bigpowers 2.88.11 → 2.88.13

package/scripts/test-golden-gate-runner.sh

@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+# story: BUG-2026-10-25-ci-critical-path
+# test-golden-gate-runner.sh — regression guard for golden_run_deterministic_gates.
+#
+# Runs the real runner against a fixture gate list and asserts:
+#   (a) a failing gate prints the tail of its output (CI used to show only FAIL)
+#   (b) GOLDEN_SKIP_GATES reports a named gate as SKIP with its reason
+#   (c) an unknown name in GOLDEN_SKIP_GATES is a FAIL, so a typo cannot
+#       silently disable nothing while claiming to skip something
+#   (d) without GOLDEN_SKIP_GATES every gate runs — the default stays full
+#
+# Usage: bash scripts/test-golden-gate-runner.sh
+
+set -euo pipefail
+source "$(dirname "${BASH_SOURCE[0]}")/lib/skill-common.sh"
+resolve_repo_root
+cd "$REPO_ROOT"
+
+FAILURES=0
+pass() { echo "PASS $1"; }
+fail() { echo "FAIL $1"; FAILURES=$((FAILURES + 1)); }
+
+# Run the runner in a subshell with a fixture gate list; prints its stdout and
+# the final counters as "COUNTS pass fail skip".
+run_fixture() {
+  (
+    source scripts/lib/golden-suite-gates.sh
+    GOLDEN_GATES=(
+      "ok-gate:true:false"
+      "bad-gate:sh -c 'echo marker-line-from-failing-gate; exit 3':false"
+      "covered-gate:true:false"
+    )
+    golden_run_deterministic_gates
+    echo "COUNTS $PASS_COUNT $FAIL_COUNT $SKIP_COUNT"
+  )
+}
+
+out=$(GOLDEN_SKIP_GATES="" run_fixture)
+echo "$out" | grep -q 'marker-line-from-failing-gate' \
+  && pass "(a) failing gate output is printed" \
+  || fail "(a) failing gate output is missing"
+echo "$out" | grep -q '^COUNTS 2 1 0$' \
+  && pass "(d) no skip list runs every gate" \
+  || fail "(d) default run counts wrong: $(echo "$out" | grep COUNTS)"
+
+out=$(GOLDEN_SKIP_GATES="covered-gate" GOLDEN_SKIP_REASON="runs in its own CI job" run_fixture)
+echo "$out" | grep -q '^\[covered-gate\] .*SKIP.*runs in its own CI job' \
+  && pass "(b) skipped gate reported with reason" \
+  || fail "(b) skipped gate not reported with reason"
+echo "$out" | grep -q '^COUNTS 1 1 1$' \
+  && pass "(b) skipped gate counted as skip, not pass" \
+  || fail "(b) skip counts wrong: $(echo "$out" | grep COUNTS)"
+
+out=$(GOLDEN_SKIP_GATES="no-such-gate" run_fixture)
+echo "$out" | grep -q 'no-such-gate' && echo "$out" | grep -q '^COUNTS 2 2 0$' \
+  && pass "(c) unknown skip name fails the run" \
+  || fail "(c) unknown skip name accepted: $(echo "$out" | grep COUNTS)"
+
+[ "$FAILURES" -eq 0 ] && echo "OK: golden gate runner" || { echo "$FAILURES check(s) failed"; exit 1; }

package/scripts/verify-tdd-red-commit.sh

@@ -6,7 +6,9 @@
 #   TDD_VERIFY_CMD='npm test' bash scripts/verify-tdd-red-commit.sh
 set -euo pipefail
 
-REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+REPO_ROOT="$(git -C "$PWD" rev-parse --show-toplevel 2>/dev/null)" || {
+  echo "verify-tdd-red-commit: not in a git repository" >&2; exit 1
+}
 cd "$REPO_ROOT"
 
 self_test() {

package/skills/audit-code/SKILL.md

@@ -1,7 +1,7 @@
 ---
-# story: e51s04
-# story: e45s18
-# story: e45s31
+<!-- story: e51s04 -->
+<!-- story: e45s18 -->
+<!-- story: e45s31 -->
 name: audit-code
 model: haiku
 effort: standard
@@ -9,8 +9,18 @@ description: Self-review checklist for the coding agent to run before dispatchin
 ---
 
 # Audit Code
-> **HARD GATE** — **HARD GATE** — Audit must check for: bugs (correctness), security, performance, and clarity. Do NOT skip security review if the code touches user data, auth, or external APIs.
+> **HARD GATE** — Audit must check for: bugs (correctness), security, performance, and clarity. Do NOT skip security review if the code touches user data, auth, or external APIs.
 
+## Target (argument)
+
+If an argument was passed after `/audit` (e.g. `/audit abc1234` or `/audit HEAD~3..HEAD`), use it as the diff target:
+
+```bash
+git diff <arg>        # range or two-ref form: abc..def, HEAD~3..HEAD
+git show <arg>        # single commit: abc1234
+```
+
+If no argument was given, review uncommitted working-tree changes (`git diff` + `git diff --staged`).
 
 Run this self-review before asking anyone else to look at the code. The goal is to catch everything that is clearly wrong or missing — so the reviewer can focus on design and architecture, not hygiene.
 
@@ -37,7 +47,6 @@ Apply the full checklist to churn-ranked files in descending order. Files with z
 bash scripts/lib/parallel-review-worktrees.sh audit-code
 ```
 
-
 ## Checklist
 
 ### Supply Chain & Security
@@ -136,7 +145,6 @@ In `--gate` mode, print one summary line per checklist section (`PASS Supply Cha
 Gate: READY -> next: commit-message
 Writes: state.yaml handoff.next_skill = commit-message
 
-
 <!-- story: e01s02 -->
 <!-- story: e06s03 -->
 <!-- story: e07s01 -->

package/skills/build-epic/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: build-epic
-# story: e18s01 e18s02 e18s03 e38s02
+<!-- story: e18s01 e18s02 e18s03 e38s02 -->
 model: sonnet
 effort: standard
 description: Eight-step epic build cycle — reads state.yaml, execution-status.yaml, and one epic capsule; updates status via bp-yaml-set or direct edit. Resume mode runs one step per invocation. Use instead of ad-hoc execute-plan for release work.
 ---
 
-# story: e20s05
+<!-- story: e20s05 -->
 
 # Build Epic
 

package/skills/change-request/SKILL.md

@@ -5,8 +5,8 @@ effort: standard
 description: Add a new requirement or reorder epics by WSJF against specs/release-plan.yaml and epic capsule directories. Modes Add and Reorder. Use when a new requirement arrives mid-release or the plan needs prioritization.
 ---
 
-# story: e45s29
-# story: e20s01
+<!-- story: e45s29 -->
+<!-- story: e20s01 -->
 
 # Change Request
 

package/skills/commit-message/SKILL.md

@@ -5,7 +5,7 @@ effort: standard
 description: Reviews working-tree changes, then drafts a Conventional Commits title/body and states the semantic-release version bump a single such commit would imply. Also notes which defensive-code categories were touched. Use when the user wants to commit recent work, prepare a Conventional Commits message, or asks for semantic-release / semver-consistent messaging before git commit.
 ---
 
-# story: e82s02
+<!-- story: e82s02 -->
 
 # Commit Message
 > **HARD GATE** — **HARD GATE** — Commits must follow Conventional Commits spec (type(scope): description). Do NOT use vague messages like 'fix' or 'updates.' The message must explain the 'why,' not the 'what.'

package/skills/compose-workflow/SKILL.md

@@ -5,9 +5,9 @@ model: sonnet
 effort: standard
 ---
 
-# story: e09s01
-# story: e45s27
-# story: e21s04
+<!-- story: e09s01 -->
+<!-- story: e45s27 -->
+<!-- story: e21s04 -->
 
 # Compose Workflow
 > **HARD GATE** — **HARD GATE** — Workflows are orchestration, not automation. Do NOT create workflows for tasks that should be single skills. Workflow complexity must be justified.

package/skills/context7-mcp/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: context7-mcp
-# story: e45s19 e45s20
+<!-- story: e45s19 e45s20 -->
 model: haiku
 effort: light
 description: Fetch current library docs via Context7 MCP instead of training data. Use when user asks about frameworks, APIs, setup, or code examples for React, Next.js, Prisma, etc.

package/skills/craft-skill/SKILL.md

@@ -1,7 +1,7 @@
 ---
-# story: e45s02
-# story: e45s12
-# story: e79s02
+<!-- story: e45s02 -->
+<!-- story: e45s12 -->
+<!-- story: e79s02 -->
 name: craft-skill
 model: sonnet
 effort: standard

package/skills/deepen-architecture/SKILL.md

@@ -1,6 +1,6 @@
 ---
-# story: e45s31
-# story: e45s14
+<!-- story: e45s31 -->
+<!-- story: e45s14 -->
 name: deepen-architecture
 model: sonnet
 effort: standard

package/skills/delegate-task/SKILL.md

@@ -5,7 +5,7 @@ effort: standard
 description: Delegate one complex task to a single subagent, review its work in two stages before merging back. Sequential — one agent at a time, with oversight. Use when a task is complex and requires careful review before the result is accepted. Distinct from dispatch-agents (no parallelism here; reviewer sees full diff before proceeding).
 ---
 
-# story: e45s30
+<!-- story: e45s30 -->
 
 # Delegate Task
 > **HARD GATE** — **HARD GATE** — Delegated work must have clear success criteria and verification commands. The delegate must be able to verify completion independently.

package/skills/deploy/SKILL.md

@@ -1,5 +1,5 @@
 ---
-# story: e45s15
+<!-- story: e45s15 -->
 name: deploy
 description: "Build → verify artifact → deploy → wait → smoke deployment pipeline. Platform-agnostic (MCP or CLI), with configurable timeout, retry with exponential backoff, and integrated health-check. The deploy half of CI/CD: run after build to push to production."
 model: sonnet

package/skills/develop-tdd/SKILL.md

@@ -1,10 +1,10 @@
 ---
-# story: e80s01
-# story: e80s03
-# story: e51s04
-# story: e45s06
-# story: e45s08
-# story: e45s34
+<!-- story: e80s01 -->
+<!-- story: e80s03 -->
+<!-- story: e51s04 -->
+<!-- story: e45s06 -->
+<!-- story: e45s08 -->
+<!-- story: e45s34 -->
 name: develop-tdd
 model: sonnet
 effort: standard

package/skills/diagnose-stall/SKILL.md

@@ -1,5 +1,5 @@
 ---
-# story: e45s38
+<!-- story: e45s38 -->
 name: diagnose-stall
 model: haiku
 effort: light

package/skills/dispatch-agents/SKILL.md

@@ -5,12 +5,12 @@ effort: standard
 description: Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate).
 ---
 
-# story: e09s04
-# story: e45s38
+<!-- story: e09s04 -->
+<!-- story: e45s38 -->
 <!-- story: e45s11 -->
 
 
-# story: e45s30
+<!-- story: e45s30 -->
 
 # Dispatch Agents
 > **HARD GATE** — **HARD GATE** — Agent work must be parallelizable and have explicit synchronization points. Do NOT dispatch work that has hidden dependencies between agents.

package/skills/elaborate-spec/SKILL.md

@@ -3,7 +3,7 @@ name: elaborate-spec
 model: opus
 effort: standard
 description: Refine a rough idea into a clear, detailed specification through dialogue. Does not produce code. Use when user has a vague idea, wants to think through a feature before planning, or needs to turn "I want X" into a concrete spec.
-# story: e24s01
+<!-- story: e24s01 -->
 ---
 
 # Elaborate Spec

package/skills/enforce-first/SKILL.md

@@ -1,5 +1,5 @@
 ---
-# story: e80s01
+<!-- story: e80s01 -->
 name: enforce-first
 model: haiku
 effort: standard

package/skills/evolve-skill/SKILL.md

@@ -4,10 +4,10 @@ description: Benchmark-gated skill evolution — consume bigpowers-benchmark rep
 model: opus
 effort: standard
 ---
-# story: e23s03
+<!-- story: e23s03 -->
 
-# story: e09s01
-# story: e09s05
+<!-- story: e09s01 -->
+<!-- story: e09s05 -->
 
 # Evolve Skill
 

package/skills/fix-bug/SKILL.md

@@ -1,5 +1,5 @@
 ---
-# story: e51s04
+<!-- story: e51s04 -->
 name: fix-bug
 model: sonnet
 effort: standard

package/skills/gate-trace/SKILL.md

@@ -1,10 +1,10 @@
 ---
-# story: e80s01
-# story: e45s05
+<!-- story: e80s01 -->
+<!-- story: e45s05 -->
 name: gate-trace
 description: "Deterministic traceability quality gate — reads coverage matrix + blind-spot data, applies decision rules with oracle confidence downgrade, emits PASS/CONCERNS/FAIL/WAIVED verdict. Use before release-branch to gate merges on traceability."
-# story: e38s06
-# story: e45s32
+<!-- story: e38s06 -->
+<!-- story: e45s32 -->
 model: haiku
 effort: light
 ---

package/skills/kickoff-branch/SKILL.md

@@ -5,9 +5,9 @@ effort: standard
 description: Create an isolated Git worktree/branch or Jujutsu workspace, then verify a clean test baseline before code. Use when starting a feature or task.
 ---
 
-# story: e51s03
-# story: e20s03
-# story: e82s02
+<!-- story: e51s03 -->
+<!-- story: e20s03 -->
+<!-- story: e82s02 -->
 
 
 # Kickoff Branch

package/skills/maintain-wiki/SKILL.md

@@ -3,7 +3,7 @@ name: maintain-wiki
 model: haiku
 effort: light
 description: "Agent-maintained OKF wiki — INGEST source docs, LINT for issues, QUERY across concept pages. Run as part of build-epic Step 8 and verify-work Phase 3."
-# story: e39s07
+<!-- story: e39s07 -->
 ---
 
 # Maintain Wiki

package/skills/migrate-spec/SKILL.md

@@ -4,12 +4,12 @@ model: sonnet
 effort: standard
 description: Detect GSD, spec-kit, or BMAD spec artifacts and transform them into bigpowers YAML layout (state.yaml, release-plan.yaml, epics/, requirements/, plans/, ADRs). Use when migrating foreign spec docs.
 ---
-# story: e25s01
-# story: e25s02
-# story: e25s03
-# story: e25s04
-# story: e25s05
-# story: e25s06
+<!-- story: e25s01 -->
+<!-- story: e25s02 -->
+<!-- story: e25s03 -->
+<!-- story: e25s04 -->
+<!-- story: e25s05 -->
+<!-- story: e25s06 -->
 
 # Migrate Spec
 

package/skills/plan-work/SKILL.md

@@ -1,16 +1,16 @@
 ---
-# story: e45s04
-# story: e45s06
-# story: e45s09
-# story: e45s33
-# story: e45s35
+<!-- story: e45s04 -->
+<!-- story: e45s06 -->
+<!-- story: e45s09 -->
+<!-- story: e45s33 -->
+<!-- story: e45s35 -->
 name: plan-work
 model: opus
 effort: standard
 description: "PLANNING SPINE STEP 3 of 3 — Plan the work: write detailed implementation tasks into the active epic capsule (specs/epics/eNN-slug/). Produces countable-story-format .md specs and runnable -tasks.yaml files. Use after slice-tasks (step 2). Not a substitute for scope-work (step 1) or slice-tasks (step 2)."
 ---
 
-# story: e45s29
+<!-- story: e45s29 -->
 
 # Plan Work
 

package/skills/quick-fix/SKILL.md

@@ -1,5 +1,5 @@
 ---
-# story: e51s04
+<!-- story: e51s04 -->
 name: quick-fix
 description: "Streamlined fast-path for trivial data-only fixes — no TDD, no branching ceremony. Collapses 6 skills into 2 for changes that are purely data with no logic risk. Aborts with fallback to investigate-bug if guardrails trigger."
 model: sonnet

package/skills/release-branch/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: release-branch
-# story: e14s01 e15s03
+<!-- story: e14s01 e15s03 -->
 model: haiku
 effort: standard
 description: Make the merge/PR/keep/discard decision for a feature branch, verify coverage gates, create the PR with gh, and clean up the worktree. Use when a feature is done and ready to ship, or when user says "release", "merge", or "open a PR".

package/skills/request-review/SKILL.md

@@ -1,19 +1,30 @@
 ---
-# story: e45s07
-# story: e45s07
-# story: e45s17
+<!-- story: e45s07 -->
+<!-- story: e45s07 -->
+<!-- story: e45s17 -->
 name: request-review
 model: opus
 effort: standard
 description: Dispatch a fresh reviewer agent with a clean context to critique the code after audit-code passes. The reviewer has no shared state with the coding agent and gives a genuine second opinion. Use after audit-code passes, before committing, or when user wants an independent code review.
 ---
 
-# story: e45s28
+<!-- story: e45s28 -->
 
 # Request Review
 
 Dispatch fresh reviewer agents with clean contexts. Reviewers have no shared state — they find what the coding agent missed.
 
+## Target (argument)
+
+If an argument was passed after `/request-review` (e.g. `/request-review abc1234` or `/request-review HEAD~3..HEAD`), use it as the diff target when building the reviewer brief:
+
+```bash
+git diff <arg>        # range: abc..def, HEAD~3..HEAD
+git show <arg>        # single commit: abc1234
+```
+
+If no argument was given, review uncommitted working-tree changes.
+
 **Distinct from `audit-code`:** `audit-code` is self-review (internal). This skill dispatches external agents.
 
 **Solo developer note:** Reviewer agents replace the human reviewer.

package/skills/research-first/SKILL.md

@@ -5,8 +5,8 @@ model: sonnet
 effort: standard
 ---
 
-# story: e03s01
-# story: e21s02
+<!-- story: e03s01 -->
+<!-- story: e21s02 -->
 
 # Research First
 

package/skills/run-benchmark/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: run-benchmark
-# story: e45s01
+<!-- story: e45s01 -->
 model: haiku
 effort: standard
 description: Run skill quality benchmarks from specs/benchmarks/ definitions — N-run with/without-skill delta grading, train/validation split, pass@k + benchmark.json reports. Use before and after evolve-skill to prove quality changes are improvements, not regressions.
-# story: e23s02
+<!-- story: e23s02 -->
 ---
 
 # Run Benchmark

package/skills/run-evals/SKILL.md

@@ -1,5 +1,5 @@
 ---
-# story: e45s37
+<!-- story: e45s37 -->
 name: run-evals
 description: Eval-Driven Development — define capability and regression evals before building; code graders use verify commands, model graders use explicit rubrics; log pass@k. Use before develop-tdd on new features, or when measuring agent capability over runs.
 model: sonnet

package/skills/run-planning/SKILL.md

@@ -4,7 +4,7 @@ model: sonnet
 effort: standard
 description: "DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (specs/planning-status.yaml) through survey-context → scope-work → research-first → elaborate-spec → plan-release → slice-tasks. NOT a duplicate of plan-work or the planning spine; it orchestrates the pre-coding discover phase only."
 ---
-# story: e24s03
+<!-- story: e24s03 -->
 
 # Run Planning
 

package/skills/scope-work/SKILL.md

@@ -5,8 +5,8 @@ model: sonnet
 effort: standard
 ---
 
-# story: e03s01
-# story: e24s02
+<!-- story: e03s01 -->
+<!-- story: e24s02 -->
 
 # Scope Work
 

package/skills/search-skills/SKILL.md

@@ -5,8 +5,8 @@ model: haiku
 effort: standard
 ---
 
-# story: e09s01
-# story: e21s01
+<!-- story: e09s01 -->
+<!-- story: e21s01 -->
 
 # Search Skills
 

package/skills/security-review/SKILL.md

@@ -10,16 +10,16 @@ description: >
   the user says "security review" or "scan for vulns".
 ---
 
-# story: e45s41
+<!-- story: e45s41 -->
 <!-- story: e45s18 -->
-# story: e26s01
-# story: e26s02
-# story: e26s03
-# story: e26s04
-# story: e26s05
-# story: e26s06
-# story: e26s07
-# story: e45s26
+<!-- story: e26s01 -->
+<!-- story: e26s02 -->
+<!-- story: e26s03 -->
+<!-- story: e26s04 -->
+<!-- story: e26s05 -->
+<!-- story: e26s06 -->
+<!-- story: e26s07 -->
+<!-- story: e45s26 -->
 
 # Security Review
 

package/skills/seed-conventions/SKILL.md

@@ -5,12 +5,12 @@ effort: standard
 description: Generate CLAUDE.md and CONVENTIONS.md for a brand-new project through a brief interview, and create the specs/ directory with evolved bigpowers structure (product/, tech-architecture/, verifications/, epics/archive/). Entry point for greenfield projects. Use when starting a new project from scratch, when user asks to set up AI agent conventions, or when there is no CLAUDE.md yet.
 ---
 
-# story: e10s01
-# story: e47s02
-# story: e10s02
-# story: e51s02
-# story: e45s21
-# story: e79s03
+<!-- story: e10s01 -->
+<!-- story: e47s02 -->
+<!-- story: e10s02 -->
+<!-- story: e51s02 -->
+<!-- story: e45s21 -->
+<!-- story: e79s03 -->
 
 
 # Seed Conventions

package/skills/session-state/SKILL.md

@@ -5,7 +5,7 @@ effort: standard
 description: Track implementation decisions and progress in specs/state.yaml to prevent context rot. Use at the start of a session to load context, and whenever a significant decision is made or a milestone is reached.
 ---
 
-# story: e45s23
+<!-- story: e45s23 -->
 
 # Session State
 > **HARD GATE** — **HARD GATE** — Session state must be synchronized with git state. If state.yaml conflicts with the working tree, halt and ask for clarification. Do NOT assume state is correct.

package/skills/slice-tasks/SKILL.md

@@ -5,7 +5,7 @@ model: sonnet
 effort: standard
 ---
 
-# story: e45s29
+<!-- story: e45s29 -->
 
 # Slice Tasks
 

package/skills/smoke-test/SKILL.md

@@ -1,5 +1,5 @@
 ---
-# story: e80s02
+<!-- story: e80s02 -->
 name: smoke-test
 phase: verify
 description: "Post-deploy health-check against a live URL. Validates HTTP status, response content, and critical endpoints. Runnable standalone OR as the final step of the deploy skill."

package/skills/stocktake-skills/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: stocktake-skills
-# story: e18s05
+<!-- story: e18s05 -->
 description: Sequential subagent batch audit of the bigpowers skill catalog — Quick Scan (changed only) or Full (all skills). Use during sustain phase, before a major release, or when catalog drift is suspected.
-# story: e22s02
+<!-- story: e22s02 -->
 model: sonnet
 effort: standard
 ---
 
-# story: e09s01
+<!-- story: e09s01 -->
 <!-- story: e45s12 -->
 <!-- story: e79s04 -->
 

package/skills/survey-context/SKILL.md

@@ -5,7 +5,7 @@ effort: standard
 description: Per-task context bootstrap — reads existing specs/ and tech-architecture docs to map the current lifecycle phase and suggest the next skill. Use at the start of any task, when returning after a break, or when unsure what to do next. For deriving a tech-stack doc from scratch, use map-codebase first.
 ---
 
-# story: e82s02
+<!-- story: e82s02 -->
 
 # Survey Context
 

package/skills/validate-contracts/SKILL.md

@@ -1,5 +1,5 @@
 ---
-# story: e80s02
+<!-- story: e80s02 -->
 name: validate-contracts
 phase: verify
 description: "Assert data shape consistency across system boundaries — live API responses against JSON Schema, key-set comparison across layers, data shape validation for migrations and exports. Catches silent data corruption before deploy."

package/skills/validate-fix/SKILL.md

@@ -1,7 +1,7 @@
 ---
-# story: e80s01
-# story: e80s04
-# story: e45s08
+<!-- story: e80s01 -->
+<!-- story: e80s04 -->
+<!-- story: e45s08 -->
 name: validate-fix
 model: haiku
 effort: standard