peaks-loop 4.0.50 → 4.0.52

package/skills/peaks-code/references/startup-sequence.md

@@ -11,23 +11,23 @@ description: peaks-code startup sequence Steps 0 / 0.5-0.87 / 1 / 2 / 2.3 / 2.5
 
 ### Peaks-Loop Slice 011 — workspace consolidate + session checkpoint/resume
 
-`peaks workspace consolidate` is the slice-011 umbrella primitive. `peaks session checkpoint` (context-overflow defense) and `peaks session resume` surface as Step 0.75 + Step N. See `references/cross-date-session-check.md`.
+`peaks workspace consolidate` is the slice-011 umbrella primitive. `peaks session checkpoint` (context-overflow defense) and `peaks session resume` surface as Step 0.75 + Step N. See `cross-date-session-check.md`.
 
 ### Peaks-Loop Step 0.75: Resume from checkpoint (BLOCKING on same-day re-invocation)
 
-When a NEW conversation opens on a session whose `lastActivity` is from today AND `.peaks/_runtime/<sessionId>/checkpoints/` has `*.json`, surface via `peaks session info --active --json` + `peaks session resume --from <path> --project <repo>`. Prompt via `AskUserQuestion` (resume / fresh); if "resume", prepend the block. Step 0.75 is no-op on precondition fail. See `references/checkpoint-resume.md`.
+When a NEW conversation opens on a session whose `lastActivity` is from today AND `.peaks/_runtime/<sessionId>/checkpoints/` has `*.json`, surface via `peaks session info --active --json` + `peaks session resume --from <path> --project <repo>`. Prompt via `AskUserQuestion` (resume / fresh); if "resume", prepend the block. Step 0.75 is no-op on precondition fail. See `checkpoint-resume.md`.
 
 ### Peaks-Loop Step N: Periodic checkpoint (auto-fire, no user action)
 
-Proactive context-overflow defense. CLI: `peaks session checkpoint [--reason <r>] [...flags]`. Fire `--reason periodic` every 20 tool calls (G1 hard-coded), `--reason artifact-written` per PRD/RD/QA/TXT write. See `references/periodic-checkpoint.md` (otherwise `tests/unit/code/checkpoint-periodic-frequency.test.ts` fails).
+Proactive context-overflow defense. CLI: `peaks session checkpoint [--reason <r>] [...flags]`. Fire `--reason periodic` every 20 tool calls (G1 hard-coded), `--reason artifact-written` per PRD/RD/QA/TXT write. See `periodic-checkpoint.md` (no guard fails on a missed cadence — the test that did was deleted in `f17aa377`).
 
 ### Peaks-Loop Step 0.6: Audit + Goal (NEW)
 
-Invoke peaks-audit after need expressed; store approved goal at `.peaks/_runtime/<sessionId>/audit-goal/<rid>.json`. **All autonomous work requires approved goal.** → `references/audit-goal-gate.md`.
+Invoke peaks-audit after need expressed; store approved goal at `.peaks/_runtime/<sessionId>/audit-goal/<rid>.json`. **All autonomous work requires approved goal.** → `skills/peaks-audit/SKILL.md`.
 
 ### Peaks-Loop Step N+1: Final Review (NEW)
 
-After autonomous work (RD, QA, security, perf), invoke peaks-final-review for 4-dim evidence. All 4 pass → final delivery; else loop back. See `references/final-review-gate.md`.
+After autonomous work (RD, QA, security, perf), invoke peaks-final-review for 4-dim evidence. All 4 pass → final delivery; else loop back. See `skills/peaks-final-review/SKILL.md`.
 
 ### Peaks-Loop Step N+2: Main-session context monitor (D6 + slice 2026-07-02)
 
@@ -37,21 +37,21 @@ After every 4th tool call, probe via `peaks code context-now --project <repo> --
 
 Run `peaks workspace init` + `peaks skill presence:set peaks-code` BEFORE any analysis, role handoff, or mode-selection question. Even "分析下这个项目" / "看一下代码" / one-line questions anchor first.
 
-→ see `references/anchoring-and-session-info.md` for the full Step 0 contract + session-conflict resolution.
+→ see `anchoring-and-session-info.md` for the full Step 0 contract + session-conflict resolution.
 
 #### Step 0 bypass — Claude Code [Fact-Forcing Gate] (slice 2.0.1-bug3)
 
 `peaks workspace init` materializes `.claude/settings.local.json` (a PreToolUse hook allow-list for `.peaks/**` paths and `peaks <subcommand>` Bash) so the [Fact-Forcing Gate] does not block Step 0. Pass `--no-claude-hooks` to opt out.
 
-→ see `references/anchoring-and-session-info.md` for the full bypass contract, recovery flow, and anti-bail-out rule.
+→ see `anchoring-and-session-info.md` for the full bypass contract, recovery flow, and anti-bail-out rule.
 
 ### Peaks-Loop Step 0.7: Detect unfinished work and offer resume (BLOCKING on first invocation per session)
 
-After Step 0, run the resume-detection probe; surface via `AskUserQuestion` if a slice is in flight. **v3.1.2 resume rule:** if `.peaks/_runtime/<sessionId>/job/<jid>/progress.json` exists, read FIRST and surface `Next: slice #N of M`. **v2.11.0 D7 override:** if user just `/compact`ed, run `peaks code post-compact-detect --project <repo> --json` FIRST; `shouldAutoResume: true` skips AskUserQuestion. → `references/resume-detection.md`.
+After Step 0, run the resume-detection probe; surface via `AskUserQuestion` if a slice is in flight. **v3.1.2 resume rule:** if `.peaks/_runtime/<sessionId>/job/<jid>/progress.json` exists, read FIRST and surface `Next: slice #N of M`. **v2.11.0 D7 override:** if user just `/compact`ed, run `peaks code post-compact-detect --project <repo> --json` FIRST; `shouldAutoResume: true` skips AskUserQuestion. → `resume-detection.md`.
 
 ### Peaks-Loop Step 0.55: 1.x → 2.0 detection (BLOCKING on first invocation per session, when the project is not on a 2.0 layout)
 
-After Step 0.7 returns "fresh", run `peaks upgrade --detect-1x --project <root> --json`. If `isOneX: true`, surface `AskUserQuestion`. → `references/step-0-55-1x-detection.md`.
+After Step 0.7 returns "fresh", run `peaks upgrade --detect-1x --project <root> --json`. If `isOneX: true`, surface `AskUserQuestion`. → `step-0-55-1x-detection.md`.
 
 ### Peaks-Loop Step 0.8 — Job 启动 (BLOCKING on LLM judgement — v3.1.1 patch + v3.1.2 mechanical gates)
 
@@ -65,7 +65,7 @@ The CLI is a **recorder + gate** for job-shape (the LLM judges). LLM calls `peak
 
 **v3.1.2 mechanical gates** (recorder-only was bypassed twice):
 
-PreToolUse hook on `peaks code gate-step-08`; size-fear ban on `peaks code emit-handoff`; forced auto-compact from ≥ 0.80 (`auto-fire`, every mode); on-disk slice progress via `peaks job checkpoint` (canonical reader `peaks job progress --job-id <jid>`). Full mechanics (judgement criteria, hook table, backup-regex rationale, hook wiring) at `references/step-0-8-gate.md`.
+PreToolUse hook on `peaks code gate-step-08`; size-fear ban on `peaks code emit-handoff`; forced auto-compact from ≥ 0.80 (`auto-fire`, every mode); on-disk slice progress via `peaks job checkpoint` (canonical reader `peaks job progress --job-id <jid>`). Full mechanics (judgement criteria, hook table, backup-regex rationale, hook wiring) at `step-0-8-gate.md`.
 
 ### Peaks-Loop Step 0.81 — per-slice 收尾
 
@@ -83,23 +83,23 @@ Active in rotating mode; fires every `rotateEvery` slices or via `peaks job rota
 
 After every `peaks sub-agent dispatch --batch-id <id>` inside a Job, BEFORE next slice checkpoint: `peaks job subagent-cleanup --job-id <jid> --batch-id <id> --force`. Non-zero → block.
 
-→ see `references/job-loop.md` for state machine, visibility, rotation cadence, cross-day recovery, 9 red lines.
+→ see `job-loop.md` for state machine, visibility, rotation cadence, cross-day recovery, 9 red lines.
 
 ### Peaks-Loop Step 1: Mode selection
 
-Use `AskUserQuestion` with `Full auto (Recommended)` first when user did not name a profile OR skill presence is stale (run `peaks skill presence:check-stale --project <path> --json` first; `stale: true` ⇒ re-ask). → `references/mode-selection.md`, `references/fast-mode.md`, `references/mode-selection-with-stale-presence.md`.
+Use `AskUserQuestion` with `Full auto (Recommended)` first when user did not name a profile OR skill presence is stale (run `peaks skill presence:check-stale --project <path> --json` first; `stale: true` ⇒ re-ask). → `mode-selection.md`, `fast-mode.md`, `mode-selection-with-stale-presence.md`.
 
 ### Peaks-Loop Step 2: Re-set skill presence with the chosen mode
 
-Re-run `peaks skill presence:set peaks-code --mode <mode-value> --gate startup`. Install statusline on first run (`peaks statusline install`). → `references/skill-presence-and-title.md`.
+Re-run `peaks skill presence:set peaks-code --mode <mode-value> --gate startup`. Install statusline on first run (`peaks statusline install`). → `skill-presence-and-title.md`.
 
 ### Peaks-Loop Step 2.3: Load project memory (durable, LLM-authored memories)
 
-Run `peaks project memories --project <repo> --json` to read decisions / conventions / modules / rules / lessons from `.peaks/memory`. → `references/project-memory-loading.md`.
+Run `peaks project memories --project <repo> --json` to read decisions / conventions / modules / rules / lessons from `.peaks/memory`. → `project-memory-loading.md`.
 
 ### Peaks-Loop Step 2.5: Set session title
 
-Extract a short title from the user's first request (8-20 Chinese chars or 4-10 English words). Run `peaks session title <sessionId> "<title>" --json`. Skip if a title is already set. → `references/skill-presence-and-title.md` (same file as Step 2). D-002: sid is positional, NOT `--session-id` flag (rejected with `error: unknown option`).
+Extract a short title from the user's first request (8-20 Chinese chars or 4-10 English words). Run `peaks session title <sessionId> "<title>" --json`. Skip if a title is already set. → `skill-presence-and-title.md` (same file as Step 2). D-002: sid is positional, NOT `--session-id` flag (rejected with `error: unknown option`).
 
 ## Sub-agent session sharing (MANDATORY — one conversation = one sid)
 
@@ -107,4 +107,4 @@ When peaks-code dispatches a sub-agent (peaks-rd, peaks-qa, peaks-ui, peaks-txt,
 
 ## Boundaries
 
-Peaks-Loop Code may identify scenarios, recommend profiles, coordinate role skills via artifacts, coordinate project memory extraction, request user confirmation at risk/commit boundaries. MUST NOT silently install hooks / create agents / enable MCP / modify Claude settings / create GitHub repos / bypass role-skill artifacts. → `references/boundaries.md`.
+Peaks-Loop Code may identify scenarios, recommend profiles, coordinate role skills via artifacts, coordinate project memory extraction, request user confirmation at risk/commit boundaries. MUST NOT silently install hooks / create agents / enable MCP / modify Claude settings / create GitHub repos / bypass role-skill artifacts. → `boundaries.md`.

package/skills/peaks-code/references/step-11-memory-sediment.md

@@ -41,7 +41,7 @@ peaks memory extract --project <repo> --artifact .peaks/_runtime/<sessionId>/txt
 
 `--apply` is REQUIRED (without it the command only previews — no files land).
 
-> **CLI reality check (D-010 sediment, 2026-07-09):** The `<!-- peaks-memory:start -->` block must be followed immediately by a **YAML frontmatter** (`title: ...`, `kind: lesson | decision | convention`) and a `---` separator. Each block must close with `<!-- peaks-memory:end -->`. A bare `peaks-memory:start` without the YAML fields is parsed but produces no `plannedWrites` — the CLI silently returns `extractedCount: 0`.
+> **CLI reality check (D-010 sediment, 2026-07-09; warnings added 2026-09-17):** The `<!-- peaks-memory:start -->` block must be followed immediately by a **YAML frontmatter** (`title: ...`, `kind: lesson | decision | convention`) and a `---` separator. Each block must close with `<!-- peaks-memory:end -->`. A marker whose body lacks those fields produces no `plannedWrites`, so `extractedCount` stays 0 — and the CLI now says why: the rejected block is named, with the failed precondition, in the envelope's `warnings[]`. The same channel catches a marker that is not the exact literal (e.g. a `kind=…` written inside it), which `warnings` reports as "… is not the exact marker …". Read `warnings` before treating `extractedCount: 0` as "there was no block" — but note the warning reports the loss, it does not recover it: fix the marker and re-run.
 
 ### 11d — Gate C (zero-write outcome)
 
@@ -87,5 +87,5 @@ The artifact-scoped extract is canonical; the batch-scoped sibling is for non-ha
 
 ## Related
 
-- `references/runbook.md` §Step 11 — full bash + flow.
-- `references/project-memory-loading.md` — Step 2.3 memory loading (read-side).
+- `runbook.md` §Step 11 — full bash + flow.
+- `project-memory-loading.md` — Step 2.3 memory loading (read-side).

package/skills/peaks-code/references/sub-agent-dispatch.md

@@ -315,9 +315,10 @@ reply. The two surfaces are not redundant — the field is for
 downstream tooling, the prose is for the human. Same payload,
 different readers.
 
-**Regression guard**: `tests/unit/dispatch/dispatch-fanout-mandatory.test.ts`
-parses the same SKILL.md text and asserts the G11.5 paragraph is
-present; do not delete the heading without also updating the guard.
+**Regression guard**: none. The unit test that parsed the same SKILL.md
+text and asserted the G11.5 paragraph is present was deleted in
+`f17aa377`; do not delete the heading — convention is the only thing
+holding it now.
 
 ---
 
@@ -379,7 +380,7 @@ When writing a SKILL.md that fans out sub-agents:
 - `.peaks/memory/sub-agent-resource-lifecycle-red-line.md` (G5 red line)
 - `.peaks/memory/sub-agent-heartbeat-progress-red-line.md` (G6 red line)
 - `skills/peaks-code/references/swarm-dispatch-contract.md` (predecessor contract)
-- `skills/peaks-qa/references/qa-fanout-contract.md` (QA-specific fan-out)
+- `skills/bee/peaks-qa/references/qa-fanout-contract.md` (QA-specific fan-out)
 
 ---
 
@@ -404,7 +405,7 @@ peaks sub-agent dispatch <role> \
 
 Then the LLM takes `data.toolCall` from the envelope (a `{name, args}` descriptor), looks up the tool by `name` in its environment, and invokes it with `args` — IDE-private, no SKILL.md hardcoding.
 
-The role's required artefact paths (also see peaks-ui/rd/qa SKILL.md and `references/swarm-dispatch-contract.md`):
+The role's required artefact paths (also see peaks-ui/rd/qa SKILL.md and `swarm-dispatch-contract.md`):
 
 | Role | Writes | Reads (PRD-side) |
 |---|---|---|
@@ -433,7 +434,7 @@ The role's required artefact paths (also see peaks-ui/rd/qa SKILL.md and `refere
       `verdict: blocked-by-orchestrator-policy` and explain. Do NOT commit
       yourself even in emergencies.
     ```
-- **Do write heartbeats** — call `peaks sub-agent heartbeat --record <dispatchRecordPath> --status running --progress <pct> --note "<text>"` at least every 30s (see `references/sub-agent-dispatch.md` §G6 for the full contract). The parent Dispatcher uses these to render the live status line during the wait.
+- **Do write heartbeats** — call `peaks sub-agent heartbeat --record <dispatchRecordPath> --status running --progress <pct> --note "<text>"` at least every 30s (see `sub-agent-dispatch.md` §G6 for the full contract). The parent Dispatcher uses these to render the live status line during the wait.
 
 After every sub-agent dispatch returns, Code **restores presence** once (not per-agent), then continues to Gate B verification:
 

package/skills/peaks-code/references/swarm-dispatch-contract.md

@@ -15,7 +15,7 @@
 > rules. As of 2.8.4 the `'serial'` opt-out was removed by user
 > direction — single-sub-agent dispatch is no longer permitted when
 > ≥ 2 leaves exist at one topological level (see
-> `references/fanout-mandatory.md`).
+> `fanout-mandatory.md`).
 
 The Swarm phase is the **default** for any DAG with ≥ 2 leaves at
 the same topological level. Code derives the fan-out set from the

package/skills/peaks-code/references/workflow-gates-and-types.md

@@ -2,11 +2,11 @@
 
 > **Maintenance**: This reference holds the canonical contract for (a) how Code sequences the 11 workflow steps, (b) which `--type` to pass to `peaks request init` for which slice shape, and (c) the executable `ls` / `grep` gate commands that physically block progression. SKILL.md keeps the narrative ("what peaks-code does"); this file keeps the contract.
 >
-> **Why extracted from SKILL.md**: this content is 165 lines of mostly-tabular + bash-block contract — reference data, not orchestration prose. Inlining it bloats SKILL.md past the 800-line cap (per `common/coding-style.md`). The numbers, gate command shapes, and type-classification rules change rarely; the SKILL.md prose around them (orchestration flow, repair-loop intent, swarm fan-out shape) changes more often.
+> **Why extracted from SKILL.md**: this content is 165 lines of mostly-tabular + bash-block contract — reference data, not orchestration prose. Inlining it bloats SKILL.md past the 800-line cap (per `.peaks/standards/common/coding-style.md`). The numbers, gate command shapes, and type-classification rules change rarely; the SKILL.md prose around them (orchestration flow, repair-loop intent, swarm fan-out shape) changes more often.
 >
 > **How peaks-loop tooling reads this file**:
 > - `peaks skill runbook peaks-code` (CLI) and the in-line LLM reading the SKILL.md should reference this file when the gate-machine or type-classification contract is in play.
-> - The test `tests/unit/skill-default-runbook.test.ts` does NOT check this file (it only checks the runbook). Future tests can add a similar fallback for the gates-and-types contract.
+> - No test reads this file, so nothing detects drift between it and the SKILL.md prose. The test that once checked the runbook fallback was deleted in `f17aa377`.
 
 ## Peaks-Loop Request type classification (MANDATORY before `peaks request init`)
 
@@ -30,7 +30,7 @@ When Peaks-Loop Code coordinates development in a code repository, keep this ord
 0. **Peaks-Loop Snapshot** — `peaks doctor` + `peaks project dashboard` to capture baseline state before anything else;
 0.5. **Peaks-Loop Workspace initialization** — `.peaks/_runtime/<session-id>/` created, directory structure verified;
 0.6. **Peaks-Loop Project scan** — archetype, component library, CSS framework, build tool, state management, routing, data fetching, legacy signals detected and recorded to `.peaks/project-scan/project-scan.md`;
-0.7. **Peaks-Loop Existing-system extraction** (MANDATORY when archetype ∈ {legacy-frontend, legacy-fullstack, frontend-monorepo}; SKIP for greenfield) — extract visual tokens and code conventions from the live codebase to `.peaks/_runtime/<session-id>/system/existing-system.md`. The path lives under `system/` (not `ui/`) because the file also records non-UI conventions (service-layer signatures, hooks, naming) that backend-only or legacy-fullstack work consumes. See `references/existing-system-extraction.md`. UI design-draft and RD implementation MUST treat the extracted tokens and conventions as hard constraints;
+0.7. **Peaks-Loop Existing-system extraction** (MANDATORY when archetype ∈ {legacy-frontend, legacy-fullstack, frontend-monorepo}; SKIP for greenfield) — extract visual tokens and code conventions from the live codebase to `.peaks/_runtime/<session-id>/system/existing-system.md`. The path lives under `system/` (not `ui/`) because the file also records non-UI conventions (service-layer signatures, hooks, naming) that backend-only or legacy-fullstack work consumes. See `existing-system-extraction.md`. UI design-draft and RD implementation MUST treat the extracted tokens and conventions as hard constraints;
 1. **Peaks-Loop Standards preflight** — `peaks standards init/update --dry-run`, must reference concrete project-scan findings (never emit generic templates);
 2. **Peaks-Loop PRD phase** — capture request as canonical artifact, extract scope and acceptance criteria:
    - Full-auto/Swarm: auto-transition to `confirmed-by-user` once the artifact is complete;

package/skills/peaks-code/references/worktree-governance.md

@@ -23,7 +23,7 @@ The 3 layers stack. L3 is the strongest because it operates BELOW the LLM's tool
 ## L1 — Sub-agent system prompt
 
 The explicit `MUST NOT` block lives in:
-- `peaks-rd/references/rd-sub-agent-dispatch.md`
+- `../../bee/peaks-rd/references/rd-sub-agent-dispatch.md`
 - `peaks-qa/...`
 - `peaks-ui/...`
 - `peaks sub-agent dispatch` CLI prompt template

package/skills/peaks-final-review/SKILL.md

@@ -41,7 +41,7 @@ denied again after a long pause. That is the gate resetting, not you regressing.
 
 > **Read once at the top of this file; the rest of the skill is written against it.**
 
-The `.peaks/` workspace is partitioned by a **single scope axis** (session-id, at `.peaks/_runtime/<sessionId>/...`) with a nested **sub-agent axis** under `.peaks/_sub_agents/<sessionId>/...`. Use `<sessionId>` placeholders (NEVER bare `<sid>`). The peaks-loop change-id axis was removed in slice `2026-06-29-change-id-root-removal`; reviewable artifacts now live under `.peaks/_runtime/<sessionId>/<role>/...` only. OpenSpec's independent `openspec/changes/<change-id>/` vocabulary (L4) is preserved untouched. CLI mapping: session-id → `peaks session *`; sub-agent → `peaks sub-agent *`. Regression test `tests/unit/skills/skills-skill-md-naming.test.ts` enforces (a) zero bare `<sid>`, (b) every `.peaks/_runtime/<X>/` has an axis label, (c) this callout is present.
+The `.peaks/` workspace is partitioned by a **single scope axis** (session-id, at `.peaks/_runtime/<sessionId>/...`) with a nested **sub-agent axis** under `.peaks/_sub_agents/<sessionId>/...`. Use `<sessionId>` placeholders (NEVER bare `<sid>`). The peaks-loop change-id axis was removed in slice `2026-06-29-change-id-root-removal`; reviewable artifacts now live under `.peaks/_runtime/<sessionId>/<role>/...` only. OpenSpec's independent `openspec/changes/<change-id>/` vocabulary (L4) is preserved untouched. CLI mapping: session-id → `peaks session *`; sub-agent → `peaks sub-agent *`. Normative by documentation only — the guard that once asserted (a) zero bare `<sid>`, (b) an axis label on every runtime path, and (c) this callout's presence was deleted in `457b9a87`. Comply by convention.
 
 # Peaks-Loop Final Review
 
@@ -80,7 +80,7 @@ The service is the **gate primitive** that closes the 10% human / 90% LLM loop.
 All of the following MUST be true before invoking this skill:
 
 - **RD complete** — implementation merged and the slice boundary recorded at `.peaks/sc/slice-decomposition/<rid>.json` (or `peaks slice check --rid <rid> --json` returns `pass`).
-- **QA complete** — `test-cases` + `test-reports` + `security-findings` + `performance-findings` present under `.peaks/_runtime/<sessionId>/qa/...` and all applicable gates A/A2/A3/A4/B/C/E/F satisfied (per `skills/peaks-qa/references/qa-transition-gates.md`).
+- **QA complete** — `test-cases` + `test-reports` + `security-findings` + `performance-findings` present under `.peaks/_runtime/<sessionId>/qa/...` and all applicable gates A/A2/A3/A4/B/C/E/F satisfied (per `skills/bee/peaks-qa/references/qa-transition-gates.md`).
 - **Security check complete** — slice 025 project-level security test plan executed; no open CRITICAL/HIGH findings.
 - **Performance baseline complete** — slice 025 project-level perf baseline recorded; no regression beyond the agreed threshold.
 - **Approved audit-goal on disk** — `.peaks/_runtime/<sessionId>/audit-goal/<rid>.json` exists and contains `successCriteria` (the service feeds these into the LLM user prompt verbatim).
@@ -231,5 +231,5 @@ When handing off, emit: rid, `allPass`, `needsAttention[]`, output path, source
 | `src/services/audit/audit-goal-service.ts:16` | Line of evidence that `LlmRunner` is reusable across audit + final-review (service-level integration). |
 | `tests/unit/final-review/final-review-service.test.ts` | Service-level unit tests (8 cases: evidence inlining, the no-evidence⇒no-`pass` gate, prompt bounds, plus contract guards). |
 | `docs/superpowers/plans/2026-06-25-slice-topology-multipass-phase-4.md:127` | Phase-4 plan prose (Task 14). |
-| `skills/peaks-qa/SKILL.md` | Upstream QA skill — 4-dim review is downstream of all QA gates. |
+| `skills/bee/peaks-qa/SKILL.md` | Upstream QA skill — 4-dim review is downstream of all QA gates. |
 | `skills/peaks-audit/SKILL.md` | Sibling skill — produces the `audit-goal` JSON that this skill consumes. |

package/skills/peaks-ide/references/audit-log-helper.md

@@ -44,9 +44,10 @@ node scripts/peaks-ide-audit-log.mjs --project <repo> --event <name> --adapter <
 The log file path is `<projectRoot>/.peaks/audit/peaks-ide-<UTC-date>.log`
 and is gitignored per the repo root `.gitignore` (`.peaks/audit/`).
 
-## Contract pinned by tests
+## Contract
 
-`tests/unit/skills/peaks-ide/audit-log-helper.test.ts` pins 4 sub-cases
-(per AC-5): helper is at the documented path, write emits one JSONL line
-with `timestamp + event + adapter + ok`, the log path is in `.gitignore`,
+No test pins this — the suite that asserted the 4 sub-cases below (per
+AC-5) was deleted in `f17aa377`. They remain the contract: helper is at
+the documented path, write emits one JSONL line with
+`timestamp + event + adapter + ok`, the log path is in `.gitignore`,
 and `--dry-run` returns the would-be line without writing.

package/skills/peaks-resume/SKILL.md

@@ -110,6 +110,6 @@ Then tell the user: "Resuming from `<gate>`. The main peaks-code skill will take
 
 ## Cross-references
 
-- The detection logic is canonical at `tests/fixtures/skill-resume-mode-detect.sh` (added in slice 003). The 8 vitest cases in `tests/unit/skill-resume-mode.test.ts` cover all classification outcomes.
+- The detection logic is canonical at `tests/fixtures/skill-resume-mode-detect.sh` (added in slice 003). Nothing covers the classification outcomes in unit tests today — the 8-case suite was deleted in `f17aa377`.
 - The SKILL.md prose at `skills/peaks-code/SKILL.md` Step 0.7 (added in slice 003) is the same logic, written for LLM consumption. This wrapper reuses the same script — there is no parallel implementation.
 - The "drives a CLI on the user's behalf" pattern (mirror of `peaks-sop`) is the closest existing precedent for this wrapper.

package/skills/peaks-slice-decompose/SKILL.md

@@ -41,7 +41,7 @@ denied again after a long pause. That is the gate resetting, not you regressing.
 
 > **Read once at the top of this file; the rest of the skill is written against it.**
 
-The `.peaks/` workspace is partitioned by a **single scope axis** (session-id, at `.peaks/_runtime/<sessionId>/...`) with a nested **sub-agent axis** under `.peaks/_sub_agents/<sessionId>/...`. Use `<sessionId>` placeholders (NEVER bare `<sid>`). The peaks-loop change-id axis was removed in slice `2026-06-29-change-id-root-removal`; reviewable artifacts now live under `.peaks/_runtime/<sessionId>/<role>/...` only. OpenSpec's independent `openspec/changes/<change-id>/` vocabulary (L4) is preserved untouched. CLI mapping: session-id → `peaks session *`; sub-agent → `peaks sub-agent *`. Regression test `tests/unit/skills/skills-skill-md-naming.test.ts` enforces (a) zero bare `<sid>`, (b) every `.peaks/_runtime/<X>/` has an axis label, (c) this callout is present.
+The `.peaks/` workspace is partitioned by a **single scope axis** (session-id, at `.peaks/_runtime/<sessionId>/...`) with a nested **sub-agent axis** under `.peaks/_sub_agents/<sessionId>/...`. Use `<sessionId>` placeholders (NEVER bare `<sid>`). The peaks-loop change-id axis was removed in slice `2026-06-29-change-id-root-removal`; reviewable artifacts now live under `.peaks/_runtime/<sessionId>/<role>/...` only. OpenSpec's independent `openspec/changes/<change-id>/` vocabulary (L4) is preserved untouched. CLI mapping: session-id → `peaks session *`; sub-agent → `peaks sub-agent *`. Normative by documentation only — the guard that once asserted (a) zero bare `<sid>`, (b) an axis label on every runtime path, and (c) this callout's presence was deleted in `457b9a87`. Comply by convention.
 
 ## Read via `SchemaRouter.readResult()` — never parse the file directly
 
@@ -164,7 +164,7 @@ Why: RID-003 SC §3.5 originally specified the CJS guard for `scripts/install-sk
 
 ### Rule 2 — Whitelist fixture sync is NOT collateral (D-009a)
 
-When a slice adds a new entry to a **whitelist fixture** (e.g. `tests/unit/ide/ide-registry.test.ts` asserting `expect(adapters).toHaveLength(7)` after adding the 8th adapter), that fixture sync is a **primary task**, not a "by the way" footnote.
+When a slice adds a new entry to a **whitelist fixture** (a test that asserts an exact set size, e.g. `expect(adapters).toHaveLength(7)`, and must be bumped when the 8th adapter is added), that fixture sync is a **primary task**, not a "by the way" footnote.
 
 Mandatory structure for any slice that adds to a known set:
 
@@ -175,8 +175,8 @@ Mandatory structure for any slice that adds to a known set:
 |---|---|---|
 | T-1 | `src/services/ide/ide-types.ts` | Add `'zcode'` to IdeId |
 | T-2 | `src/services/ide/ide-registry.ts` | Register ZCODE_ADAPTER |
-| T-3 | `tests/unit/ide/ide-registry.test.ts` | Update whitelist: 7 → 8 adapters, add 'zcode' |
-| T-4 | `tests/unit/install-skills-script.test.ts` | Update whitelist: 5 → 6 platforms, add 'zcode' |
+| T-3 | the adapter-registry whitelist fixture | Update whitelist: 7 → 8 adapters, add 'zcode' |
+| T-4 | the install-skills platform whitelist fixture | Update whitelist: 5 → 6 platforms, add 'zcode' |
 ```
 
 If you find a whitelist fixture during execution but didn't pre-list it as a task, treat it as a **NEW TASK** and run the SC ↔ QA repair loop, not as "necessary collateral". Pre-listing prevents surprises at Gate 1.

package/skills/peaks-slice-decompose/references/cross-pass-edge-interpretation.md

@@ -1,6 +1,6 @@
 # Cross-pass edge interpretation
 
-Source of truth: `src/services/slice/cross-pass-edge-merger.ts` (`merge` function) + `src/services/slice/llm-arbitrator.ts` (`arbitrate`). Read this together with `references/v2-schema.md` for the field-level definitions.
+Source of truth: `src/services/slice/cross-pass-edge-merger.ts` (`merge` function) + `src/services/slice/llm-arbitrator.ts` (`arbitrate`). Read this together with `v2-schema.md` for the field-level definitions.
 
 ## What is a `CrossPassEdge`
 

package/skills/peaks-slice-decompose/references/granularity-decision.md

@@ -61,7 +61,7 @@ The function returns one of three branches:
 
 ### Tie-break behavior
 
-`auto` mode does NOT itself consult the LLM — the `'tie-break'` branch only signals that the workUnit is borderline. The actual LLM call happens during cross-pass edge detection in `cross-pass-edge-merger.ts` (see `references/cross-pass-edge-interpretation.md`). The merge step may add an `llm-arbitrated` edge even when the parent was subdivided as `'tie-break'`.
+`auto` mode does NOT itself consult the LLM — the `'tie-break'` branch only signals that the workUnit is borderline. The actual LLM call happens during cross-pass edge detection in `cross-pass-edge-merger.ts` (see `cross-pass-edge-interpretation.md`). The merge step may add an `llm-arbitrated` edge even when the parent was subdivided as `'tie-break'`.
 
 ## `auto` decision tree
 

package/skills/peaks-slice-decompose/references/v2-schema.md

@@ -76,7 +76,7 @@ The CLI serialises via `SchemaRouter.writeResult()` → `JSON.stringify(result,
 | `toPass` | `PassNumber` | The lower (finer) pass number. Always `fromPass < toPass`. |
 | `fromSliceId` | `string` | Slice id in `fromPass`. |
 | `toSliceId` | `string` | Slice id in `toPass`. |
-| `kind` | `CrossPassEdgeKind` (`'type-shares' \| 'fixture-shares' \| 'import-re-export' \| 'llm-arbitrated'`) | See `references/cross-pass-edge-interpretation.md`. |
+| `kind` | `CrossPassEdgeKind` (`'type-shares' \| 'fixture-shares' \| 'import-re-export' \| 'llm-arbitrated'`) | See `cross-pass-edge-interpretation.md`. |
 | `confidence` | `EdgeConfidence \| 'llm'` | `'llm'` only when `kind === 'llm-arbitrated'`. Structural detectors emit `'structural'`. |
 | `evidence` | `string` | Human-readable: the import line, the shared fixture id, or `llm:<callId>: <reason>` for LLM edges. |
 | `arbitratedBy` | `string \| null` | The `LlmArbitration.callId` that produced this edge, or `null` for static-detected edges. |
@@ -140,6 +140,6 @@ Any future schema change MUST:
 2. Extend `SchemaRouter.readResult()` to accept and dispatch it.
 3. Bump `DecompositionResultV3.schemaVersion: 'v3'`.
 4. Keep the v2 reader path intact (no in-place rewrite of v2 files).
-5. Update this reference + add a `references/v3-schema.md`.
+5. Update this reference + add a sibling v3 schema reference next to it.
 
 In-place edits to v1/v2 fields are forbidden: any consumer that already wrote a v2 file expects its schema to remain stable.

package/skills/peaks-solo/SKILL.md

@@ -247,6 +247,5 @@ peaks-solo 是 dispatcher,**不**是 orchestrator,**不**是 implementer。下
 - `references/triage-decision-table.md` — 关键词 → leaf skill 完整映射表(≥ 10 行)
 - `references/fallback-tool-inventory.md` — 自规划允许 + 禁止工具清单
 - `references/sediment-prompt-template.md` — 4-option AskUserQuestion 沉淀模板
-- spec: `docs/superpowers/specs/2026-07-08-peaks-solo-dispatcher-design.md` §3.1, §3.3, §3.4, §3.5
-- plan: `docs/superpowers/plans/2026-07-08-peaks-solo-dispatcher/s1-peaks-solo-skill.md`
+- spec / plan: the `2026-07-08-peaks-solo-dispatcher` design + plan docs were retired in `e6e35842`; the surviving record of that slice is `.peaks/memory/2026-07-08-peaks-solo-dogfood.md` and the decision memo below.
 - decision memo: `.peaks/memory/user-decision-2026-07-08-revive-peaks-solo-as-dispatcher.md`