@bonesofspring/ai-rules 0.2.26 → 0.2.27

package/docs/specs/INDEX.md

@@ -0,0 +1,9 @@
+# Product specs INDEX
+
+Discovery table for `docs/specs/**`. Agents start here when the file exists.
+
+| id | type | domain | title | path | routes | aliases | status |
+|----|------|--------|-------|------|--------|---------|--------|
+| <!-- example-row: example-page | page | example | Example page | docs/specs/domains/example/example-page.md | /example | ExamplePage | draft --> |
+
+<!-- Add one row per page/feature spec. Keep `id` and `path` in sync with frontmatter. -->

package/docs/specs/_templates/feature.md

@@ -0,0 +1,32 @@
+---
+id: example-feature
+type: feature
+domain: example
+routes: []
+ui: []
+store: []
+api: []
+aliases: []
+e2e: []
+status: draft
+owners: []
+related: []
+---
+
+# Example feature
+
+## Overview
+
+Cross-page shared behavior for this domain. Prefer `type: feature` on backend/MCP stacks.
+
+## Shared behavior / constraints
+
+- Invariants that apply across related pages/tools.
+
+## Related pages
+
+- Link page specs in this domain (or N/A).
+
+## Cross-cutting states
+
+N/A

package/docs/specs/_templates/page.md

@@ -0,0 +1,47 @@
+---
+id: example-page
+type: page
+domain: example
+routes: []
+ui: []
+store: []
+api: []
+aliases: []
+e2e: []
+status: draft
+owners: []
+related: []
+---
+
+# Example page
+
+## Overview
+
+Short product behavior summary. Replace placeholders from brief AC / user / labeled sources.
+
+## Entry / actors
+
+Who enters this page and from where.
+
+## Primary flows
+
+1. Happy path steps.
+
+## States
+
+- Loading: …
+- Empty: …
+- Error: …
+- Success: …
+
+## Acceptance criteria
+
+- [ ] Link or restated AC from brief / product source.
+
+## Edge cases
+
+N/A
+
+## Related specs
+
+- (optional feature.md or sibling page ids)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bonesofspring/ai-rules",
-  "version": "0.2.26",
+  "version": "0.2.27",
   "description": "Presets of Cursor, Claude, Mavis, and OpenCode rules/commands for Revy Ross personal use",
   "license": "MIT",
   "author": "Revy Ross",
@@ -23,7 +23,9 @@
   "files": [
     "README.md",
     "CHANGELOG.md",
+    "LICENSE",
     "bin",
+    "docs",
     "presets",
     "scripts"
   ],
@@ -35,10 +37,12 @@
     "check:hook-only-lifecycle": "bash scripts/check-hook-only-lifecycle.sh",
     "check:local-overlay": "bash scripts/check-local-overlay.sh",
     "check:preset-i18n": "AI_RULES_I18N_FAIL=1 AI_RULES_I18N_SOFT=0 bash scripts/check-preset-i18n.sh",
+    "check:frontmatter": "node scripts/check-frontmatter.mjs",
     "check:shared-core-drift": "bash scripts/check-shared-core-drift.sh",
     "check:product-specs": "bash scripts/check-product-specs.sh",
     "check:product-specs:dogfood": "bash scripts/check-product-specs.sh ../../dogfood/mcp-ts-sample",
     "check:rule-eval": "node scripts/check-rule-eval.mjs",
+    "check:generated-drift": "node scripts/check-generated-drift.mjs",
     "test:cli-mcp-merge": "node scripts/test-cli-mcp-merge.mjs",
     "test:cli-init-clean": "node scripts/test-cli-init-clean.mjs",
     "test:chain-coverage": "node scripts/test-chain-team-phases-coverage.mjs",
@@ -54,6 +58,7 @@
     "check:opencode-token-budget": "node scripts/check-opencode-token-budget.mjs",
     "check:opencode-local-overlay": "node scripts/check-opencode-local-overlay.mjs",
     "test:opencode-context-budget": "node scripts/test-opencode-context-budget.mjs",
+    "test:probe-mavis-capabilities": "node scripts/test-probe-mavis-capabilities.mjs",
     "generate:mavis": "node scripts/generate-mavis.mjs",
     "generate:opencode": "node scripts/generate-opencode.mjs"
   },

package/presets/_shared/core/meta/preset-layering.md

@@ -7,7 +7,7 @@ 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/_shared/core/meta/preset-pr-checklist.md

@@ -10,7 +10,7 @@ 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/_shared/core/meta/preset-token-budget.md

@@ -6,19 +6,19 @@ 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
 
@@ -34,4 +34,4 @@ 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/_shared/core/quality/code-quality-and-refactoring.md

@@ -12,6 +12,12 @@
 - **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/claude/android-kotlin/agents/build-verifier.md

@@ -37,7 +37,7 @@ When validating **android-kotlin preset** changes (or `scope: preset-structure-v
 
 ### FAIL (android-kotlin packaging)
 
-1. **Token budget:** Cursor `alwaysApply: true` count ≤ **3**; Claude rules without `paths:` === **3** (**exclude `**/README.md`**). Meta `preset-*` rules must **not** be always-on.
+1. **Token budget:** Cursor `alwaysApply: true` count 3–5; Claude rules without `paths:` 3–5 (**exclude `**/README.md`**). Meta `preset-*` rules must **not** be always-on.
 2. **Chain fork:** `hooks/chain-team-phases.sh` byte-≠ every other stack (Cursor + Claude).
 3. **Forbidden handoff strings** in android-kotlin `chain-team-phases.sh` (Cursor + Claude): `playwright-test-`, `playwright-agents`, `playwright-e2e`, `user-playwright`, `app/__tests__/e2e`, `xcuitest-test-`, positive `xcodebuild` / `SwiftLint` as required handoffs, positive yarn `lint:js` / `lint:css`.
 4. **Required handoff stems:** `AGENT_HANDOFF` includes `instrumentation-test-planner` (or generator/healer); `build-verifier` prose mentions `gradle-tooling` and/or `post-change-build`.
@@ -45,7 +45,7 @@ When validating **android-kotlin preset** changes (or `scope: preset-structure-v
 6. **Twin presence (hard):** Cursor rule → Claude twin + mapping row — **FAIL** if missing.
 7. **Mapping / README:** `claude/android-kotlin/rules/README.md` mapping table present.
 8. **shared-core consumers:** if `_shared/core/**` changed, matching embeds updated (or intentional fork documented).
-9. **Session-start body budget:** sum of the 3 always-on / session-start bodies ≤ **140** lines.
+9. **Session-start body budget:** sum of the intended always-on / session-start bodies ≤ **200** lines.
 10. **Embed drift:** `packages/ai-rules/scripts/check-shared-core-drift.sh` with `AI_RULES_DRIFT_FAIL=1`.
 11. **Root AGENTS template:** ship `REPO_AGENTS.md` → **FAIL** if missing.
 12. **Hooks cookbook:** `hooks.json` must **not** reference `hooks/examples/`.

package/presets/claude/android-kotlin/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 — single entry point

package/presets/claude/android-kotlin/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/claude/android-kotlin/hooks/examples/README.md

@@ -8,11 +8,13 @@ Optional scripts under `hooks/examples/`. **Not** referenced from default `hooks
 | `format-edited.example.sh` | Stack formatter / linter on edited files |
 | `test-on-save.example.sh` | Scoped tests for the stack |
 
-## Wiring (Cursor)
+## Wiring (Claude Code)
+
+Claude Code has no preset `hooks.json`; hooks are registered in `.claude/settings.json` and fire on events such as `PreToolUse`, `PostToolUse`, and `Stop`.
 
 1. Copy an example into `hooks/` (drop `.example` suffix), e.g. `cp hooks/examples/secret-guard.example.sh hooks/secret-guard.sh`.
 2. `chmod +x hooks/secret-guard.sh`.
-3. Add a hook entry in `.cursor/hooks.json` (e.g. `beforeShellExecution` or `afterFileEdit` — see Cursor hooks docs).
-4. Keep cookbook scripts **out** of the default preset `hooks.json` when contributing back upstream.
+3. Register the command in `.claude/settings.json` (see Claude Code hooks docs for event/matcher syntax).
+4. Keep cookbook scripts **out** of the default preset when contributing back upstream.
 
 Stack: **android-kotlin** — recipes must stay stack-safe (no cross-stack lint/test commands).

package/presets/claude/android-kotlin/hooks/examples/test-on-save.example.sh

@@ -1,8 +1,10 @@
 #!/usr/bin/env bash
-# Optional: ./gradlew test slice for the active scheme (adjust SCHEME/DEST).
+# Optional: ./gradlew unit-test slice after save.
 # NOT in default hooks.json. No Playwright / yarn lint.
 set -euo pipefail
-SCHEME="${XCODE_SCHEME:-App}"
-DEST="${XCODE_DESTINATION:-platform=Android Simulator,name=iPhone 16}"
-./gradlew test -scheme "$SCHEME" -destination "$DEST" -quiet 2>/dev/null || true
+ROOT="${CURSOR_PROJECT_DIR:-.}"
+cd "$ROOT" 2>/dev/null || exit 0
+[[ -f gradlew ]] || exit 0
+# Prefer a targeted Gradle task; adjust module/task to match the repo.
+./gradlew test --quiet 2>/dev/null || true
 exit 0

package/presets/claude/android-kotlin/rules/README.md

@@ -13,7 +13,7 @@ In Claude Code all `.md` files under `rules/` are **discovered recursively**. Bo
 
 ## Loading budget
 
-- **Session-start (no `paths:`):** exactly **3** — `android-app-core`, `boundaries`, `code-quality` (≤140 body lines total)
+- **Session-start (no `paths:`):** 3–5 — `android-app-core`, `boundaries`, `code-quality` (≤200 body lines total)
 - **Everything else** — with `paths:`
 - **Soft twin depth:** domain rules ≥15 body lines; thin aliases (`agent-team-intake`, `technical-retro`) may be shorter
 

package/presets/claude/android-kotlin/rules/tooling-and-review/code-quality.md

@@ -18,6 +18,12 @@ description: Maintain and improve Android Kotlin code quality and architecture
 - **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/claude/android-kotlin/rules/tooling-and-review/mcp-usage.md

@@ -1,7 +1,7 @@
 ---
 description: When to call shipped Context7 and local overlay MCP — detect presence, use if the task fits, degrade.
 paths:
-  - **/*.kt
+  - "**/*.kt"
 ---
 
 <!-- shared-core: quality/mcp-usage.md -->

package/presets/claude/android-kotlin/rules/tooling-and-review/preset-layering.md

@@ -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/**."
 paths:
   - packages/ai-rules/presets/**/*
   - .claude/**/*
@@ -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/claude/android-kotlin/rules/tooling-and-review/preset-no-cross-stack-leakage.md

@@ -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."
 paths:
   - packages/ai-rules/presets/**/*
   - .claude/**/*

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

@@ -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."
 paths:
   - packages/ai-rules/presets/**/*
   - .claude/**/*
@@ -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/claude/android-kotlin/rules/tooling-and-review/preset-token-budget.md

@@ -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."
 paths:
   - packages/ai-rules/presets/**/*
   - .claude/**/*
@@ -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/claude/android-kotlin/rules/tooling-and-review/preset-twin-sync.md

@@ -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."
 paths:
   - packages/ai-rules/presets/**/*
   - .claude/**/*

package/presets/claude/android-kotlin/rules/ui-and-accessibility/compose.md

@@ -29,3 +29,5 @@ paths:
 - Render loading / empty / error / content from ViewModel state — no hidden local business rules.
 - Hoist state as the repo does; avoid duplicating ViewModel state in remember blocks.
 - Side-effect APIs (`LaunchedEffect`, etc.) only for UI concerns, not repository calls.
+- Prefer **decomposition over conditionals**: a composable with several `when` / `if` branches that render different UI should delegate to small sub-composables (`LoadingState()`, `EmptyState()`, `Content()`), not nest branches in one body.
+- Keep the condition in the parent; sub-composables receive resolved state. A `mode` / `variant` parameter that switches between unrelated layouts is **two** composables, not one.

package/presets/claude/go/CLAUDE.md

@@ -4,7 +4,7 @@ Preset for Go backends using ports & adapters.
 
 **Repo-root agents:** see [`AGENTS.md`](../../AGENTS.md) at the project root.
 
-- Session-start: `go-app-core`, `architecture/boundaries`, `code-quality` (exactly 3).
+- Session-start: `go-app-core`, `architecture/boundaries`, `code-quality` (3–5).
 - Delivery: `architecture/feature-delivery.md` + skill `feature-delivery`.
 - After Go edits: `tooling-and-review/post-change-test.md`.
 - Integration tests: agents `integration-test-*` (never Playwright/XCUITest).

package/presets/claude/go/agents/build-verifier.md

@@ -31,7 +31,7 @@ From `packages/ai-rules/`:
 yarn check:preset-structure
 ```
 
-Hard gates: twin-map (stacks include **go**), token-budget (alwaysApply/session-start = 3), leakage (`GO_FORBIDDEN_*`, chain forks go≠next≠ios-swift≠java), shared-core drift (`AI_RULES_DRIFT_FAIL=1` via `check:preset-structure`).
+Hard gates: twin-map (stacks include **go**), token-budget (alwaysApply / session-start 3–5), leakage (`GO_FORBIDDEN_*`, chain forks go≠next≠ios-swift≠java), shared-core drift (`AI_RULES_DRIFT_FAIL=1` via `check:preset-structure`).
 
 Document PASS/FAIL in `validation-report.md`.
 

package/presets/claude/go/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 — single entry point

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

@@ -43,7 +43,10 @@ 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);
 }
@@ -70,6 +73,9 @@ 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');
@@ -77,6 +83,13 @@ 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 */ }
     }
@@ -490,7 +503,10 @@ 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,
@@ -517,7 +533,7 @@ 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) {
@@ -539,6 +555,19 @@ 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/claude/go/hooks/examples/README.md

@@ -8,11 +8,13 @@ Optional scripts under `hooks/examples/`. **Not** referenced from default `hooks
 | `format-edited.example.sh` | Stack formatter / linter on edited files |
 | `test-on-save.example.sh` | Scoped tests for the stack |
 
-## Wiring (Cursor)
+## Wiring (Claude Code)
+
+Claude Code has no preset `hooks.json`; hooks are registered in `.claude/settings.json` and fire on events such as `PreToolUse`, `PostToolUse`, and `Stop`.
 
 1. Copy an example into `hooks/` (drop `.example` suffix), e.g. `cp hooks/examples/secret-guard.example.sh hooks/secret-guard.sh`.
 2. `chmod +x hooks/secret-guard.sh`.
-3. Add a hook entry in `.cursor/hooks.json` (e.g. `beforeShellExecution` or `afterFileEdit` — see Cursor hooks docs).
-4. Keep cookbook scripts **out** of the default preset `hooks.json` when contributing back upstream.
+3. Register the command in `.claude/settings.json` (see Claude Code hooks docs for event/matcher syntax).
+4. Keep cookbook scripts **out** of the default preset when contributing back upstream.
 
 Stack: **go** — recipes must stay stack-safe (no cross-stack lint/test commands).

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

@@ -12,7 +12,7 @@ Claude topic `.md` files are **derived** from Cursor SoT `presets/cursor/go/rule
 
 ## Loading budget
 
-- **Session-start (no `paths:`):** exactly **3** — `go-app-core`, `boundaries`, `code-quality`
+- **Session-start (no `paths:`):** 3–5 — `go-app-core`, `boundaries`, `code-quality`
 - All others — with `paths:`
 - **Twin depth:** domain rules target ≥15 body lines; thin aliases: `agent-team-intake`, `technical-retro`; checklist **stubs** documented in Cursor `presets/cursor/go/rules/README.md` Catalog (Depth column)
 

package/presets/claude/go/rules/api-and-data/adapters-driven.md

@@ -2,9 +2,9 @@
 description: Driven adapters (persistence, cache, messaging) for Go hexagonal services
 paths:
   - internal/adapters/persistence/**/*
-  - **/adapters/persistence/**/*
-  - **/adapters/cache/**/*
-  - **/adapters/messaging/**/*
+  - "**/adapters/persistence/**/*"
+  - "**/adapters/cache/**/*"
+  - "**/adapters/messaging/**/*"
 ---