@bonesofspring/ai-rules 0.2.26 → 0.2.27

package/presets/cursor/java/rules/preset-token-budget.mdc

@@ -17,19 +17,19 @@ Invariants for rule loading in an **installed** preset (consumer app).
 
 | Platform | Always-on | Cap |
 |----------|-----------|-----|
-| Cursor | `alwaysApply: true` | **≤ 4** |
-| Claude | rules **without** `paths:` | **exactly 3** |
-| Mavis | `adapter-map` rules with `loadMode: root-entry` | **≤ 4** |
-| OpenCode | `adapter-map` rules with `loadMode: root-entry` | **≤ 4** |
+| Cursor | `alwaysApply: true` | **3–5** |
+| Claude | rules **without** `paths:` | **3–5** |
+| Mavis | `adapter-map` rules with `loadMode: root-entry` | **3–5** |
+| OpenCode | `adapter-map` rules with `loadMode: root-entry` | **3–5** |
 
-**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.
+Caps are **aligned** across platforms: minimum **3** (base invariants), maximum **5**. Slots beyond the base invariants are reserved for `ai-local-overlay` (consumer-owned `.ai.local/` rules). If you do not need local overlay, demote that rule to `globs: ["**/.ai.local/**"]` / Claude `paths:`, or a non-root load mode on Mavis / OpenCode.
 
-**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.
+**Claude Option A (README exclusion):** when counting Claude rules without `paths:` / session-start, **exclude `**/README.md`** (topic indexes are not session-start rules). Body budget sums only the intended session-start rules (≤5).
 
 Session-start body budget:
-- Claude trio: ≤140 lines total (stretch ≤120).
-- Cursor 4-set: ≤170 lines total (4 rules including `ai-local-overlay`).
-- Mavis / OpenCode: ≤4 root-entry rule files; combined root `AGENTS.md` + platform entry ≤170 nonempty lines. Do not dump the full rule catalog into `AGENTS.md`.
+- Claude session-start: ≤200 lines total (stretch ≤170).
+- Cursor always-on: ≤200 lines total (stretch ≤170).
+- Mavis / OpenCode: ≤5 root-entry rule files; combined root `AGENTS.md` + platform entry ≤200 nonempty lines. Do not dump the full rule catalog into `AGENTS.md`.
 
 ## Meta / author rules
 
@@ -45,4 +45,4 @@ Orchestrator, feature-delivery, code-review, post-change gates, domain globs —
 
 ## Verifier
 
-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.
+build-verifier **FAIL** if Cursor `alwaysApply` count or Claude session-start count is outside **3–5** (Claude count **excludes `**/README.md`**), or if a `preset-*` meta rule is marked always-on.

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

@@ -32,7 +32,7 @@ From `packages/ai-rules/`:
 yarn check:preset-structure
 ```
 
-Hard gates: twin-map (stacks include **mcp-ts**), token-budget (alwaysApply/session-start = 3), leakage (`MCP_TS_FORBIDDEN_IN_CHAIN`, `MCP_TS_FORBIDDEN_AGENT_STEMS`, chain forks mcp-ts≠next≠ios-swift≠go≠java≠php-hexagonal≠php-laravel), shared-core drift (`AI_RULES_DRIFT_FAIL=1` via `check:preset-structure`).
+Hard gates: twin-map (stacks include **mcp-ts**), token-budget (alwaysApply / session-start 3–5), leakage (`MCP_TS_FORBIDDEN_IN_CHAIN`, `MCP_TS_FORBIDDEN_AGENT_STEMS`, chain forks mcp-ts≠next≠ios-swift≠go≠java≠php-hexagonal≠php-laravel), shared-core drift (`AI_RULES_DRIFT_FAIL=1` via `check:preset-structure`).
 
 Document PASS/FAIL in `validation-report.md`. Soft leakage output:
 

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

@@ -1,6 +1,6 @@
 ---
 name: task
-description: Route a natural-language task through the agent-team pipeline: task-router, pipeline.json, and the first planned specialist.
+description: "Route a natural-language task through the agent-team pipeline: task-router, pipeline.json, and the first planned specialist."
 ---
 
 # Task — unified entry point (router + pipeline)

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

@@ -44,7 +44,10 @@ try {
 }
 
 const slug = active.slug;
-if (!slug) {
+// Reject non-kebab / traversal slugs: the runtime writes status.json and
+// metrics.json under tasks/<slug>, so an unchecked slug could escape the tree.
+const SLUG_RE = /^[a-z0-9]+(?:-[a-z0-9]+)*$/;
+if (typeof slug !== 'string' || slug.length > 48 || !SLUG_RE.test(slug)) {
   process.stdout.write('{}');
   process.exit(0);
 }
@@ -71,6 +74,9 @@ function waitForMetricsLock() {
   // 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.
+  // A lock left behind by a killed process is reclaimed once its mtime is older
+  // than STALE_LOCK_MS, so one crash cannot brick the task forever.
+  const STALE_LOCK_MS = 30000;
   for (let attempt = 0; attempt < 200; attempt += 1) {
     try {
       const fd = fs.openSync(METRICS_LOCK, 'wx');
@@ -78,6 +84,13 @@ function waitForMetricsLock() {
       return;
     } catch (error) {
       if (!error || error.code !== 'EEXIST') throw error;
+      try {
+        const lockStat = fs.statSync(METRICS_LOCK);
+        if (Date.now() - lockStat.mtimeMs > STALE_LOCK_MS) {
+          fs.unlinkSync(METRICS_LOCK);
+          continue;
+        }
+      } catch {}
       const until = Date.now() + 10;
       while (Date.now() < until) { /* 10 ms busy-wait */ }
     }
@@ -435,7 +448,10 @@ function legacyFlow() {
 
 
 if (hookInput.action === 'end_human_gate') {
-    status.awaitingHumanGate = false;
+  // Only advance when a gate was actually open. A duplicate or retried
+  // end_human_gate must be a no-op, not a silent pipeline skip.
+  const gateWasOpen = Boolean(status.activeHumanGateEventId) || status.awaitingHumanGate === true;
+  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,
@@ -462,7 +478,7 @@ if (hookInput.action === 'end_human_gate') {
     });
     delete status.activeHumanGateEventId;
   }
-  if (hookInput.activateNext && fs.existsSync(pipelinePath)) {
+  if (gateWasOpen && hookInput.activateNext && fs.existsSync(pipelinePath)) {
     let resumePipeline = null;
     try { resumePipeline = JSON.parse(fs.readFileSync(pipelinePath, 'utf8')); } catch {}
     if (resumePipeline) {
@@ -484,6 +500,19 @@ if (hookInput.action === 'end_human_gate') {
         else out(handoffForAgent(resumeAgents[0], resumeNext.step.scope, resumeNext.step));
         process.exit(0);
       }
+      // Gate on the final step: no executable step remains. Complete the
+      // pipeline instead of leaving it in_progress forever.
+      status.state = 'completed';
+      completeTaskMetrics();
+      writeStatus({
+        pipelineIndex: resumeSteps.length,
+        phase: 'done',
+        state: 'completed',
+        currentAgent: null,
+        awaitingHumanGate: false,
+      });
+      out(`Pipeline complete for "${slug}". Run /technical-retro ${slug}.`);
+      process.exit(0);
     }
   }
   // A2 (retro §8): if gate closes the final human gate of the pipeline

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

@@ -1,6 +1,6 @@
 # Rules (preset mcp-ts)
 
-## alwaysApply (3)
+## alwaysApply (3–5)
 
 | Rule | Role |
 |------|------|
@@ -8,7 +8,7 @@
 | `mcp-server-boundaries` | Registration / handler / capability / lifecycle |
 | `code-quality-and-refactoring` | Shared quality + TS MCP notes |
 
-**Session-start body budget:** sum of the 3 always-on bodies ≤ **140** lines (stretch ≤120).
+**Session-start body budget:** sum of the intended always-on bodies ≤ **200** lines (stretch ≤170).
 
 ## Twin depth (Cursor↔Claude)
 

package/presets/cursor/mcp-ts/rules/anti-sycophancy-discipline.mdc

@@ -1,8 +1,8 @@
 ---
 description: Anti-sycophancy discipline for code generation and review — VERIFY, failure modes, UNTESTED, honest status. Load when writing or changing code.
 globs:
-  - **/*.ts
-  - **/*.tsx
+  - "**/*.ts"
+  - "**/*.tsx"
 alwaysApply: false
 ---
 

package/presets/cursor/mcp-ts/rules/code-quality-and-refactoring.mdc

@@ -19,6 +19,12 @@ alwaysApply: true
 - **CUPID:** Composable; Unix philosophy (one responsibility); Predictable; Idiomatic (repo); Domain-based.
 - **Composition over inheritance;** Law of Demeter — no `a.b.c.d` chains; via public API / facade.
 
+# Over-abstraction guardrails
+
+- **No unnecessary constants:** do not hoist a one-off literal, string, or boolean into a named constant. Inline it, or use an existing token/enum when the value is meaningful and reused. Named constants are for shared, semantic, or repeated values.
+- **No invented utilities:** do not add a `utils`/helper for a single call site or a thin pass-through wrapper. Inline it or extend the existing helper; a new shared utility is justified only after the Rule of Three.
+- **Decompose over conditionals:** a unit (function, component, hook) that accumulates several branches (`if` / ternary / `switch`) should be split into smaller units with one reason to change instead of piling up conditions.
+
 # Refactoring during changes
 
 - Light refactor is OK if it reduces duplication, improves readability, and does not break public contracts.

package/presets/cursor/mcp-ts/rules/mcp-auth-secrets.mdc

@@ -1,10 +1,10 @@
 ---
 description: MCP env config, remote auth, redaction, secret handling
 globs:
-  - **/auth/**/*
-  - **/config/**/*
-  - **/.env*
-  - **/secrets/**/*
+  - "**/auth/**/*"
+  - "**/config/**/*"
+  - "**/.env*"
+  - "**/secrets/**/*"
 alwaysApply: false
 ---
 

package/presets/cursor/mcp-ts/rules/mcp-contract-testing.mdc

@@ -1,8 +1,8 @@
 ---
 description: MCP schema snapshots, contract fixtures, optional Inspector smoke
 globs:
-  - **/*.{test,spec}.{ts,tsx,js}
-  - **/fixtures/**/*
+  - "**/*.{test,spec}.{ts,tsx,js}"
+  - "**/fixtures/**/*"
   - src/tools/**/*
   - src/resources/**/*
   - src/prompts/**/*

package/presets/cursor/mcp-ts/rules/mcp-server-boundaries.mdc

@@ -1,5 +1,5 @@
 ---
-description: MCP server module boundaries: registration, handler, capability, lifecycle
+description: "MCP server module boundaries: registration, handler, capability, lifecycle"
 alwaysApply: true
 ---
 

package/presets/cursor/mcp-ts/rules/mcp-tool-design.mdc

@@ -1,5 +1,5 @@
 ---
-description: MCP tool/resource/prompt design: names, schemas, errors, least surprise
+description: "MCP tool/resource/prompt design: names, schemas, errors, least surprise"
 globs:
   - src/tools/**/*
   - src/resources/**/*

package/presets/cursor/mcp-ts/rules/mcp-transport-packaging.mdc

@@ -3,8 +3,8 @@ description: MCP stdio lifecycle, optional remote transport, bin/npx packaging
 globs:
   - src/index.ts
   - package.json
-  - **/Dockerfile
-  - **/docker-compose*.yml
+  - "**/Dockerfile"
+  - "**/docker-compose*.yml"
 alwaysApply: false
 ---
 

package/presets/cursor/mcp-ts/rules/mcp-ts-tooling.mdc

@@ -3,9 +3,9 @@ description: Discover package manager; typecheck/test/Inspector commands for MCP
 globs:
   - package.json
   - tsconfig*.json
-  - **/vitest.config.*
-  - **/jest.config.*
-  - **/eslint.config.*
+  - "**/vitest.config.*"
+  - "**/jest.config.*"
+  - "**/eslint.config.*"
 alwaysApply: false
 ---
 

package/presets/cursor/mcp-ts/rules/preset-layering.mdc

@@ -18,7 +18,7 @@ Rules for **preset authors** (`packages/ai-rules/presets/**`). Not always-on in
 | Layer | Where | What to put |
 |-------|-------|-------------|
 | **Core** | `presets/_shared/core/**` | Stack-agnostic prose + checklists; no frontmatter; no paths `app/**`, `Features/**`, Playwright, xcodebuild |
-| **Stack** | `presets/{cursor\|claude\|mavis\|opencode}/<stack>/` | Domain/tooling, stack always-on trio, stack examples in **Stack notes** |
+| **Stack** | `presets/{cursor\|claude\|mavis\|opencode}/<stack>/` | Domain/tooling, stack always-on set (3–5), stack examples in **Stack notes** |
 | **Platform** | Cursor `.mdc` / Claude `.md` / Mavis `.md` / OpenCode `.md` | Frontmatter (`alwaysApply`/`globs` vs `paths:` vs OpenCode `mode`/`permission`), platform-only (`BUGBOT.md`, `CLAUDE.md`) |
 
 ## Where to put a new rule

package/presets/cursor/mcp-ts/rules/preset-pr-checklist.mdc

@@ -21,7 +21,7 @@ Checklist for PRs that touch `packages/ai-rules/presets/**` (and dogfood `.curso
 - [ ] **Mavis derive:** mapped `cursor/<stack>/` change → `mavis/<stack>/` + `adapter-map.json` **same PR** when the stack is in `releasedStacks` (run `generate-mavis.mjs --stack <stack>` + `check-mavis-adapter-map.mjs`; see `preset-twin-sync` § Mavis derivation)
 - [ ] **OpenCode derive:** mapped `cursor/<stack>/` change → `opencode/<stack>/` + `adapter-map.json` **same PR** when the stack is in `releasedStacks` (run `generate-opencode.mjs --stack <stack>` + `check-opencode-adapter-map.mjs`; see `preset-twin-sync` § OpenCode derivation)
 - [ ] **Mapping:** `claude/<stack>/rules/README.md` mapping table is current
-- [ ] **Token budget:** Cursor `alwaysApply` ≤ 4 (4th slot reserved for `ai-local-overlay`); Claude session-start exactly 3; meta rules not always-on
+- [ ] **Token budget:** Cursor `alwaysApply` and Claude session-start both **3–5** (extra slots reserved for `ai-local-overlay`); body sum ≤200 (stretch ≤170); 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`.

package/presets/cursor/mcp-ts/rules/preset-token-budget.mdc

@@ -17,19 +17,19 @@ Invariants for rule loading in an **installed** preset (consumer app).
 
 | Platform | Always-on | Cap |
 |----------|-----------|-----|
-| Cursor | `alwaysApply: true` | **≤ 4** |
-| Claude | rules **without** `paths:` | **exactly 3** |
-| Mavis | `adapter-map` rules with `loadMode: root-entry` | **≤ 4** |
-| OpenCode | `adapter-map` rules with `loadMode: root-entry` | **≤ 4** |
+| Cursor | `alwaysApply: true` | **3–5** |
+| Claude | rules **without** `paths:` | **3–5** |
+| Mavis | `adapter-map` rules with `loadMode: root-entry` | **3–5** |
+| OpenCode | `adapter-map` rules with `loadMode: root-entry` | **3–5** |
 
-**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.
+Caps are **aligned** across platforms: minimum **3** (base invariants), maximum **5**. Slots beyond the base invariants are reserved for `ai-local-overlay` (consumer-owned `.ai.local/` rules). If you do not need local overlay, demote that rule to `globs: ["**/.ai.local/**"]` / Claude `paths:`, or a non-root load mode on Mavis / OpenCode.
 
-**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.
+**Claude Option A (README exclusion):** when counting Claude rules without `paths:` / session-start, **exclude `**/README.md`** (topic indexes are not session-start rules). Body budget sums only the intended session-start rules (≤5).
 
 Session-start body budget:
-- Claude trio: ≤140 lines total (stretch ≤120).
-- Cursor 4-set: ≤170 lines total (4 rules including `ai-local-overlay`).
-- Mavis / OpenCode: ≤4 root-entry rule files; combined root `AGENTS.md` + platform entry ≤170 nonempty lines. Do not dump the full rule catalog into `AGENTS.md`.
+- Claude session-start: ≤200 lines total (stretch ≤170).
+- Cursor always-on: ≤200 lines total (stretch ≤170).
+- Mavis / OpenCode: ≤5 root-entry rule files; combined root `AGENTS.md` + platform entry ≤200 nonempty lines. Do not dump the full rule catalog into `AGENTS.md`.
 
 ## Meta / author rules
 
@@ -45,4 +45,4 @@ Orchestrator, feature-delivery, code-review, post-change gates, domain globs —
 
 ## Verifier
 
-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.
+build-verifier **FAIL** if Cursor `alwaysApply` count or Claude session-start count is outside **3–5** (Claude count **excludes `**/README.md`**), or if a `preset-*` meta rule is marked always-on.

package/presets/cursor/mcp-ts/rules/security-mcp.mdc

@@ -1,5 +1,5 @@
 ---
-description: MCP security: injection boundaries, capability minimization, SSRF/secrets
+description: "MCP security: injection boundaries, capability minimization, SSRF/secrets"
 globs:
   - src/tools/**/*
   - src/resources/**/*

package/presets/cursor/mcp-ts/rules/tests-unit.mdc

@@ -1,8 +1,8 @@
 ---
 description: Unit testing conventions for MCP handlers and schemas
 globs:
-  - **/*.{test,spec}.{ts,tsx,js}
-  - **/__tests__/**/*
+  - "**/*.{test,spec}.{ts,tsx,js}"
+  - "**/__tests__/**/*"
 alwaysApply: false
 ---
 

package/presets/cursor/next/README.md

@@ -13,6 +13,6 @@ npx @bonesofspring/ai-rules init cursor --preset next
 | `rules/`, `agents/`, `skills/`, `commands/`, `hooks/` | `.cursor/<dir>/` |
 | `team/` | **`.ai.local/team/`** (templates; slugs preserved) |
 
-Always-on (≤4): `next-app-core`, `package-manager`, `code-quality-and-refactoring`, `ai-local-overlay`. Living gotchas: `.ai.local/conventions.md`. Overlay: [`docs/LOCAL-OVERLAY.md`](../../docs/LOCAL-OVERLAY.md).
+Always-on (3–5): `next-app-core`, `package-manager`, `code-quality-and-refactoring`, `ai-local-overlay`. Living gotchas: `.ai.local/conventions.md`. Overlay: [`docs/LOCAL-OVERLAY.md`](../../../docs/LOCAL-OVERLAY.md).
 
-Claude twin: `presets/claude/next/` (same PR). `BUGBOT.md` / `hooks.json` are Cursor-only. Catalog: [`rules/README.md`](./rules/README.md). Contribute: [`docs/PRESET-CONTRIBUTION.md`](../../docs/PRESET-CONTRIBUTION.md).
+Claude twin: `presets/claude/next/` (same PR). `BUGBOT.md` / `hooks.json` are Cursor-only. Catalog: [`rules/README.md`](./rules/README.md). Contribute: [`docs/PRESET-CONTRIBUTION.md`](../../../docs/PRESET-CONTRIBUTION.md).

package/presets/cursor/next/agents/build-verifier.md

@@ -38,12 +38,12 @@ When validating **preset packaging** changes (paths under `packages/ai-rules/pre
 
 ### FAIL (all stacks)
 
-1. **Token budget:** Cursor `alwaysApply: true` count ≤ **4** (4th slot reserved for `ai-local-overlay`); Claude rules without `paths:` === **3** (**exclude `**/README.md`** — Option A). Meta `preset-*` rules must **not** be `alwaysApply: true`.
+1. **Token budget:** Cursor `alwaysApply: true` count 3–5 (extra slots reserved for `ai-local-overlay`); Claude rules without `paths:` 3–5 (**exclude `**/README.md`** — Option A). Meta `preset-*` rules must **not** be `alwaysApply: true`.
 2. **Leakage (next):** hooks/agents must not require `xcuitest-test-*` handoffs or `xcodebuild` as the default Next post-change gate. See `preset-no-cross-stack-leakage.mdc`.
 3. **Mapping / README:** `claude/next/rules/README.md` must include a Cursor→Claude mapping table; stack `rules/README.md` should document core→stack mapping when `_shared` consumers exist.
 4. **shared-core consumers:** if `_shared/core/**` changed, every file with matching `<!-- shared-core: … -->` in this PR must be updated (or intentional fork documented in validation-report).
 5. **Twin presence:** Cursor rule change without Claude twin same PR → **FAIL** (next, nuxt, svelte, ios-swift, go, java, mcp-ts, php-hexagonal, and php-laravel). Domain twin body ≥15 lines; thin aliases (`agent-team-intake`, `technical-retro`) may be shorter.
-6. **Session-start body budget (soft→document, FAIL if grossly over):** sum body lines of the **3** intended always-on / session-start rules ≤ **140** (stretch ≤120); do **not** include `**/README.md`. Record the sum in validation-report.
+6. **Session-start body budget (soft→document, FAIL if grossly over):** sum body lines of the intended always-on / session-start rules ≤ **200** (stretch ≤170); do **not** include `**/README.md`. Record the sum in validation-report.
 7. **Embed drift (hard in `check:preset-structure`):** run `packages/ai-rules/scripts/check-shared-core-drift.sh` with `AI_RULES_DRIFT_FAIL=1` (bundled by the structure orchestrator). Lineage stems are excluded from body equality.
 8. **Dogfood (monorepo soft):** if root `.cursor/` is in the PR, prefer sync via `packages/ai-rules/scripts/sync-dogfood-cursor.sh`; mass deletion of tracked dogfood without migration doc → note as risk / FAIL for maintainers.
 

package/presets/cursor/next/commands/task.md

@@ -1,6 +1,6 @@
 ---
 name: task
-description: Route a natural-language task through the agent-team pipeline: task-router, pipeline.json, and the first planned specialist.
+description: "Route a natural-language task through the agent-team pipeline: task-router, pipeline.json, and the first planned specialist."
 ---
 
 # Task — unified entry point (router + pipeline)

package/presets/cursor/next/hooks/chain-team-phases.sh

@@ -42,7 +42,10 @@ try {
 }
 
 const slug = active.slug;
-if (!slug) {
+// Reject non-kebab / traversal slugs: the runtime writes status.json and
+// metrics.json under tasks/<slug>, so an unchecked slug could escape the tree.
+const SLUG_RE = /^[a-z0-9]+(?:-[a-z0-9]+)*$/;
+if (typeof slug !== 'string' || slug.length > 48 || !SLUG_RE.test(slug)) {
   process.stdout.write('{}');
   process.exit(0);
 }
@@ -69,6 +72,9 @@ function waitForMetricsLock() {
   // 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.
+  // A lock left behind by a killed process is reclaimed once its mtime is older
+  // than STALE_LOCK_MS, so one crash cannot brick the task forever.
+  const STALE_LOCK_MS = 30000;
   for (let attempt = 0; attempt < 200; attempt += 1) {
     try {
       const fd = fs.openSync(METRICS_LOCK, 'wx');
@@ -76,6 +82,13 @@ function waitForMetricsLock() {
       return;
     } catch (error) {
       if (!error || error.code !== 'EEXIST') throw error;
+      try {
+        const lockStat = fs.statSync(METRICS_LOCK);
+        if (Date.now() - lockStat.mtimeMs > STALE_LOCK_MS) {
+          fs.unlinkSync(METRICS_LOCK);
+          continue;
+        }
+      } catch {}
       const until = Date.now() + 10;
       while (Date.now() < until) { /* 10 ms busy-wait */ }
     }
@@ -495,7 +508,10 @@ function legacyFlow() {
 
 
 if (hookInput.action === 'end_human_gate') {
-    status.awaitingHumanGate = false;
+  // Only advance when a gate was actually open. A duplicate or retried
+  // end_human_gate must be a no-op, not a silent pipeline skip.
+  const gateWasOpen = Boolean(status.activeHumanGateEventId) || status.awaitingHumanGate === true;
+  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,
@@ -522,7 +538,7 @@ if (hookInput.action === 'end_human_gate') {
     });
     delete status.activeHumanGateEventId;
   }
-  if (hookInput.activateNext && fs.existsSync(pipelinePath)) {
+  if (gateWasOpen && hookInput.activateNext && fs.existsSync(pipelinePath)) {
     let resumePipeline = null;
     try { resumePipeline = JSON.parse(fs.readFileSync(pipelinePath, 'utf8')); } catch {}
     if (resumePipeline) {
@@ -544,6 +560,19 @@ if (hookInput.action === 'end_human_gate') {
         else out(handoffForAgent(resumeAgents[0], resumeNext.step.scope, resumeNext.step));
         process.exit(0);
       }
+      // Gate on the final step: no executable step remains. Complete the
+      // pipeline instead of leaving it in_progress forever.
+      status.state = 'completed';
+      completeTaskMetrics();
+      writeStatus({
+        pipelineIndex: resumeSteps.length,
+        phase: 'done',
+        state: 'completed',
+        currentAgent: null,
+        awaitingHumanGate: false,
+      });
+      out(`Pipeline complete for "${slug}". Run /technical-retro ${slug}.`);
+      process.exit(0);
     }
   }
   // A2 (retro §8): if gate closes the final human gate of the pipeline

package/presets/cursor/next/rules/README.md

@@ -9,7 +9,7 @@
 
 ### Loading strategy
 
-- **`alwaysApply: true`** (Cursor) / **without `paths:`** (Claude) — base invariants (**Cursor ≤4**, Claude exactly 3):
+- **`alwaysApply: true`** (Cursor) / **without `paths:`** (Claude) — base invariants (Cursor/Claude 3–5):
   - Cursor: `next-app-core`, `package-manager`, `code-quality-and-refactoring`, `ai-local-overlay`
   - Claude: `next-app-core`, `package-manager`, `code-quality`
 - **On-demand / requestable** — `post-change-lint` (**required after code edits**, not always-on), `agent-team-intake` (via orchestrator/commands), `agent-team-orchestrator`, architecture, imports, UI, tests, feature-delivery-workflow, `design-guidance`, `mcp-usage`, `anti-sycophancy-discipline`, `react-next-anti-hallucination`, reference-features, product-specs, product-specs-authoring, next-app-router, `security-next`, react-a11y-coding, `technical-retro`, `mockup-review`, `ux-design`

package/presets/cursor/next/rules/api-services.mdc

@@ -21,8 +21,8 @@ impact: HIGH
 - For each domain area (for example, orders, billing, account settings):
   - a separate directory in `app/src/api/services/<ServiceName or feature>/**` following repository convention.
 - Inside a module:
-  - files with API calls (`index.ts` or `*.service.ts`);
-  - mapper files (`*responseMappers.ts`);
+  - files with API calls — follow the repo's shape: `index.ts` / `*.service.ts`, **or** a per-domain module exporting an object (`XxxApiMethods` in `<Domain>.apiMethods.ts` with `<Domain>.endpoints.ts` and `<Domain>.responseTypes.ts`) as in neighboring services;
+  - mapper files (`*responseMappers.ts`) — pure `format…` / `map…` functions named as in the repo;
   - request/response-specific types (if not moved to `app/src/types/**` with export through the `@/types` barrel).
   - when needed — local `index.ts` / barrel inside the module for structure **within** `app/src/api/**`; **outside** this layer UI, store, and other code import only from the root barrel `app/src/api/index.ts` (`import … from '@/api'`, **`public-imports.mdc`**).
 
@@ -70,10 +70,12 @@ export const getCard = async (id: string) => {
 
 ```ts
 import type { TCard } from '@/types'
-import { mapCardResponse } from './cardResponseMappers'
+import { formatCardResponse } from './cardResponseMappers'
 
 export const getCard = async (id: string): Promise<TCard> => {
   const { data } = await cardsClient.get(`/cards/${id}`)
-  return mapCardResponse(data)
+  return formatCardResponse(data)
 }
 ```
+
+Mapper function verb (`format…` vs `map…`) follows the repo — match neighboring mappers.

package/presets/cursor/next/rules/code-quality-and-refactoring.mdc

@@ -19,6 +19,12 @@ alwaysApply: true
 - **CUPID:** Composable; Unix philosophy (one responsibility); Predictable; Idiomatic (repo); Domain-based.
 - **Composition over inheritance;** Law of Demeter — no `a.b.c.d` chains; via public API / facade.
 
+# Over-abstraction guardrails
+
+- **No unnecessary constants:** do not hoist a one-off literal, string, or boolean into a named constant. Inline it, or use an existing token/enum when the value is meaningful and reused. Named constants are for shared, semantic, or repeated values.
+- **No invented utilities:** do not add a `utils`/helper for a single call site or a thin pass-through wrapper. Inline it or extend the existing helper; a new shared utility is justified only after the Rule of Three.
+- **Decompose over conditionals:** a unit (function, component, hook) that accumulates several branches (`if` / ternary / `switch`) should be split into smaller units with one reason to change instead of piling up conditions.
+
 # Refactoring during changes
 
 - Light refactor is OK if it reduces duplication, improves readability, and does not break public contracts.

package/presets/cursor/next/rules/feature-delivery-workflow.mdc

@@ -11,6 +11,10 @@ alwaysApply: false
 
 When the prompt or `brief.md` contains a `figma.com` URL, **mockup review** (`mockup-reviewer` / skill `mockup-review`) must complete — or the user must continue past FAIL/`BLOCKED_MCP` via `/task-continue` — **before UI implementation**. Non-UI tasks no-op this gate. When required-signal and **no** `figma.com`, **`ux-design.md`** (on the analysis manifest entry) must exist and not be `INCOMPLETE` before UI work — else **blocked**, hand back to `task-analyst`. Parallel to the mockup gate.
 
+## Style discovery (mandatory)
+
+Before writing a new file in a layer, open **1–2 analog files** in the same layer and mirror: export shape, name prefixes (`T` / `I` where the repo uses them), file suffixes (`.apiMethods.ts`, `.endpoints.ts`, `.data.ts`, `.hooks.ts`, `styles.ts`), mapper / selector / thunk naming, and barrel shape. Record the analogs in the handoff. Where this preset's examples differ from the repo, **the repo wins**.
+
 Typical feature with backend data and shared state. Layer details — `architecture-boundaries.mdc`, `next-app-core.mdc`.
 
 ## Checklist (work order)

package/presets/cursor/next/rules/next-app-core.mdc

@@ -10,8 +10,9 @@ Concrete versions come **from `package.json` and configs of the target repositor
 # Project structure
 
 - `app/` — Next.js root; `app/src/**` — code; `app/__tests__/e2e/**` — e2e.
-- `app/tsconfig.json`: `baseUrl: "."`, `paths: { "@/*": ["./src/*"] }`.
+- `app/tsconfig.json`: `paths: { "@/*": ["./src/*"] }` (`baseUrl` may be absent with TS ≥5 / `moduleResolution: bundler` — check the file, do not add it blindly).
 - **Requirement:** `@/*` instead of relative imports that climb the tree.
+- **Router mode:** detect from the repo before adding routes — App Router (`app/src/app/**`, `page.tsx`) vs Pages Router (`app/src/pages/**`, `_app.tsx`). Do **not** assume App Router; follow the mode already in use (`next-app-router.mdc`, `navigation-router-stack.mdc`).
 
 # Architectural layers
 

package/presets/cursor/next/rules/preset-layering.mdc

@@ -1,5 +1,5 @@
 ---
-description: Preset authoring: Core → Stack → Platform layering. Use when editing packages/ai-rules/presets/**.
+description: "Preset authoring: Core → Stack → Platform layering. Use when editing packages/ai-rules/presets/**."
 globs:
   - packages/ai-rules/presets/**/*
   - .cursor/rules/**/*
@@ -18,7 +18,7 @@ Rules for **preset authors** (`packages/ai-rules/presets/**`). Not always-on in
 | Layer | Where | What to put |
 |-------|-------|-------------|
 | **Core** | `presets/_shared/core/**` | Stack-agnostic prose + checklists; no frontmatter; no paths `app/**`, `Features/**`, Playwright, xcodebuild |
-| **Stack** | `presets/{cursor\|claude\|mavis\|opencode}/<stack>/` | Domain/tooling, stack always-on trio, stack examples in **Stack notes** |
+| **Stack** | `presets/{cursor\|claude\|mavis\|opencode}/<stack>/` | Domain/tooling, stack always-on set (3–5), stack examples in **Stack notes** |
 | **Platform** | Cursor `.mdc` / Claude `.md` / Mavis `.md` / OpenCode `.md` | Frontmatter (`alwaysApply`/`globs` vs `paths:` vs OpenCode `mode`/`permission`), platform-only (`BUGBOT.md`, `CLAUDE.md`) |
 
 ## Where to put a new rule

package/presets/cursor/next/rules/preset-no-cross-stack-leakage.mdc

@@ -1,5 +1,5 @@
 ---
-description: Preset authoring: forbid cross-stack agent/path leakage in hooks and agents.
+description: "Preset authoring: forbid cross-stack agent/path leakage in hooks and agents."
 globs:
   - packages/ai-rules/presets/**/*
   - .cursor/rules/**/*

package/presets/cursor/next/rules/preset-pr-checklist.mdc

@@ -1,5 +1,5 @@
 ---
-description: Preset authoring: PR checklist for twin sync, budget, leakage, README. Use on preset PRs.
+description: "Preset authoring: PR checklist for twin sync, budget, leakage, README. Use on preset PRs."
 globs:
   - packages/ai-rules/presets/**/*
   - .cursor/rules/**/*
@@ -21,7 +21,7 @@ Checklist for PRs that touch `packages/ai-rules/presets/**` (and dogfood `.curso
 - [ ] **Mavis derive:** mapped `cursor/<stack>/` change → `mavis/<stack>/` + `adapter-map.json` **same PR** when the stack is in `releasedStacks` (run `generate-mavis.mjs --stack <stack>` + `check-mavis-adapter-map.mjs`; see `preset-twin-sync` § Mavis derivation)
 - [ ] **OpenCode derive:** mapped `cursor/<stack>/` change → `opencode/<stack>/` + `adapter-map.json` **same PR** when the stack is in `releasedStacks` (run `generate-opencode.mjs --stack <stack>` + `check-opencode-adapter-map.mjs`; see `preset-twin-sync` § OpenCode derivation)
 - [ ] **Mapping:** `claude/<stack>/rules/README.md` mapping table is current
-- [ ] **Token budget:** Cursor `alwaysApply` ≤ 4 (4th slot reserved for `ai-local-overlay`); Claude session-start exactly 3; meta rules not always-on
+- [ ] **Token budget:** Cursor `alwaysApply` and Claude session-start both **3–5** (extra slots reserved for `ai-local-overlay`); body sum ≤200 (stretch ≤170); 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`.

package/presets/cursor/next/rules/preset-token-budget.mdc

@@ -1,5 +1,5 @@
 ---
-description: Preset authoring: ≤3 always-on / session-start; meta rules never alwaysApply.
+description: "Preset authoring: ≤3 always-on / session-start; meta rules never alwaysApply."
 globs:
   - packages/ai-rules/presets/**/*
   - .cursor/rules/**/*
@@ -17,19 +17,19 @@ Invariants for rule loading in an **installed** preset (consumer app).
 
 | Platform | Always-on | Cap |
 |----------|-----------|-----|
-| Cursor | `alwaysApply: true` | **≤ 4** |
-| Claude | rules **without** `paths:` | **exactly 3** |
-| Mavis | `adapter-map` rules with `loadMode: root-entry` | **≤ 4** |
-| OpenCode | `adapter-map` rules with `loadMode: root-entry` | **≤ 4** |
+| Cursor | `alwaysApply: true` | **3–5** |
+| Claude | rules **without** `paths:` | **3–5** |
+| Mavis | `adapter-map` rules with `loadMode: root-entry` | **3–5** |
+| OpenCode | `adapter-map` rules with `loadMode: root-entry` | **3–5** |
 
-**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.
+Caps are **aligned** across platforms: minimum **3** (base invariants), maximum **5**. Slots beyond the base invariants are reserved for `ai-local-overlay` (consumer-owned `.ai.local/` rules). If you do not need local overlay, demote that rule to `globs: ["**/.ai.local/**"]` / Claude `paths:`, or a non-root load mode on Mavis / OpenCode.
 
-**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.
+**Claude Option A (README exclusion):** when counting Claude rules without `paths:` / session-start, **exclude `**/README.md`** (topic indexes are not session-start rules). Body budget sums only the intended session-start rules (≤5).
 
 Session-start body budget:
-- Claude trio: ≤140 lines total (stretch ≤120).
-- Cursor 4-set: ≤170 lines total (4 rules including `ai-local-overlay`).
-- Mavis / OpenCode: ≤4 root-entry rule files; combined root `AGENTS.md` + platform entry ≤170 nonempty lines. Do not dump the full rule catalog into `AGENTS.md`.
+- Claude session-start: ≤200 lines total (stretch ≤170).
+- Cursor always-on: ≤200 lines total (stretch ≤170).
+- Mavis / OpenCode: ≤5 root-entry rule files; combined root `AGENTS.md` + platform entry ≤200 nonempty lines. Do not dump the full rule catalog into `AGENTS.md`.
 
 ## Meta / author rules
 
@@ -45,4 +45,4 @@ Orchestrator, feature-delivery, code-review, post-change gates, domain globs —
 
 ## Verifier
 
-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.
+build-verifier **FAIL** if Cursor `alwaysApply` count or Claude session-start count is outside **3–5** (Claude count **excludes `**/README.md`**), or if a `preset-*` meta rule is marked always-on.

package/presets/cursor/next/rules/preset-twin-sync.mdc

@@ -1,5 +1,5 @@
 ---
-description: Preset authoring: Cursor SoT → Claude twin same PR. Use when editing preset rules.
+description: "Preset authoring: Cursor SoT → Claude twin same PR. Use when editing preset rules."
 globs:
   - packages/ai-rules/presets/**/*
   - .cursor/rules/**/*