737,7 +748,7 @@
     "pipeline/scripts/validate-diff-risk.mjs": "cf53943f71a717fddaacf7426dea9d5eb4e0ec7bdb27bdfb91915176df9fee99",
     "pipeline/scripts/validate-planning.mjs": "a6da1193e1a86709de3e308c317b9b0e0b282650951c1a7aad6944d6b2cc2adc",
     "pipeline/scripts/validate-reviewer.mjs": "491fdcd01bd8692419157abfeb91da813505f099ede8cf150557f8aeaad04d86",
-    "pipeline/scripts/validate-state.mjs": "ac2cfde75fe216a7549ba476c58f777f27d36e068de3796909926d68de2fb65a",
+    "pipeline/scripts/validate-state.mjs": "d1c6a6caaf43df8357c41d12f40ebd940465d6d2a5e2ec374c776061700898b2",
     "pipeline/scripts/validate-test-gap.mjs": "14fa89867e49497adb2b88a3290e78d0f263afa74a5b83b062115fc5a22204f7",
     "pipeline/scripts/validate-triage.mjs": "7cd78686494c4dc003b4cd66817dfe583adbdab536b54da3fbb80c9fa0e1a216",
     "pipeline/scripts/valven-gate.mjs": "1bd10b59fe2e282759942c1a3961facabc4c0c36b1e603aadc9f8ef00b27b513",
@@ -750,9 +761,9 @@
     "pipeline/scripts/worktree-finalize.sh": "ca2bb363bec738cfce57ce5f46962d69664810003cc56dde0a82ab9133dbf557",
     "pipeline/scripts/worktree-prepare.sh": "9391c828375b127f77c86e3c830dbbaf355a61464c6437319969f2f1eecc72b1",
     "pipeline/scripts/worktrees.mjs": "90dfd09b70fffe9b56c331a4ae2692cc248f4898f4ee6aee4239ef0b20888a90",
-    "pipeline/scripts/write-state.mjs": "e1198bf970eace07d3eff22b394808a526e473df65d3d58aa2d5a12cfdac8b49",
+    "pipeline/scripts/write-state.mjs": "f49cb7700d837867a006caa90c17cd9e2887f0e1b676bbd8e74410ee5ba87410",
     "pipeline/scripts/write-store-config.mjs": "b994a061f6febb2ca3d396074d8b51d2c1c1f991d3072d321703380da3639a56",
-    "pipeline/skills/.skill-manifest.json": "eee94a5b60738fcd1c41838ce3a0ac5f5e07fa88edffdd8759555dad81875dad",
+    "pipeline/skills/.skill-manifest.json": "f57ff9f4e6b07e4e6621865b95b89ea3a710b53d9ec4faaa996cd5a9b0952fc5",
     "pipeline/skills/.skills-index.json": "8f15e925ca59885155d64fb42aa925c9b826a7f192288fa6822015aa3cc87d05",
     "pipeline/skills/shared/README.md": "30d382420084a9ec3fa716e84f4f9e1e980ed25e01056349e2dbb19f4ac21602",
     "pipeline/skills/shared/core/apple-archive-compliance/SKILL.md": "08d5277e4a6c246c613bd3bea27646f580f1bdc1937cb4acbbd93a156e15b24e",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "20.28.0",
+  "version": "20.29.0",
   "description": "6-phase AI development pipeline with full orchestration on Claude Code, Copilot CLI and Codex CLI. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Fable triage, default-FAIL evidence gates, secret + intent guards, per-phase cost ledger, persistent learnings memory, wiki generation, commit automation. Token-preserving uninstall.",
   "type": "module",
   "main": "index.js",