@bonesofspring/ai-rules 0.2.20 → 0.2.22

package/presets/claude/java/hooks/chain-team-phases.sh

@@ -65,10 +65,20 @@ const STACK = 'java';
 const PLATFORM = 'claude';
 
 function waitForMetricsLock() {
+  // OD-1: real advisory lock via create-exclusive (fs.openSync(_, 'wx')).
+  // The previous impl spun on Atomics.wait against an unrelated SharedArrayBuffer
+  // and never blocked on the lock file, so two concurrent subagentStop events
+  // could both acquire the lock and corrupt metrics.json. Retry EEXIST with a
+  // 10 ms sleep up to 200 attempts (2 s ceiling). On any other error, throw.
   for (let attempt = 0; attempt < 200; attempt += 1) {
-    try { fs.mkdirSync(METRICS_LOCK); return; } catch (error) {
-      if (error && error.code !== 'EEXIST') throw error;
-      Atomics.wait(new Int32Array(new SharedArrayBuffer(4)), 0, 0, 10);
+    try {
+      const fd = fs.openSync(METRICS_LOCK, 'wx');
+      try { fs.closeSync(fd); } catch {}
+      return;
+    } catch (error) {
+      if (!error || error.code !== 'EEXIST') throw error;
+      const until = Date.now() + 10;
+      while (Date.now() < until) { /* 10 ms busy-wait */ }
     }
   }
   throw new Error('metrics lock timeout');
@@ -77,7 +87,7 @@ let taskLockHeld = false;
 function releaseTaskLock() {
   if (!taskLockHeld) return;
   taskLockHeld = false;
-  try { fs.rmdirSync(METRICS_LOCK); } catch {}
+  try { fs.unlinkSync(METRICS_LOCK); } catch {}
 }
 waitForMetricsLock();
 taskLockHeld = true;
@@ -105,7 +115,7 @@ function mutateMetrics(mutator) {
     fs.writeFileSync(temporary, JSON.stringify(metrics, null, 2) + '\n');
     fs.renameSync(temporary, METRICS_PATH);
   } finally {
-    if (acquiredHere) { try { fs.rmdirSync(METRICS_LOCK); } catch {} }
+    if (acquiredHere) { try { fs.unlinkSync(METRICS_LOCK); } catch {} }
   }
 }
 function appendMetric(event) { mutateMetrics((metrics) => metrics.events.push({ eventId: `${metrics.task.runId}:${Date.now()}:${Math.random().toString(16).slice(2)}`, ...event })); }
@@ -134,10 +144,17 @@ const DEFAULT_ARTIFACT_OUTPUT_IDS = {
   'build-verifier': 'validation',
   'code-reviewer': 'review',
   'security-reviewer': 'security-review',
-  'accessibility-reviewer': 'a11y-review',
   'performance-auditor': 'perf-report',
   'api-contract-reviewer': 'api-contract-review',
   'tech-writer': 'documentation',
+  'openspec-author': 'openspec-change',
+  'qa-tester': 'qa',
+  'unit-test-planner': 'unit-test-plan',
+  'unit-test-generator': 'unit-test-spec',
+  'unit-test-healer': 'unit-test-heal',
+  'integration-test-planner': 'integration-test-plan',
+  'integration-test-generator': 'integration-test-spec',
+  'integration-test-healer': 'integration-test-heal',
 };
 function artifactOutputIdFor(step, agent) {
   if (step && typeof step.artifactOutputId === 'string') return step.artifactOutputId;
@@ -242,7 +259,17 @@ function recordSkippedStep(step, stepIndex) {
 function writeStatus(next) {
   status = { ...status, ...next, slug, updatedAt: now };
   const temporary = `${statusPath}.${process.pid}.${Date.now()}.tmp`;
-  fs.writeFileSync(temporary, JSON.stringify(status, null, 2) + '\n');
+  // Open + write + fsync + rename so the durable file lands on disk before
+  // the orchestrator reads it. Closes the race window where a subagent that
+  // completed milliseconds before writeStatus() could otherwise invoke the
+  // next step on a stale status (in particular the human-gate write).
+  const fd = fs.openSync(temporary, 'w');
+  try {
+    fs.writeSync(fd, JSON.stringify(status, null, 2) + '\n');
+    try { fs.fsyncSync(fd); } catch {}
+  } finally {
+    fs.closeSync(fd);
+  }
   fs.renameSync(temporary, statusPath);
 }
 
@@ -337,6 +364,12 @@ const AGENT_HANDOFF = {
     `Follow tests-integration.mdc, integration-testing, and debug-investigation. Do not use browser e2e tooling. Upsert the owned terminal receipt in artifact-manifest.json; do not mutate status.json lifecycle fields.`,
   'tech-writer': (s) =>
     `Invoke tech-writer for slug "${s}". Write documentation.md from task artifacts. Upsert the owned terminal receipt in artifact-manifest.json; do not mutate status.json lifecycle fields.`,
+  'openspec-author': (s, scope) =>
+    `Invoke openspec-author for slug "${s}"${scope ? ` (scope: ${scope})` : ''}. ` +
+    `Read openspec/config.yaml schema + rules; if openspec/** is absent, emit blocked ("openspec/** not initialized"). ` +
+    `Author openspec/changes/<change-id>/{proposal.md, design.md, tasks.md, .openspec.yaml} and the capability spec delta per phase (explore|propose|apply|archive). ` +
+    `Run \`openspec validate <change-id> --type change --strict\` and \`openspec validate --specs --strict\` (Phase 3); surface FAIL output verbatim. ` +
+    `Upsert the owned terminal receipt (artifactOutputId \`openspec-change\`) in artifact-manifest.json with validator exit code + evidence paths; do not mutate status.json lifecycle fields. `,
 };
 
 const REVIEW_AGENTS = new Set([
@@ -457,7 +490,19 @@ function legacyFlow() {
 
 
 if (hookInput.action === 'end_human_gate') {
-  status.awaitingHumanGate = false;
+    status.awaitingHumanGate = false;
+  // A2 (retro §8): pin a single runId per pipeline so subsequent events don't
+  // fragment the metrics ledger across multiple runId sequences. Prefer
+  // metrics.json.task.runId when metrics already exist, then status.metricsRunId,
+  // then mint a fresh seed only on first ever emit.
+  try {
+    if (fs.existsSync(METRICS_PATH)) {
+      const existing = JSON.parse(fs.readFileSync(METRICS_PATH, 'utf8'));
+      if (existing && existing.task && typeof existing.task.runId === 'string') {
+        status.metricsRunId = existing.task.runId;
+      }
+    }
+  } catch {}
   if (status.state === 'awaiting_approval') {
     status.state = 'in_progress';
     status.phase = status.phase === 'human_gate' ? 'executing' : status.phase;
@@ -496,11 +541,29 @@ if (hookInput.action === 'end_human_gate') {
       }
     }
   }
-  writeStatus({
-    awaitingHumanGate: false,
-    state: status.state,
-    phase: status.phase,
-  });
+  // A2 (retro §8): if gate closes the final human gate of the pipeline
+  // (no resume happens, or current step's gate was the last), surface
+  // state="awaiting_approval" so a subsequent /task-continue doesn't misinterpret
+  // the post-gate idle state as "still in progress".
+  {
+    let gateWasTerminal = false;
+    if (!hookInput.activateNext && fs.existsSync(pipelinePath)) {
+      try {
+        const pipe = JSON.parse(fs.readFileSync(pipelinePath, 'utf8'));
+        const steps = pipe.steps || [];
+        const idx = typeof status.pipelineIndex === 'number' ? status.pipelineIndex : 0;
+        const cur = steps[idx];
+        const gates = Array.isArray(pipe.humanGates) ? pipe.humanGates : [];
+        const hasGate = (step) => Array.isArray(gates) && gates.some((g) => typeof g === 'string' && getStepAgents(step).some((a) => g === `after:${a}`));
+        if (cur && hasGate(cur)) gateWasTerminal = true;
+      } catch {}
+    }
+    writeStatus({
+      awaitingHumanGate: false,
+      state: gateWasTerminal ? 'awaiting_approval' : status.state,
+      phase: status.phase,
+    });
+  }
   process.stdout.write(JSON.stringify({ ok: true, action: 'end_human_gate', activeHumanGateEventId: status.activeHumanGateEventId || null }));
   process.exit(0);
 }
@@ -510,9 +573,37 @@ if (!fs.existsSync(pipelinePath)) {
 }
 
 let pipeline;
+let pipelineParseError = null;
 try {
   pipeline = JSON.parse(fs.readFileSync(pipelinePath, 'utf8'));
-} catch {
+} catch (error) {
+  pipelineParseError = error;
+}
+// Modern pipelines carry an `intent` field. If pipeline.json is present but
+// unparseable, surface the error so the orchestrator can stop and report
+// instead of falling back to legacyFlow() — which silently drops modern
+// roles like `openspec-author`, `qa-tester`, and the test-planner trio.
+if (pipelineParseError) {
+  if (fs.existsSync(pipelinePath)) {
+    const raw = fs.readFileSync(pipelinePath, 'utf8');
+    const hasModernIntent = /"intent"\s*:/.test(raw);
+    appendMetric({
+      eventId: `${status.metricsRunId || slug}:pipeline_parse_error:${Date.now()}`,
+      type: 'pipeline_parse_error',
+      at: now,
+      source: 'hook',
+      attributionConfidence: 'high',
+      error: String(pipelineParseError.message || pipelineParseError),
+      hasModernIntent,
+    });
+    if (hasModernIntent) {
+      writeStatus({ state: 'blocked', phase: 'blocked', currentAgent: 'task-router' });
+      process.stdout.write(JSON.stringify({
+        followup_message: `pipeline.json is malformed for slug "${slug}" — JSON parse error: ${pipelineParseError.message}. Re-run the task-router to regenerate pipeline.json, then resume via /task-continue ${slug}.`,
+      }));
+      process.exit(0);
+    }
+  }
   legacyFlow();
 }
 

package/presets/claude/java/rules/README.md

@@ -30,6 +30,7 @@ Claude topic `.md` files are **derived** from Cursor SoT `presets/cursor/java/ru
 | `architecture-boundaries.mdc` | `architecture/boundaries.md` |
 | `anti-sycophancy-discipline.mdc` | `tooling-and-review/anti-sycophancy-discipline.md` |
 | `code-quality-and-refactoring.mdc` | `tooling-and-review/code-quality.md` |
+| `ai-local-overlay.mdc` | `tooling-and-review/ai-local-overlay.md` |
 | `design-guidance.mdc` | `tooling-and-review/design-guidance.md` |
 | `mcp-usage.mdc` | `tooling-and-review/mcp-usage.md` |
 | `code-review-mr.mdc` | `tooling-and-review/code-review.md` |

package/presets/claude/java/rules/tooling-and-review/agent-team-orchestrator.md

@@ -23,8 +23,6 @@ Work request without `/task` — see **agent-team-intake** (when to suggest the
 |---------|------|
 | **`/task <desc>`** | **Preferred** — router → dynamic pipeline → first agent |
 | `/task-continue <slug>` | After human gate or pause |
-| `/feature-start <desc>` | Legacy: analyst-only start (no router) |
-| `/feature-continue <slug>` | Alias of task-continue |
 | `/spec-start [desc]` | Generate/bootstrap `docs/specs` — router intent `spec-gen` → analyst author mode → human gate |
 | `/technical-retro [slug]` | Retro with agent team block |
 
@@ -163,7 +161,7 @@ After each agent completes, verify its terminal manifest receipt, then let the o
 
 ## Legacy mode
 
-If `pipeline.json` is missing (old `/feature-start` tasks), fall back to fixed phases: analysis → development → review → testing. Hook supports both.
+If `pipeline.json` is missing, fall back to fixed phases: analysis → development → review → testing. Hook supports both.
 
 ## Skip pipeline when
 
@@ -208,4 +206,4 @@ When the work edits `packages/ai-rules/presets/**` (or dogfood `.cursor/` sync o
 - Chain hook handoffs: `integration-test-*`, `post-change-test`, `java-tooling` — never `lint:js`, Playwright, XCUITest, or `xcodebuild`.
 - Skills: `feature-delivery`, `unit-testing`, `integration-testing`, `ci-investigation`, `debug-investigation`, `code-review`, `technical-retro`, `write-adr`.
 
-**Product specs:** When `/task`, `/feature-start`, or `/spec-start` touches pages/features/`docs/specs`: if INDEX exists and no generate intent → instruct next agent to load requestable **`product-specs`** (consume; soft-fail; never invent). If generate/bootstrap/`spec-gen` → load **`product-specs-authoring`** + skill **`spec-authoring`** inside **task-analyst** (not a separate pipeline step); pass created spec paths + INDEX diff in handoff; human gate must approve before feature-developer. No-op if INDEX absent and no author intent.
+**Product specs:** When `/task` or `/spec-start` touches pages/features/`docs/specs`: if INDEX exists and no generate intent → instruct next agent to load requestable **`product-specs`** (consume; soft-fail; never invent). If generate/bootstrap/`spec-gen` → load **`product-specs-authoring`** + skill **`spec-authoring`** inside **task-analyst** (not a separate pipeline step); pass created spec paths + INDEX diff in handoff; human gate must approve before feature-developer. No-op if INDEX absent and no author intent.

package/presets/claude/java/rules/tooling-and-review/ai-local-overlay.md

@@ -0,0 +1,48 @@
+---
+description: Local overlay from .ai.local/ (consumer-owned rules with priority over preset rules) — MANDATORY
+paths:
+  - "**/.ai.local/**"
+  - "**/AGENTS.md"
+  - "**/CLAUDE.md"
+alwaysApply: false
+impact: CRITICAL
+---
+
+# Local overlay (`.ai.local/`) — MANDATORY
+
+This rule is mandatory. **You MUST** obey it on every turn, without exception.
+
+## On every turn
+
+1. **Probe** — before answering, run `ls -la .ai.local` from the repository root.
+2. **Walk** — if `.ai.local/` exists at multiple levels (monorepo), read every level from root to leaf. **Deeper wins** in practice: more specific rules appear later in the assembled context and take precedence.
+3. **Apply** — treat every `.ai.local/rules/*.md` and `.ai.local/conventions.md` as a higher-priority rule for this repo. The block below ("Authoring `.ai.local/rules/*.md`") defines the conventions.
+4. **Conflict** — if a local rule conflicts with a preset rule, **the local rule wins**. If a local rule body contains `override: kill <preset-rule-name>`, drop that preset rule from your context window entirely.
+5. **Acknowledge** — when answering a user question, briefly state which `.ai.local/` rules apply to the current task (one line is enough). Format: `Using .ai.local: <rule-name>(, <rule-name>)*`. If no `.ai.local/` exists, do NOT mention this rule.
+
+If `.ai.local/` does not exist → **no-op**, do not error. Do not produce any log line about its absence.
+
+## Authoring `.ai.local/rules/*.md` (consumer-side reference)
+
+Each `.ai.local/rules/<name>.md` is a plain-markdown rule body. The model parses it as:
+
+- Lines before `## Body` are scope metadata. Only `glob:` / `globs:` / `override:` lines are recognised.
+- Everything from `## Body` onward is the rule body.
+- `glob: always` → always-on. Counts against your context budget.
+- `globs: <comma-separated globs>` → on-demand; applies only when matching files are in focus.
+- `override: kill <preset-rule-name>` → drop that preset rule from context.
+
+Keep files ≤ 120 lines. Match the style of preset rules (short sections, bullets, code examples).
+
+## Limitations (read this)
+
+- Cursor/Claude do **not** natively read `.ai.local/`. This rule is a **prompt-only** mechanism: it asks you, the model, to read and apply the files. Reliability is high but not 100%.
+- If a user adds a file to `.ai.local/` mid-session, **restart the session** to be sure it is picked up.
+- "Priority" is **contextual**, not enforced. Always re-read the local rule before answering questions that touch it.
+- This rule is **not** session-start (Claude convention); it loads on touch of `.ai.local/**` or `AGENTS.md`/`CLAUDE.md`. The "every turn" mandate is enforced by the body text, not by Cursor/Claude loading semantics.
+
+## Pointers
+
+- Authoring guide: `docs/LOCAL-OVERLAY.md` in the `@bonesofspring/ai-rules` package.
+- Living gotchas alternative: `.claude/team/conventions.md`.
+- Root `AGENTS.md` reinforces this rule with a `MANDATORY` section.

package/presets/claude/java/rules/tooling-and-review/preset-pr-checklist.md

@@ -19,11 +19,15 @@ Checklist for PRs that touch `packages/ai-rules/presets/**` (and dogfood `.curso
 - [ ] **Core:** if `_shared/core/**` changed — all `<!-- shared-core: … -->` consumers updated (or documented intentional fork)
 - [ ] **Twin:** Cursor change → Claude twin **same PR** (**FAIL** if missing on next, nuxt, svelte, ios-swift, android-kotlin, go, java, mcp-ts, php-hexagonal, and php-laravel — see `preset-twin-sync`)
 - [ ] **Mapping:** `claude/<stack>/rules/README.md` mapping table is current
-- [ ] **Token budget:** alwaysApply / session-start ≤ 3; meta rules not always-on
+- [ ] **Token budget:** Cursor `alwaysApply` ≤ 4 (4th slot reserved for `ai-local-overlay`); Claude session-start exactly 3; meta rules not always-on
+- [ ] **Local overlay coverage:** every installable stack ships `ai-local-overlay.mdc` (Cursor) and `ai-local-overlay.md` (Claude) with `MANDATORY` + acknowledgement format + `docs/LOCAL-OVERLAY.md` pointer; Claude twin listed in `claude/<stack>/rules/README.md` mapping table. Run `packages/ai-rules/scripts/check-local-overlay.sh`.
 - [ ] **Leakage:** no foreign stack agent stems / handoff strings (`preset-no-cross-stack-leakage`)
+- [ ] **Hook-only lifecycle:** `status.json` / `metrics.json` writes happen only inside `hooks/`; agents read but never rewrite lifecycle fields. Run `packages/ai-rules/scripts/check-hook-only-lifecycle.sh`.
+- [ ] **Chain fork:** the byte-wise MD5 uniqueness of `chain-team-phases.sh` across the 10 stacks × 2 platforms (20 hooks) holds. Run `packages/ai-rules/scripts/check-chain-hook-coverage.sh` and `packages/ai-rules/scripts/test-chain-team-phases-coverage.mjs`.
 - [ ] **Twin depth:** domain ≥15 lines; thin aliases documented
 - [ ] **README:** stack `rules/README.md` core→stack mapping / catalog updated if stems added
 - [ ] **CHANGELOG / package README:** note when public preset paths or install surface change
+- [ ] **i18n anchors:** kept-marked Cyrillic fragments in `tests-unit.md(c)` stay consistent with their English counterparts. Run `packages/ai-rules/scripts/check-preset-i18n.sh`.
 - [ ] **Dogfood:** run `packages/ai-rules/scripts/sync-dogfood-cursor.sh` (or document intentional skip) when maintaining this monorepo
 - [ ] **shared-core drift:** for embed-mode stems, run `packages/ai-rules/scripts/check-shared-core-drift.sh` (or document intentional fork)
 

package/presets/claude/java/rules/tooling-and-review/preset-token-budget.md

@@ -17,12 +17,16 @@ Invariants for rule loading in an **installed** preset (consumer app).
 
 | Platform | Always-on | Cap |
 |----------|-----------|-----|
-| Cursor | `alwaysApply: true` | **≤ 3** |
+| Cursor | `alwaysApply: true` | **≤ 4** |
 | Claude | rules **without** `paths:` | **exactly 3** |
 
+**Cursor 4th slot is reserved for `ai-local-overlay`** (consumer-owned `.ai.local/` rules). If you do not need local overlay, demote that rule to `globs: ["**/.ai.local/**"]` and revert to ≤3.
+
 **Claude Option A (README exclusion):** when counting Claude rules without `paths:` / session-start, **exclude `**/README.md`** (topic indexes are not session-start rules). The intended session-start trio remains **exactly 3**; body budget sums **only those 3** rules.
 
-Session-start body budget (where documented): ≤140 lines total (stretch ≤120).
+Session-start body budget:
+- Claude trio: ≤140 lines total (stretch ≤120).
+- Cursor 4-set: ≤170 lines total (4 rules including `ai-local-overlay`).
 
 ## Meta / author rules
 
@@ -38,4 +42,4 @@ Orchestrator, feature-delivery, code-review, post-change gates, domain globs —
 
 ## Verifier
 
-build-verifier **FAIL** if alwaysApply / session-start count exceeds 3 (Claude count **excludes `**/README.md`**), or if a `preset-*` meta rule is marked always-on.
+build-verifier **FAIL** if Cursor `alwaysApply` count exceeds 4, Claude session-start count exceeds 3 (Claude count **excludes `**/README.md`**), or if a `preset-*` meta rule is marked always-on.

package/presets/claude/java/rules/tooling-and-review/preset-twin-sync.md

@@ -39,6 +39,8 @@ Cursor `.mdc` — **SoT per stack**. Claude topic `.md` — derived twin.
 
 - **Domain** rules: ≥15 body lines (FAIL if thin without documented alias reason).
 - **Thin aliases** (`agent-team-intake`, `technical-retro`): may be shorter (soft) if they only point to a command/skill.
+- **Slim-companion rules** (UI-edit bundle, slim app-cores, slim tooling): may be shorter than 15 lines **if and only if** the body is a pointer into shared-core / stack-prose (no standalone prose). Examples live in stack `rules/README.md` (e.g. `cursor/next/rules/README.md` "UI-edit bundle" intent).
+  - Mechanical enforcement lives in `packages/ai-rules/scripts/check-preset-token-budget.sh` — see `SLIM_COMPANION_ALLOWLIST` (the 53 stems accepted as slim pointers) and `MIN_SLIM_BODY_LINES` (5-line floor). Slim-companion rules with a body of 6–14 lines whose stem is **not** in the allowlist are reported as slim violations by the script.
 
 ## Severity (build-verifier)
 

package/presets/claude/mcp-ts/agents/build-verifier.md

@@ -59,3 +59,7 @@ Document PASS/FAIL in `validation-report.md`. Soft leakage output:
 
 13. **Product-specs assets (FAIL):** package must ship `presets/_shared/assets/docs-specs/INDEX.md`, `_templates/page.md`, `_templates/feature.md`. Cursor+Claude twins for `product-specs` and `product-specs-authoring` must embed matching shared-core markers; both stems **requestable** (`alwaysApply: false` / Claude `paths: docs/specs/**`) — never session-start.
 14. **Optional consumer check (WARN default):** `scripts/check-product-specs.sh` + schema stub may exist for opt-in consumer CI; **FAIL** only with `--strict` or AC that requires named specs — do not force consumer CI.
+
+## Receipt binding
+
+> **Receipt binding.** When writing the terminal receipt to `artifact-manifest.json`, set `entry.receipt.attemptId = <attemptId supplied by the orchestrator>` (the orchestrator provides this via `attemptId` on invocation). The hook at `chain-team-phases.sh:readBoundReceiptOutcome` rejects entries whose `attemptId` does not match the current attempt, or whose `Date.parse(timestamps.completedAt) < Date.parse(attemptStartedAt)`. A missing or stale attemptId causes `awaiting_artifact_receipt` stalls. <!-- shared-core: receipt-binding -->

package/presets/claude/mcp-ts/agents/feature-developer.md

@@ -19,6 +19,7 @@ Implement MCP server features following **mcp-ts** boundaries.
 
 1. Read `feature-delivery-workflow.mdc`, `mcp-server-boundaries.mdc`, `reference-features.mdc`.
 2. After `*.ts` edits: invoke `post-change-test.mdc` (+ `mcp-ts-tooling.mdc`).
+3. **Verify carry-over at HEAD before applying** (refactor intent only). When the brief comes from a prior review's carry-over findings list, for each item run `git show HEAD:<path>` or `grep` to confirm the finding still applies at the current HEAD; if the file already contains the fix, mark it as **NO-OP at HEAD** in `implementation.md` and skip the edit; if the file is unchanged, apply the fix and cite file:line. Target ≤2 NO-OP items per refactor pipeline.
 
 ## Do / Don't
 
@@ -88,3 +89,7 @@ Load requestable rule `mcp-usage` when verifying third-party library APIs (Conte
 - **Owned outputs:** `implementation.md` plus changed implementation/test paths; upsert only the manifest entry assigned by handoff (`artifactOutputId`; fallback `implementation`) and preserve all foreign entries.
 - **Terminal receipt:** cover applicable AC/task IDs, list authoritative evidence paths, and emit `completed` or `blocked`. Bind it to the supplied `attemptId` when present.
 - **Shared state:** never create or mutate `status.json` or `metrics.json`; the orchestration runtime/hook owns lifecycle, gates, retries, attempts, and timestamps.
+
+## Receipt binding
+
+> **Receipt binding.** When writing the terminal receipt to `artifact-manifest.json`, set `entry.receipt.attemptId = <attemptId supplied by the orchestrator>` (the orchestrator provides this via `attemptId` on invocation). The hook at `chain-team-phases.sh:readBoundReceiptOutcome` rejects entries whose `attemptId` does not match the current attempt, or whose `Date.parse(timestamps.completedAt) < Date.parse(attemptStartedAt)`. A missing or stale attemptId causes `awaiting_artifact_receipt` stalls. <!-- shared-core: receipt-binding -->

package/presets/claude/mcp-ts/agents/task-analyst.md

@@ -1,6 +1,6 @@
 ---
 name: task-analyst
-description: Task analysis specialist. Clarifies requirements, validates acceptance criteria, and decomposes work into concrete tasks. Use for /feature-start, task intake, or when the user asks to analyze or decompose a feature before coding. Writes only team artifacts; never writes production code.
+description: Task analysis specialist. Clarifies requirements, validates acceptance criteria, and decomposes work into concrete tasks. Use for task intake, or when the user asks to analyze or decompose a feature before coding. Writes only team artifacts; never writes production code.
 readonly: false
 ---
 

package/presets/claude/mcp-ts/agents/task-router.md

@@ -19,7 +19,7 @@ You are a task router for a **TypeScript MCP server** agent team. You **do not**
 |--------|---------|---------------|
 | `feature` | "add tool", "new", "implement", schema/handler | task-analyst → feature-developer → build-verifier → **security-reviewer** when [sensitive](#security-reviewer-routing); else document skip |
 | `bugfix` | "bug", "fix", "doesn't work", "crashes" | task-analyst → feature-developer → build-verifier → **security-reviewer** when [sensitive](#security-reviewer-routing); else document skip |
-| `review-only` | "review", "review MR", "check diff" | `security-reviewer` for threat/capability/auth/secrets diffs; **plus** parent applies skill `code-review` (write `review.md`) — no `code-reviewer` agent in Phase 1. Pure schema/style-only diffs: skip security step, parent skill only (document in `skipped`) |
+| `review-only` | "review", "review MR", "check diff" | `security-reviewer` for threat/capability/auth/secrets diffs; **plus** parent applies skill `code-review` (write `review.md`) — no dedicated agent in Phase 1. Pure schema/style-only diffs: skip security step, parent skill only (document in `skipped`) |
 | `spike` | "investigate", "spike", proof of concept | task-analyst → solution-architect |
 | `refactor` | "refactor", "no behavior change" | task-analyst → feature-developer → build-verifier → **security-reviewer** when [sensitive](#security-reviewer-routing); else document skip |
 | `retro` | "retro", "postmortem" | (orchestrator → `/technical-retro`) |

package/presets/claude/mcp-ts/commands/README.md

@@ -6,6 +6,4 @@ Slash commands are copied to `.cursor/commands/` (Cursor) or `.claude/commands/`
 |---------|---------|
 | `/task` | Router + pipeline entry |
 | `/task-continue` | Resume after human gate |
-| `/feature-start` | Legacy analyst-only start |
-| `/feature-continue` | Alias of task-continue |
 | `/technical-retro` | Retro |

package/presets/claude/mcp-ts/commands/task-continue.md

@@ -5,7 +5,7 @@ description: Continue an agent-team task after a human gate, pause, or review ch
 
 # Task continue — after human gate or pause
 
-Resume the pipeline from `pipeline.json`. Semantic alias: `/feature-continue`.
+Resume the pipeline from `pipeline.json`.
 
 ## Arguments
 

package/presets/claude/mcp-ts/commands/task.md

@@ -33,7 +33,7 @@ Examples:
    - **do not** write lifecycle fields in `status.json` / `metrics.json` yourself — orchestration runtime/hook owns them (see **agent-artifact-contracts**). If `status.json` is missing, only minimal bootstrap is allowed (`slug`, `intent`, `pipelineIndex: 0`, `currentAgent: steps[0]`, `state: in_progress`) — **do not** increment `pipelineIndex` manually;
    - invoke subagent for `pipeline.steps[0].agent` (slug, artifact paths, scope).
 6. **After each agent** — wait for hook handoff / reconciliation terminal receipt → `status.state`; do not start the next step until `status.json` reflects handoff (or until hook returns `followup_message`).
-7. **Human gate** — if there is a gate in `humanGates` after the current step (`after:<agent>`), **stop** after the agent finishes and ask for `/task-continue <slug>` (or `/feature-continue <slug>`).
+7. **Human gate** — if there is a gate in `humanGates` after the current step (`after:<agent>`), **stop** after the agent finishes and ask for `/task-continue <slug>`.
 
 ## Do not
 
@@ -46,9 +46,6 @@ Examples:
 - `awaitingHumanGate` / `state: awaiting_approval` → offer artifact review or `/task-continue <slug>`.
 - `in_progress` → ask: continue or new slug.
 
-## Legacy
-
-`/feature-start` and `/feature-continue` remain compatible; for new tasks prefer `/task`.
 
 ## Metrics
 

package/presets/claude/mcp-ts/commands/technical-retro.md

@@ -10,7 +10,7 @@ The agent acts as a **neutral facilitator of a technical retrospective**, not as
 ## When to use
 
 - User asks: "retro", "technical retro", "sprint/iteration review", "action items after release".
-- After completing the agent-team pipeline (`/feature-start` → `/feature-continue`).
+- After completing the agent-team pipeline.
 - Context available: period, topic (release, incident), task slug, notes.
 
 ## Inputs (gather; do not invent)
@@ -53,7 +53,7 @@ Do not attribute facts not present in artifacts, diff, or the user's message.
 
 ## "Agent work" block (required when slug present)
 
-If retro is tied to a `/feature-start` pipeline:
+If retro is tied to an agent-team pipeline:
 
 | Question | What to capture |
 |----------|-----------------|

package/presets/claude/mcp-ts/hooks/chain-team-phases.sh

@@ -66,10 +66,20 @@ const STACK = 'mcp-ts';
 const PLATFORM = 'claude';
 
 function waitForMetricsLock() {
+  // OD-1: real advisory lock via create-exclusive (fs.openSync(_, 'wx')).
+  // The previous impl spun on Atomics.wait against an unrelated SharedArrayBuffer
+  // and never blocked on the lock file, so two concurrent subagentStop events
+  // could both acquire the lock and corrupt metrics.json. Retry EEXIST with a
+  // 10 ms sleep up to 200 attempts (2 s ceiling). On any other error, throw.
   for (let attempt = 0; attempt < 200; attempt += 1) {
-    try { fs.mkdirSync(METRICS_LOCK); return; } catch (error) {
-      if (error && error.code !== 'EEXIST') throw error;
-      Atomics.wait(new Int32Array(new SharedArrayBuffer(4)), 0, 0, 10);
+    try {
+      const fd = fs.openSync(METRICS_LOCK, 'wx');
+      try { fs.closeSync(fd); } catch {}
+      return;
+    } catch (error) {
+      if (!error || error.code !== 'EEXIST') throw error;
+      const until = Date.now() + 10;
+      while (Date.now() < until) { /* 10 ms busy-wait */ }
     }
   }
   throw new Error('metrics lock timeout');
@@ -78,7 +88,7 @@ let taskLockHeld = false;
 function releaseTaskLock() {
   if (!taskLockHeld) return;
   taskLockHeld = false;
-  try { fs.rmdirSync(METRICS_LOCK); } catch {}
+  try { fs.unlinkSync(METRICS_LOCK); } catch {}
 }
 waitForMetricsLock();
 taskLockHeld = true;
@@ -106,7 +116,7 @@ function mutateMetrics(mutator) {
     fs.writeFileSync(temporary, JSON.stringify(metrics, null, 2) + '\n');
     fs.renameSync(temporary, METRICS_PATH);
   } finally {
-    if (acquiredHere) { try { fs.rmdirSync(METRICS_LOCK); } catch {} }
+    if (acquiredHere) { try { fs.unlinkSync(METRICS_LOCK); } catch {} }
   }
 }
 function appendMetric(event) { mutateMetrics((metrics) => metrics.events.push({ eventId: `${metrics.task.runId}:${Date.now()}:${Math.random().toString(16).slice(2)}`, ...event })); }
@@ -128,17 +138,10 @@ const DEFAULT_ARTIFACT_OUTPUT_IDS = {
   'task-router': 'routing',
   'task-analyst': 'analysis',
   'solution-architect': 'architecture',
-  'migration-specialist': 'migration-plan',
   debugger: 'debug',
-  'ci-investigator': 'ci',
   'feature-developer': 'implementation',
   'build-verifier': 'validation',
-  'code-reviewer': 'review',
   'security-reviewer': 'security-review',
-  'accessibility-reviewer': 'a11y-review',
-  'performance-auditor': 'perf-report',
-  'api-contract-reviewer': 'api-contract-review',
-  'tech-writer': 'documentation',
 };
 function artifactOutputIdFor(step, agent) {
   if (step && typeof step.artifactOutputId === 'string') return step.artifactOutputId;
@@ -243,7 +246,17 @@ function recordSkippedStep(step, stepIndex) {
 function writeStatus(next) {
   status = { ...status, ...next, slug, updatedAt: now };
   const temporary = `${statusPath}.${process.pid}.${Date.now()}.tmp`;
-  fs.writeFileSync(temporary, JSON.stringify(status, null, 2) + '\n');
+  // Open + write + fsync + rename so the durable file lands on disk before
+  // the orchestrator reads it. Closes the race window where a subagent that
+  // completed milliseconds before writeStatus() could otherwise invoke the
+  // next step on a stale status (in particular the human-gate write).
+  const fd = fs.openSync(temporary, 'w');
+  try {
+    fs.writeSync(fd, JSON.stringify(status, null, 2) + '\n');
+    try { fs.fsyncSync(fd); } catch {}
+  } finally {
+    fs.closeSync(fd);
+  }
   fs.renameSync(temporary, statusPath);
 }
 
@@ -422,7 +435,19 @@ function legacyFlow() {
 
 
 if (hookInput.action === 'end_human_gate') {
-  status.awaitingHumanGate = false;
+    status.awaitingHumanGate = false;
+  // A2 (retro §8): pin a single runId per pipeline so subsequent events don't
+  // fragment the metrics ledger across multiple runId sequences. Prefer
+  // metrics.json.task.runId when metrics already exist, then status.metricsRunId,
+  // then mint a fresh seed only on first ever emit.
+  try {
+    if (fs.existsSync(METRICS_PATH)) {
+      const existing = JSON.parse(fs.readFileSync(METRICS_PATH, 'utf8'));
+      if (existing && existing.task && typeof existing.task.runId === 'string') {
+        status.metricsRunId = existing.task.runId;
+      }
+    }
+  } catch {}
   if (status.state === 'awaiting_approval') {
     status.state = 'in_progress';
     status.phase = status.phase === 'human_gate' ? 'executing' : status.phase;
@@ -461,11 +486,29 @@ if (hookInput.action === 'end_human_gate') {
       }
     }
   }
-  writeStatus({
-    awaitingHumanGate: false,
-    state: status.state,
-    phase: status.phase,
-  });
+  // A2 (retro §8): if gate closes the final human gate of the pipeline
+  // (no resume happens, or current step's gate was the last), surface
+  // state="awaiting_approval" so a subsequent /task-continue doesn't misinterpret
+  // the post-gate idle state as "still in progress".
+  {
+    let gateWasTerminal = false;
+    if (!hookInput.activateNext && fs.existsSync(pipelinePath)) {
+      try {
+        const pipe = JSON.parse(fs.readFileSync(pipelinePath, 'utf8'));
+        const steps = pipe.steps || [];
+        const idx = typeof status.pipelineIndex === 'number' ? status.pipelineIndex : 0;
+        const cur = steps[idx];
+        const gates = Array.isArray(pipe.humanGates) ? pipe.humanGates : [];
+        const hasGate = (step) => Array.isArray(gates) && gates.some((g) => typeof g === 'string' && getStepAgents(step).some((a) => g === `after:${a}`));
+        if (cur && hasGate(cur)) gateWasTerminal = true;
+      } catch {}
+    }
+    writeStatus({
+      awaitingHumanGate: false,
+      state: gateWasTerminal ? 'awaiting_approval' : status.state,
+      phase: status.phase,
+    });
+  }
   process.stdout.write(JSON.stringify({ ok: true, action: 'end_human_gate', activeHumanGateEventId: status.activeHumanGateEventId || null }));
   process.exit(0);
 }
@@ -475,9 +518,37 @@ if (!fs.existsSync(pipelinePath)) {
 }
 
 let pipeline;
+let pipelineParseError = null;
 try {
   pipeline = JSON.parse(fs.readFileSync(pipelinePath, 'utf8'));
-} catch {
+} catch (error) {
+  pipelineParseError = error;
+}
+// Modern pipelines carry an `intent` field. If pipeline.json is present but
+// unparseable, surface the error so the orchestrator can stop and report
+// instead of falling back to legacyFlow() — which silently drops modern
+// roles like `openspec-author`, `qa-tester`, and the test-planner trio.
+if (pipelineParseError) {
+  if (fs.existsSync(pipelinePath)) {
+    const raw = fs.readFileSync(pipelinePath, 'utf8');
+    const hasModernIntent = /"intent"\s*:/.test(raw);
+    appendMetric({
+      eventId: `${status.metricsRunId || slug}:pipeline_parse_error:${Date.now()}`,
+      type: 'pipeline_parse_error',
+      at: now,
+      source: 'hook',
+      attributionConfidence: 'high',
+      error: String(pipelineParseError.message || pipelineParseError),
+      hasModernIntent,
+    });
+    if (hasModernIntent) {
+      writeStatus({ state: 'blocked', phase: 'blocked', currentAgent: 'task-router' });
+      process.stdout.write(JSON.stringify({
+        followup_message: `pipeline.json is malformed for slug "${slug}" — JSON parse error: ${pipelineParseError.message}. Re-run the task-router to regenerate pipeline.json, then resume via /task-continue ${slug}.`,
+      }));
+      process.exit(0);
+    }
+  }
   legacyFlow();
 }
 

package/presets/claude/mcp-ts/rules/README.md

@@ -24,6 +24,7 @@ Claude topic `.md` files are **derived** from Cursor SoT `presets/cursor/mcp-ts/
 | `agent-team-orchestrator.mdc` | `tooling-and-review/agent-team-orchestrator.md` |
 | `anti-sycophancy-discipline.mdc` | `tooling-and-review/anti-sycophancy-discipline.md` |
 | `code-quality-and-refactoring.mdc` | `tooling-and-review/code-quality.md` |
+| `ai-local-overlay.mdc` | `tooling-and-review/ai-local-overlay.md` |
 | `code-review-mr.mdc` | `tooling-and-review/code-review.md` |
 | `design-guidance.mdc` | `tooling-and-review/design-guidance.md` |
 | `mcp-usage.mdc` | `tooling-and-review/mcp-usage.md` |

package/presets/claude/mcp-ts/rules/tooling-and-review/agent-team-orchestrator.md

@@ -19,8 +19,6 @@ Work request without `/task` — see **agent-team-intake** (when to suggest the
 |---------|------|
 | **`/task <desc>`** | **Preferred** — router → dynamic pipeline → first agent |
 | `/task-continue <slug>` | After human gate or pause |
-| `/feature-start <desc>` | Legacy: analyst-only start (no router) |
-| `/feature-continue <slug>` | Alias of task-continue |
 | `/spec-start [desc]` | Generate/bootstrap `docs/specs` — router intent `spec-gen` → analyst author mode → human gate |
 | `/technical-retro [slug]` | Retro with agent team block |
 
@@ -159,7 +157,7 @@ After each agent completes, verify its terminal manifest receipt, then let the o
 
 ## Legacy mode
 
-If `pipeline.json` is missing (old `/feature-start` tasks), fall back to fixed phases: analysis → development → review → testing. Hook supports both.
+If `pipeline.json` is missing, fall back to fixed phases: analysis → development → review → testing. Hook supports both.
 
 ## Skip pipeline when
 
@@ -190,4 +188,4 @@ When the work edits `packages/ai-rules/presets/**` (or dogfood `.cursor/` sync o
 - **Review-only:** pipeline step = `security-reviewer` for threat/capability diffs; parent applies skill `code-review` for schema/contract/style (no `code-reviewer` agent in Phase 1).
 - After TS changes, pipeline includes **build-verifier** with repository typecheck/test via `post-change-test` / `mcp-ts-tooling`.
 
-**Product specs:** When `/task`, `/feature-start`, or `/spec-start` touches pages/features/`docs/specs`: if INDEX exists and no generate intent → instruct next agent to load requestable **`product-specs`** (consume; soft-fail; never invent). If generate/bootstrap/`spec-gen` → load **`product-specs-authoring`** + skill **`spec-authoring`** inside **task-analyst** (not a separate pipeline step); pass created spec paths + INDEX diff in handoff; human gate must approve before feature-developer. No-op if INDEX absent and no author intent.
+**Product specs:** When `/task` or `/spec-start` touches pages/features/`docs/specs`: if INDEX exists and no generate intent → instruct next agent to load requestable **`product-specs`** (consume; soft-fail; never invent). If generate/bootstrap/`spec-gen` → load **`product-specs-authoring`** + skill **`spec-authoring`** inside **task-analyst** (not a separate pipeline step); pass created spec paths + INDEX diff in handoff; human gate must approve before feature-developer. No-op if INDEX absent and no author intent.