peaks-loop 3.0.0

package/skills/peaks-rd/SKILL.md

@@ -0,0 +1,279 @@
+---
+name: peaks-rd
+description: Research and development skill for Peaks. Use for engineering analysis, refactor planning, project scanning, code standards, unit-test coverage gates, implementation contracts, task graphs, and RD handoffs. Always use this for Peaks-Cli refactor workflows.
+---
+
+## Single-scope-axis naming convention
+
+> **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 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 `openspec/changes/<change-id>/` vocabulary (L4) is preserved. CLI: session-id → `peaks session *`; sub-agent → `peaks sub-agent *`. Regression test enforces (a) zero bare `<sid>`, (b) every `.peaks/_runtime/<X>/` has an axis label, (c) this callout is present.
+
+## peaks-context auto-build (v3.0)
+
+RD workflow automatically runs `peaks context build --audience peaks-rd` before the LLM is invoked. No manual setup needed.
+
+## Karpathy enforcement (Slice 1/6 — karpathy prompt-injection-lift)
+
+> **Read once per RD invocation; RD is built around these 4 guidelines.**
+
+Every RD action (planning, implementation, sub-agent dispatch, fan-out) MUST align with the 4 Karpathy guidelines. The full text lives at `andrej-karpathy-skills:karpathy-guidelines` (reference material only — do not execute upstream / run installer / persist sensitive examples). RD sub-agents receive the full text via `references/rd-sub-agent-dispatch.md` (see "Karpathy-guidelines context"). The 4 guidelines are:
+
+1. **Think Before Coding** — surface assumptions, name tradeoffs, ask when unclear. State red-line scope in `## Red-line scope` before any code change.
+2. **Simplicity First** — minimum code that solves the problem. No speculative features, no abstractions for single-use code, no error handling for impossible scenarios. If 200 lines could be 50, rewrite it. The 800-line file cap and `peaks scan file-size` gate enforce this mechanically.
+3. **Surgical Changes** — touch only what the user's request requires. Remove imports / variables / functions that *your* changes made unused. Do not refactor adjacent code. Every changed line must trace to the user's request.
+4. **Goal-Driven Execution** — define verifiable success criteria (`peaks request show --role rd` carries ACs from PRD). For multi-step work, state plan + verify checkpoints before acting.
+
+Cross-references: Slice 1 PRD §AC-1 / `tests/unit/skills/karpathy-prompt-injection.test.ts` (4-point assertion guard). The canonical skill id is `andrej-karpathy-skills:karpathy-guidelines`.
+
+## Scope directory (slice 10 — read scopeDir from envelope)
+
+The canonical scope dir for this request is provided as `envelope.data.scopeDir` (absolute path). Write all reviewable files under that path. **NEVER** construct paths like `.peaks/_runtime/<sessionId>/...` from frontmatter — the path has already been resolved by the CLI.
+
+# Peaks-Cli RD
+
+Peaks-Cli RD owns engineering analysis, implementation planning, and refactor execution contracts.
+
+## Hard contracts for browser self-test (BLOCKING — read before any browser_take_screenshot / login flow)
+
+For frontend / UI-affecting slices, RD's self-test uses the Playwright MCP headed browser. LLM checks its own tool list for the Playwright MCP entry; if absent, surface the install command (`claude mcp add playwright -- npx @playwright/mcp@latest`) and report the gate blocked. Two contracts: (1) self-test screenshots land under `.peaks/_runtime/<sessionId>/qa/screenshots/`, (2) login / CAPTCHA / SSO / MFA is a hard block — surface with `AskUserQuestion`. Same in spirit as `peaks-qa`'s; RD and QA share the headed-browser path.
+
+→ see `references/browser-self-test-contracts.md` and `references/browser-action-wrapper.md` (slice 3 thin wrapper).
+
+## Sub-agent dispatch (when launched by peaks-solo swarm)
+
+When this skill is launched as a sub-agent via `peaks sub-agent dispatch <role>` (then the LLM executes the returned toolCall) from `peaks-solo`, the following sections of THIS skill are **suspended** for the sub-agent run: Session id (use parent's), Skill presence, Workspace initialization, Mode selection, Statusline install.
+
+What the sub-agent MUST still do: read PRD via `peaks request show`, run standards preflight (dry-run only), write planning artefact (`rd/tech-doc.md` for feature/refactor; `rd/bug-analysis.md` for bugfix; skip for config/docs/chore), return compact JSON envelope.
+
+→ see `references/rd-sub-agent-dispatch.md` for the full contract + hard prohibitions.
+
+## Skill presence (MANDATORY first action — main-loop context only)
+
+When this skill is running in the main Claude session (not as a sub-agent — i.e. user invoked `peaks-rd` directly, or `peaks-solo` is executing the role inline in assisted/strict mode), before any analysis or tool call, immediately run `peaks skill presence:set peaks-rd --project <repo> --mode <mode> --gate startup`. Install statusline on first run. Read durable project memory via `peaks project memories --project <repo> --json`.
+
+→ see `references/skill-presence-and-title.md` for the full contract.
+
+## Responsibilities
+
+- scan the current project before changes;
+- prefer existing project standards over built-in language standards;
+- enforce the 95% UT coverage refactor gate;
+- split broad refactors by minimal functional slices;
+- generate refactor options, risk matrix, rollback plan, and task graph preview;
+- implement only after strict specs and confirmations exist.
+
+## Mandatory per-request artifact
+
+Every RD invocation — feature, bug, refactor, clarification — must write a durable artifact at `.peaks/_runtime/<session-id>/rd/requests/<request-id>.md` (the canonical placeholder form: `<session-id>` is the active session id at runtime, `<request-id>` follows `YYYY-MM-DD-<kebab-slug>`; the runtime path is `.peaks/_runtime/<session-id>/rd/requests/<request-id>.md`). This is the canonical engineering record for that request; handoff to QA/SC is blocked while the artifact is missing or its state is `draft` / `spec-locked` without implementation evidence.
+
+→ see `references/artifact-per-request.md` for the template + the per-slice vs per-session rule.
+
+## Default runbook
+
+See `references/rd-runbook.md` for the full 9-step runbook (steps #0–#8) with every CLI invocation, project-scan BLOCKING rule, component-library detection, CSS framework conflict check, and 6 transition gates.
+
+## RD gate index
+
+You cannot declare a phase complete from memory. Each gate below is a `ls` or `grep` command you **MUST run** and whose output you **MUST see** before proceeding. CLI enforcement: the gates are ALSO enforced by `peaks request transition`, which fails with `code: PREREQUISITES_MISSING` if any are absent.
+
+Gate index: A (project-scan), A2 (tech-doc path verification), A3 (CLAUDE.md + .claude/rules), B (tech-doc + request artifact), B2 (unit tests on changed surface), B3 (code-review.md), B4 (security-review.md), B5 (lint — no unfilled placeholders), B6 (request-type-sanity), B7 (repair-status — 3-cycle cap), B8 (diff-vs-scope), B9 (perf-baseline).
+
+→ see `references/rd-transition-gates.md` for the per-gate contract + `ls` / `grep` shell snippets.
+
+## Project standards preflight
+
+Before RD planning or implementation work in a code repository, call `peaks standards init --project <path> --dry-run` and `peaks standards update --project <path> --dry-run`. Apply only when write authorization exists; otherwise keep the CLI output as a preflight next action.
+
+→ see `references/rd-standards-preflight.md` for the preflight contract.
+
+## Library version awareness (3rd-party breaking-change gate)
+
+After `peaks scan libraries` lands the dependency list under `## Library versions` in `rd/project-scan.md`, RD MUST cross-check the slice's diff against `schemas/library-breaking-changes.data.json` before writing any 3rd-party API call. On a hit, warn in the handoff + persist a `lesson` memory. Check `schemas/library-breaking-changes.meta.json` for freshness before reading the data.
+
+→ see `references/library-version-awareness.md` for the full 4-step process + data-freshness check.
+
+## GStack integration and code dry-runs
+
+Map gstack stages to Peaks-Cli RD risk matrices, task graphs, and slice contracts. Adapt gstack concepts into Peaks-Cli artifacts; do not invoke gstack commands as runtime deps. Dry-run before planning, after each slice, before handoff.
+
+→ see `references/rd-gstack-integration.md` for the full integration contract.
+
+## Requirement boundary red-line self-check
+
+Before every code or mock change, RD must write and then enforce a red-line scope check in the RD artifact:
+
+1. name the exact product requirement, route, UI surface, API path, data model, and path/glob patterns that are in scope (write under `## Red-line scope` with `In-scope:` / `Out-of-scope:` subheaders);
+2. name adjacent surfaces explicitly out of scope (list pages, delete/update flows, unrelated API endpoints, existing data records, auth, permissions, shared runtime config);
+3. reject any implementation that modifies, deletes, mocks, or replaces out-of-scope behavior just to make validation pass;
+4. for API/mock work, mock only the exact request path and method required by the approved slice;
+5. before handoff, run `peaks scan diff-vs-scope --rid <rid> --project <repo>` (Peaks-Cli Gate B8). The CLI auto-allows test files and `.peaks/` artifacts.
+
+## Mandatory tech-doc output (RD-side)
+
+**BLOCKING — Do not hand off to QA without this file.** Every RD invocation that touches code MUST produce a tech-doc artifact at `.peaks/_runtime/<sessionId>/rd/tech-doc.md`. If this file is missing at QA handoff, the handoff is invalid.
+
+> **v2.11.0 Group A:** the per-session `rd/tech-doc.md` is removed. The per-slice source of truth is now the immutable peaks-prd handoff at `.peaks/_runtime/<sessionId>/prd/handoff.md` (sha256-hashed); the per-slice planning record is `rd/requests/<rid>.md`. See `references/artifact-per-request.md` for the canonical RD artefact contract.
+
+## Mandatory perf-baseline output (RD-side perf gate)
+
+**BLOCKING — Do not hand off to QA without a perf-baseline file when the slice has a user-visible performance surface.** The QA stage's Gate A4 (performance check) needs a stable reference to diff against; without an RD-side baseline, the first time Gate A4 runs it has nothing to compare against. **Slice 025**: the perf baseline is stable across slices within a session and is refreshed on trigger; use `peaks workflow plan refresh perf --apply` for refreshes.
+
+→ see `references/mandatory-perf-baseline.md` for the full "when this applies" + `peaks perf baseline --apply` workflow + slice-025 refresh contract.
+
+## Implementation completion gates
+
+RD cannot mark a development slice complete until all of these are true. Each gate below maps to a hard verification gate in the Transition Verification Gates section — run the corresponding command, see the output. The gates (0, 0.5, 0.6, 1, 2, 3, 4, 5, 6, 6.5, 7, 8, 9, 10, 11, 12) are listed in `references/rd-runbook.md` §7.
+
+If any gate fails, return to development for fixes or hand off as blocked. Do not describe the work as done, shippable, or ready for QA.
+
+## Parallel review fan-out (v2.12.0 3-way fanout — code-reviewer + qa-test-cases-writer + karpathy-reviewer)
+
+The THREE review activities run in parallel via `peaks sub-agent dispatch <role>`, not sequentially. Sub-agents: `code-reviewer`, `qa-test-cases-writer` (writes `qa/test-cases/<rid>.md`), `karpathy-reviewer` (the **hard Karpathy-Gate**). This is the v2.12.0 3-way fanout. Feature / refactor / bugfix: all three. Config / docs / chore: no fan-out — no `karpathy-reviewer` dispatched. OCR augmentation (B3): `peaksConfig.ocr.llm` → `peaks code-review run-ocr --json` → merge into `code-review.md`; → `references/ocr-integration.md`.
+
+> **v2.12.0 collapse (Group A):** the 5-way fan-out moved `security-reviewer` + `perf-baseline-reviewer` into standalone audit skills (`peaks-security-audit` + `peaks-perf-audit`). → `references/v2-12-fanout-collapse.md`.
+
+> **v2.15.0+:** 技术决策 AI 据 prd 业务场景块自决,user 不参与;存量项目无 UT,改 A 前跑 `peaks impact scan`(G13);fork 场景 tech-doc 列上游基线+业务 patch 集(G11)。详见 `.peaks/memory/peaks-cli-user-role-and-tech-decision.md`。
+
+> **Slice 2026-06-24-efficiency-4p-bundle / G4 (P1.3) — karpathy-skip policy authoritative.** Decision table at `src/services/rd/reviewer-dispatch-policy.ts` (`shouldDispatchKarpathy`, `reviewerListFor`). Pinned by `tests/unit/rd/karpathy-skip-on-config-docs-chore.test.ts`.
+
+### Hard Karpathy-Gate (Slice 5/6)
+
+The `karpathy-reviewer` sub-agent is a **hard gate** for `rd:qa-handoff`. Per `andrej-karpathy-skills:karpathy-guidelines` §1 Think Before Coding ("state your assumptions") + §3 Surgical Changes ("touch only what the user asked"), `peaks request transition --state qa-handoff` is BLOCKED by the CLI gate until `.peaks/_runtime/<sessionId>/rd/karpathy-review.md` exists with the `## Karpathy-Gate` header and at least one of the 4 guideline section markers. The file is enforced by the `KARPATHY_REVIEW` prerequisite in `src/services/artifacts/artifact-prerequisites.ts` (added in Slice 5). The escape hatch is `peaks request transition --allow-incomplete --confirm` (assisted mode). The companion `peaks scan karpathy` CLI is a structural scanner for the same file (`src/services/scan/karpathy-service.ts`); the semantic review is the sub-agent's job.
+
+### Peaks-Cli Gate C — type-specific RD evidence
+
+The CLI gate at `rd:qa-handoff` is the authoritative check. Missing any required file → DO NOT attempt the qa-handoff transition; CLI will reject with `PREREQUISITES_MISSING`.
+
+| Request type | Required RD evidence |
+|---|---|
+| feature / refactor | `audit/security.md` + `audit/perf.md` + `rd/code-review.md` + `rd/karpathy-review.md` + `qa/test-cases/<rid>.md` + `prd/handoff.md` |
+| bugfix | `audit/security.md` + `audit/perf.md` (perf-shaped only) + `rd/code-review.md` + `rd/karpathy-review.md` + `qa/test-cases/<rid>.md` + `prd/handoff.md` |
+| config | `audit/security.md` |
+| docs / chore | (no extra evidence required) |
+
+→ see `references/rd-fanout-contracts.md` for the **3** sub-agents' contracts + hard prohibitions + aggregation + degradation. Pre-v2.12.0 `rd/{security-review,perf-baseline}.md` paths remain readable for the 1-minor-release back-compat window.
+
+## Refactor hard gates
+
+If a request is refactor, cleanup, architecture adjustment, module split, or technical debt work: scan project structure and existing standards; locate or run UT coverage; block implementation unless coverage is >= 95%; treat missing, unknown, or unverifiable coverage as failing; generate intermediate artifacts before implementation; call or consume peaks-prd and peaks-qa artifacts even in direct RD mode; require strict slice spec before each slice; require 100% acceptance for the slice; require code changes and intermediate artifacts to be traceable in local `.peaks/_runtime/<sessionId>/` storage before continuing.
+
+→ see `references/refactor-workflow.md` for the full workflow + required artifacts list.
+
+## Unit-test coverage red line
+
+The 100% coverage target on testable files is meaningful coverage, not a score to chase. RD must not write coverage-padding tests. Rules: defensive guards for unreachable cases → remove the guard; IO/platform glue that cannot be tested cleanly → add to `coverage.exclude`; real behavior a caller relies on → write a behavior-framed test; if the only way to 100% is a padding test, lower the target or simplify the production code. Test names must describe behavior, not coverage targets.
+
+## OpenSpec usage
+
+For non-trivial RD changes, use OpenSpec when the project already has `openspec/` or the user approves adding OpenSpec. In repositories that already contain `openspec/`, missing OpenSpec change artifacts are a blocking pre-implementation issue, not an optional suggestion.
+
+Create or update `openspec/changes/<change-id>/proposal.md`, `design.md`, `tasks.md`, and `specs/**/spec.md` before implementation slices begin. If the repository uses a different existing OpenSpec layout, follow that layout and record the file paths in the RD handoff.
+
+OpenSpec artifacts are durable project specification files, not Peaks-Cli runtime swarm artifacts. They may live in the target repository root under `openspec/changes/...`. Swarm/runtime outputs such as task graphs, worker briefs, worker reports, reducer reports, scan reports, validation evidence, and compact handoffs must remain in the configured Peaks-Cli artifact workspace outside the target repository.
+
+Peaks-Cli PRD/RD/QA gates remain authoritative: OpenSpec structures the durable spec, while Peaks-Cli artifacts still carry role handoffs, coverage gates, QA evidence, swarm coordination, and execution state.
+
+→ see `references/openspec-cli.md` for the CLI recipes.
+
+## Mock data placement rules (BLOCKING — framework-aware)
+
+When the project-scan in `.peaks/_runtime/<sessionId>/rd/project-scan.md` identifies a frontend framework, mock data MUST follow the framework's built-in mock mechanism. **Never write mock data inline in component files.**
+
+→ see `references/mock-data-placement.md` for the framework-to-mock-directory mapping + hard rules + verification gate.
+
+## Frontend project generation
+
+When RD work creates a frontend application and the user has not specified a technology stack, default to React + Vite + shadcn/ui with `peaks shadcn init --preset [CODE] --template vite`. Generated projects must not contain JavaScript source or config files. TypeScript only.
+
+→ see `references/frontend-project-generation.md` for the scaffold protocol.
+
+## Artifact and standards output
+
+When project identification or scanning produces reports, matrices, maps, plans, or validation files, write them under the configured Peaks-Cli artifact workspace (default: `.peaks/_runtime/<sessionId>/rd/`). Do not default to a git-backed artifact repository or external artifact sync. Route standards mutations through `peaks standards init/update`; do not hand-write. Do not update user-global `~/.claude/rules/**` from this workflow.
+
+→ see `references/artifact-and-standards-output.md` for the full contract.
+
+## Compact handoff
+
+Before RD work stops, finishes, blocks, or hands off to another role, emit a short resumable capsule: mode, scope, coverage status, validated decisions, current slice, artifact paths, blockers, and next action. Link to scan reports, matrices, plans, and task graphs instead of restating them.
+
+The handoff artifact carries **mandatory YAML frontmatter** (`requestId`, `scope`, `files`, `decisions[]`, `risks[]`, `nextActions[]`, `gateEvidence`, `schemaVersion`) so peaks-qa can mechanically cross-check. See `references/writing-handoff-frontmatter.md` for the field schema and validation.
+
+→ see `references/compact-handoff.md`.
+
+## External references
+
+## Codegraph project analysis
+
+Codegraph is local project-analysis evidence, scoped to red-line scope boundaries (changed files / symbols) and read via `peaks codegraph affected --project <path> <changed-files...> --json`. Peaks-Cli RD gates remain authoritative; codegraph is untrusted supporting evidence. Do not let codegraph output drive scope, design, or QA verdict decisions, and never mutate agent settings, Claude settings, or hooks from codegraph. Do not commit `.codegraph/` artifacts or persist generated `.codegraph/` databases into git. Codegraph context is written to `.peaks/_runtime/<sessionId>/rd/codegraph-context.md` for handoff to QA / TXT.
+
+## Matt Pocock skills integration
+
+Matt Pocock skills (`diagnose` / `triage` / `tdd` / `improve-codebase-architecture` / `prototype`): engineering references only. Inspect before applying; Peaks-Cli RD gates remain authoritative. Understand Anything: `peaks understand status/show --json`. Codegraph: local analysis only, never commit `.codegraph/` artifacts. Other external resources: `peaks capabilities --source access-repo/mcp-server --json` for capability discovery.
+
+→ see `references/external-references.md` + `references/matt-pocock-integration.md` + `references/codegraph-project-analysis.md`.
+
+## Boundaries
+
+Do not bypass PRD/QA artifacts. Do not install hooks, agents, MCP, or settings. Ask the Peaks-Cli CLI to handle runtime side effects.
+
+Do not bypass the parallel review fan-out when the slice has a code-review / qa-test-cases / karpathy-review surface — see `## Parallel review fan-out` above. The three review activities are fan-out, not sequential; sequential re-implementation of the same logic by the main RD loop defeats the wall-clock benefit and is treated as a red-line violation.
+
+**Security / perf audit boundary (v2.12.0):** security and perf audit run as standalone audit skills (`peaks-security-audit`, `peaks-perf-audit`) whose outputs land at `audit/security.md` / `audit/perf.md`. RD does **not** dispatch `security-reviewer` or `perf-baseline-reviewer` sub-agents. See `references/rd-fanout-contracts.md` §"Deprecated reviewer back-compat".
+
+## Sub-agent context governance (G7 + G7.7 + G8 + G9 — slice #010)
+
+RD sub-agent prompt template MUST include the G7 path convention + G8.6 share protocol. Detailed protocol: `skills/peaks-solo/references/context-governance.md` + `skills/peaks-solo/references/headroom-integration.md`.
+
+→ see `references/rd-context-governance.md` for the full G7 / G8.6 / G9 protocol + RD sub-agent prompt template.
+
+## Sub-stages (Plan 3 — strategic + tactical split)
+
+peaks-rd runs in two sub-stages:
+
+1. **Strategic** — root-cause analysis, design intent. Outputs the strategy markdown + STRAT.sig.
+2. **Tactical** — minimal implementation. AST hard gate compares external API calls against peaks-context's locked-version docs. Outputs the impl json + TACT.sig.
+
+Hard constraint: TACT.sig cannot be written when the AST gate has violations.
+The LLM auto-fixes and retries (peaks-qa's 3-cycle repair cap).
+
+Karpathy guidelines remain injected in both sub-stages.
+
+Public entry points (from `src/services/rd/rd-service.ts`):
+
+- `runStrategic(input: RunStrategicInput): Promise<StrategyOutput>` — strategy writer
+- `runTactical(input: RunTacticalInput): Promise<ImplOutput>` — runs AST gate then writes impl.json + TACT.sig chained to inputSig
+
+## References
+
+Index of every `references/` file in this skill. Read on demand.
+
+| File | Coverage |
+|---|---|
+| `references/artifact-and-standards-output.md` | Artifact + standards output contract. |
+| `references/artifact-contracts.md` | Sub-agent handoff artifact contracts. |
+| `references/artifact-per-request.md` | RD per-request artifact + per-slice vs per-session scope. |
+| `references/browser-self-test-contracts.md` | Browser self-test contracts (1) + (2). |
+| `references/codegraph-project-analysis.md` | Codegraph local analysis (untrusted evidence). |
+| `references/command-migration.md` | Legacy command migration map. |
+| `references/compact-handoff.md` | RD compact handoff capsule. |
+| `references/external-references.md` | External 3rd-party inventory. |
+| `references/frontend-project-generation.md` | React + Vite + shadcn/ui default. |
+| `references/library-version-awareness.md` | Breaking-change gate + freshness check. |
+| `references/mandatory-perf-baseline.md` | RD-side perf baseline + `peaks perf baseline` workflow. |
+| `references/matt-pocock-integration.md` | Matt Pocock skills as references. |
+| `references/mock-data-placement.md` | Framework-to-mock-directory mapping + rules. |
+| `references/openspec-cli.md` | OpenSpec CLI recipes. |
+| `references/parallel-review-fanout.md` | 3-way parallel review fan-out. |
+| `references/reading-v2-slice-results.md` | Read peaks-slice-decompose v2 envelope + per-pass dispatch. |
+| `references/writing-handoff-frontmatter.md` | Required frontmatter fields for RD → QA handoff. |
+| `references/rd-context-governance.md` | G7 + G8.6 + G9 RD sub-agent protocol. |
+| `references/rd-gstack-integration.md` | GStack → Peaks mapping + dry-run cadence. |
+| `references/rd-runbook.md` | Default 9-step runbook (steps #0–#8). |
+| `references/rd-standards-preflight.md` | Standards preflight dry-run contract. |
+| `references/rd-sub-agent-dispatch.md` | Sub-agent suspended sections + contract. |
+| `references/rd-transition-gates.md` | Per-gate A-A3-B-B9 contract. |
+| `references/refactor-workflow.md` | Refactor hard gates + required artifacts. |
+| `references/skill-presence-and-title.md` | RD skill presence (main loop only). |
+| `references/v2-12-fanout-collapse.md` | v2.12.0 fan-out collapse. |

package/skills/peaks-rd/references/artifact-and-standards-output.md

@@ -0,0 +1,9 @@
+# Artifact and standards output (RD)
+
+> Body of `## Artifact and standards output`. When project identification or scanning produces reports, matrices, maps, plans, or validation files, write them under the configured Peaks-Cli artifact workspace. By default, use local non-git storage at `.peaks/_runtime/<sessionId>/rd/` in the target project or the Peaks-Cli CLI-provided local workspace. If the artifact workspace is unknown, create or request `.peaks/_runtime/<sessionId>/` before writing generated outputs. Use one session directory consistently so generated outputs stay grouped.
+
+Do not default to a git-backed artifact repository, external artifact sync, or automatic commits for intermediate artifacts. Git inclusion or sync requires explicit user confirmation or an active profile that clearly authorizes it. Browser evidence must be sanitized before retention: do not store login URLs, cookies, headers, tokens, storage state, browser traces, or screenshots/logs containing PII or SSO/MFA material.
+
+When project-local `CLAUDE.md` or project-local `.claude/rules/**` is created or updated, route the mutation through `peaks standards init` or `peaks standards update`; do not hand-write standards mutations. Derive the content from the current scan results and existing project standards. Keep only the rules that match the project's languages, frameworks, tooling, and repository layout. Do not emit generic templates, copy-pasted boilerplate, or rules unrelated to the current scan evidence. Do not update user-global `~/.claude/rules/**` from this workflow.
+
+If the scan results are insufficient to justify a rule, leave it out or surface a review-only suggestion instead of writing it into project standards.

package/skills/peaks-rd/references/artifact-contracts.md

@@ -0,0 +1,7 @@
+# artifact-contracts.md
+
+This reference documents artifact-contracts.md for peaks-rd.
+
+Default local artifact path: `.peaks/_runtime/<session-id>/rd/`.
+
+RD artifacts should include scan reports, OpenSpec path notes, slice specs, task graphs, coverage evidence, code-review and security-review reports, post-check dry-run output, and handoff capsules. Keep artifacts local by default. Do not commit or sync them unless explicitly authorized.

package/skills/peaks-rd/references/artifact-per-request.md

@@ -0,0 +1,112 @@
+# RD per-request artifact contract
+
+Every RD invocation must leave one durable artifact under the workflow-local workspace so the engineering decisions and slice contracts are traceable later.
+
+## Required path
+
+```
+.peaks/_runtime/<session-id>/rd/requests/<request-id>.md
+```
+
+Use the `<request-id>` PRD assigned (`YYYY-MM-DD-<kebab-slug>`). RD may also produce companion artifacts (task graph JSON, scan report, coverage evidence, slice spec, dry-run output) under the same `rd/` workspace and link to them from this file.
+
+## Required content
+
+```markdown
+# RD Request <request-id>
+
+- linked-prd: .peaks/_runtime/<session-id>/prd/requests/<request-id>.md
+- linked-ui:  .peaks/_runtime/<session-id>/ui/requests/<request-id>.md  (when UI involved)
+- type: feature | bug | refactor | clarification
+
+## Red-line scope
+
+- in-scope files / routes / API paths / data models
+- explicit out-of-scope surfaces (do not modify, mock, delete, or replace)
+
+## Standards preflight
+
+- `peaks standards init/update --project <path> --dry-run` output paths and status
+- planned application: apply | review-only | blocked
+
+## OpenSpec linkage (when openspec/ exists)
+
+- change-id: <openspec change id>
+- entry validate: `peaks openspec validate <change-id>` data.valid status
+- to-rd projection: `peaks openspec to-rd <change-id>` artifact path
+- exit validate (after implementation): status
+
+## Coverage status
+
+- current total UT coverage: <percent>
+- new/changed code coverage: <percent>
+- gate verdict: pass | legacy-accepted | blocked
+
+## Slice contract
+
+For each slice in this request:
+
+- slice id
+- functional boundary
+- pre-refactor behavior summary
+- target structure
+- unit-test requirements
+- acceptance checks (100% required per slice)
+- rollback plan
+- commit boundary (one per slice; aligned with OpenSpec tasks.md section when available)
+
+## Implementation evidence
+
+- diff paths
+- test commands + outputs
+- code review findings + fixes
+- security review findings + fixes
+- dry-run output
+
+## MCP usage (when external docs lookup was used)
+
+- capabilityId / tool / sanitized args
+- artifact path of stored result
+- no secrets, no full network bodies
+
+## Handoff
+
+- to peaks-qa: <link to QA request artifact>
+- to peaks-sc: <link to SC commit-boundary artifact>
+
+## Status
+
+- created: <ISO timestamp>
+- last update: <ISO timestamp>
+- state: draft | spec-locked | implemented | qa-handoff | blocked
+```
+
+## Rules
+
+- Do not skip the RD artifact for "trivial" fixes. Even a one-line bug fix needs the red-line scope and acceptance checks recorded.
+- Refactor work requires UT coverage ≥ 95% before slicing begins; record the verdict in this artifact, not just in chat.
+- Sanitize MCP/network/browser evidence before writing.
+- Do not commit unless the user or active profile authorizes durable retention.
+- Handoff to QA is blocked while state is `draft` or `spec-locked` without implementation evidence.
+
+---
+
+## Two RD artifact files — do not confuse them
+
+> Body of `## Two RD artifact files`. RD has two distinct artifact files, and the most common regression is to write the per-slice content into the per-session file. They serve different readers and live in different places:
+
+| File | Scope | Reader | Required content |
+|---|---|---|---|
+| `.peaks/_runtime/<sessionId>/prd/handoff.md` | per-slice — immutable peaks-prd source of truth (v2.11.0+) | RD, QA, all sub-agents | Goals, non-goals, acceptance criteria, architecture, slice graph, mock strategy, cross-cutting decisions. sha256-hashed in frontmatter; sub-agents verify the hash before reading. |
+| `.peaks/_runtime/<sessionId>/rd/requests/<rid>.md` | per-slice — one request, one planning artifact | QA, SC, the lint gate | Red-line scope, in-scope / out-of-scope, unit-test requirements, **Implementation evidence** (file list, `pnpm test` output, git diff excerpts), MCP usage, handoff, status. **This is the file the lint gate checks for placeholders.** |
+| `.peaks/_runtime/<sessionId>/rd/code-review.md` | per-session — the engineering review | QA, the human reviewer | Code review findings + fixes. |
+| `.peaks/_runtime/<sessionId>/rd/security-review.md` | per-session — the security review | QA | Security review findings + fixes. |
+
+> **v2.11.0 change (Group A):** `rd/tech-doc.md` is removed. The per-slice source of truth moves to the immutable peaks-prd handoff (`prd/handoff.md`); the per-slice planning record is `rd/requests/<rid>.md`. The "per-session" content category is no longer RD's responsibility — it lives upstream in the PRD handoff.
+
+**Failure mode the lint gate catches**: the LLM writes the actual implementation content into a side file and leaves `rd/requests/<rid>.md` as the default template (with placeholder sections like "Implementation evidence: 留待 RD 实施阶段补充" and "MCP usage: N/A"). The lint gate then fails the slice with 6+ lint errors on the `<rid>.md` template even though the actual content lives elsewhere.
+
+**Rule**:
+- **Per-slice content** (red-line scope, in-scope / out-of-scope, the implementation evidence list, the unit-test assertions, the handoff) → **belongs in `rd/requests/<rid>.md`**.
+- **Source-of-truth architecture content** (goals, non-goals, ACs, slice graph, mock strategy, cross-cutting decisions) → **belongs in `prd/handoff.md`** (immutable, sha256-hashed).
+- When in doubt: copy the per-slice content into the `<rid>.md` artifact's "Implementation evidence" section after writing it to the handoff. The two files can carry overlapping context; the gate only enforces that `<rid>.md` is not empty placeholders.

package/skills/peaks-rd/references/browser-action-wrapper.md

@@ -0,0 +1,39 @@
+# `peaks browser action` — slice 3 thin Playwright wrapper
+
+For the common browser flow (navigate → click → fill → snapshot → extract),
+use `peaks browser action <intent>` instead of hand-shelling each MCP tool
+call. Five supported intents; each invocation triggers EXACTLY ONE MCP
+tool call (no auto-snapshot between intents).
+
+| Intent | Required args | MCP tool name |
+|--------|---------------|----------------|
+| `navigate` | `--url <url>` | `browser_navigate` |
+| `click` | `--selector <simple>` | `browser_click` |
+| `fill` | `--selector <simple> --value <v>` | `browser_fill_form` |
+| `snapshot` | (none) | `browser_snapshot` |
+| `extract` | `--expression <js>` | `browser_evaluate` |
+
+(MCP namespace prefix is injected by the agent harness — do NOT bake it
+into SKILL.md; see slice 016 contract.)
+
+## Selector rules
+
+Selectors MUST be simple: `#id`, `.class`, `tag`, `tag#id`, `tag.class`.
+Anything else (XPath, attribute selectors, descendant chains, pseudo-class
+chains) returns a "fall back to raw MCP" error.
+
+## Anti-features (intentionally not built)
+
+- No retry / circuit-breaker
+- No selector caching
+- No accessibility tree customization
+- No screenshot / video
+- No "smart selector healing"
+
+If you need any of those, fall back to the raw Playwright MCP tools.
+
+## KPI
+
+Single browser action ≤ 5s end-to-end. The wrapper is a synchronous
+dispatch + one MCP call; wall time = `runBrowserAction.elapsedMs` plus
+the underlying MCP round-trip.

package/skills/peaks-rd/references/browser-self-test-contracts.md

@@ -0,0 +1,29 @@
+# Browser self-test contracts
+
+> Body of `## Hard contracts for browser self-test` + `### Contract 1` + `### Contract 2`.
+
+For frontend or UI-affecting slices, RD's self-test uses the Playwright MCP headed browser to verify the implementation behaves correctly before handing off to QA. The two contracts below are identical in spirit to `peaks-qa`'s contracts — RD and QA share the same headed-browser path and the same evidence conventions; only the role differs.
+
+## Contract 1 — Self-test screenshots must land under .peaks/_runtime/<sessionId>/qa/screenshots/
+
+Even though RD runs the self-test, **the screenshot evidence is QA's** by convention (the test report under `.peaks/_runtime/<sessionId>/qa/test-reports/` cites these paths). Therefore RD's Playwright screenshot tool calls (the LLM invokes `browser_take_screenshot` directly when the the Playwright MCP tools are present in the LLM's tool list) MUST pass `filename` (in the args object) whose absolute path is inside `.peaks/_runtime/<sessionId>/qa/screenshots/`, exactly the same contract QA enforces. Do not let Playwright fall back to the project root. If the the Playwright MCP tools are absent from the tool list, STOP and tell the user: `claude mcp add playwright -- npx @playwright/mcp@latest` (Claude Code) or consult the IDE's MCP install docs.
+
+## Contract 2 — Login / CAPTCHA / SSO / MFA wall is a hard block, not a skip
+
+When the headed browser hits an auth wall, RD does **not** skip the browser gate. The skill must surface the wall with `AskUserQuestion` and pick one of three paths:
+
+```
+AskUserQuestion({
+  question: "Headed browser hit a login wall at <URL>. How should RD self-test proceed?",
+  options: [
+    { label: "I am logged in / I'll log in now",
+      description: "Pause RD. The visible browser is already open; the user completes login in-place, then types 'logged in' or equivalent. RD resumes browser_navigate + browser_snapshot from the post-login page." },
+    { label: "Skip browser self-test, hand off to QA",
+      description: "Mark the slice's browser self-test as deferred. Do NOT mark the slice as RD-done; transition to qa-handoff with browser-gate=blocked reason=login-required, and let QA's gate machinery surface the wall to the user again." },
+    { label: "Cancel the workflow",
+      description: "Stop RD. Emit a blocked TXT handoff so peaks-solo can surface the auth wall to the user. Do not modify code paths that the browser gate would have covered." }
+  ]
+})
+```
+
+The full hard-block contract is defined in `peaks-qa` (see "Hard contracts for browser validation" there); RD inherits the same rules. Without an explicit decision from the user, RD does not advance past the wall.

package/skills/peaks-rd/references/code-reviewer-4dim-hint.md

@@ -0,0 +1,72 @@
+# Code-reviewer 4-dim hint (slice 2.1 — proposal 2)
+
+> Hint block appended to the code-reviewer sub-agent prompt at dispatch
+> time. The RD main loop injects the verbatim block below after the
+> Karpathy-guidelines context block (see
+> `references/rd-sub-agent-dispatch.md` §"Karpathy-guidelines context").
+> The block is the canonical promotion surface for the convention at
+> `.peaks/standards/typescript/testing.md`.
+
+## What the reviewer checks (4-dim convention)
+
+When the diff under review touches `tests/unit/**`, the reviewer MUST
+verify the diff does not violate the 4-dimension split
+(`render` / `behavior` / `integration` / `a11y`). The reviewer does not
+need to flag every test-case misalignment; only `describe`-level
+violations (one `describe` block spanning two dimensions).
+
+### Review checklist for test diffs
+
+- [ ] Each `describe(...)` block is exactly one dimension. No test case
+      inside belongs to a different dimension.
+- [ ] No mocking of the SUT in `render` / `behavior` blocks. (Mocks are
+      allowed in `integration` blocks and only for the external
+      boundary.)
+- [ ] Error-message text and error-class names live in `a11y`, not in
+      `behavior`. (Asserting `expect(...).toThrow(SomeError)` is
+      `behavior`; asserting on the message regex is `a11y`.)
+- [ ] E2E tests under `tests/e2e/**` are NOT in scope of this check —
+      they follow `peaks-qa`'s test-case-generation rules instead.
+
+### Severity mapping
+
+| Violation | Severity | Reason |
+|---|---|---|
+| `describe` block spanning 2+ dimensions | LOW | Doc-level concern; reviewer flags so the next refactor can split. **Not a blocker.** |
+| Mocking the SUT in `render` | MEDIUM | Breaks the "render = no SUT mocks" rule; the mock is hiding real behavior. |
+| Mocking the SUT in `behavior` | MEDIUM | Same as above for `behavior`. |
+| Putting error-message regex in `behavior` instead of `a11y` | LOW | Doc-level concern; non-blocking. |
+
+### How to apply this hint
+
+1. Run `git diff -- tests/unit/**` (and any new file under
+   `tests/unit/_samples/**`).
+2. For each `describe` block in the diff, classify it into one of the
+   4 dimensions using the decision tree in
+   `.peaks/standards/typescript/testing.md`.
+3. If a block fits more than one dimension, flag it under the
+   "Doc-level" category — do NOT block.
+4. Add a single line under the existing `## Review Summary` table:
+
+```
+| Severity | Count | Status |
+|----------|-------|--------|
+| CRITICAL | 0     | pass   |
+| HIGH     | 0     | pass   |
+| MEDIUM   | <n>   | info   |     ← test-mock violations (if any)
+| LOW      | <m>   | note   |     ← 4-dim doc-level violations (if any)
+```
+
+Where `<n>` and `<m>` are the counts from steps 2-3. Empty counts
+(`0 | pass`) are fine — absence of test diffs means nothing to flag.
+
+### What this hint does NOT do
+
+- It does NOT introduce a lint rule. ESLint custom rules for
+  `describe`-dimension classification age poorly (false positives on
+  inline test files, fragile AST parsing).
+- It does NOT require retroactive refactor of existing test files.
+  Only test diffs under review are checked.
+- It does NOT override the existing `code-reviewer.md` checklist
+  (security / quality / performance). The 4-dim check is a parallel,
+  lower-severity concern.

package/skills/peaks-rd/references/codegraph-project-analysis.md

@@ -0,0 +1,5 @@
+## Codegraph project analysis (RD)
+
+> Body of `## Codegraph project analysis`. RD may use `peaks codegraph affected --project <path> <changed-files...> --json` as local project-analysis evidence to inform red-line scope boundaries before writing tech-doc or starting implementation. Treat the output as untrusted supporting evidence — verify against the actual code before relying on it.
+
+Do not run upstream installer flows, mutate agent settings, or commit `.codegraph/` artifacts. Peaks-Cli RD gates remain authoritative for handoff and acceptance.

package/skills/peaks-rd/references/command-migration.md

@@ -0,0 +1,3 @@
+# command-migration.md
+
+This reference documents command-migration.md for peaks-rd.

package/skills/peaks-rd/references/compact-handoff.md

@@ -0,0 +1,3 @@
+# Compact handoff (RD)
+
+> Body of `## Compact handoff`. Before RD work stops, finishes, blocks, or hands off to another role, emit a short resumable capsule: mode, scope, coverage status, validated decisions, current slice, artifact paths, blockers, and next action. Link to scan reports, matrices, plans, and task graphs instead of restating them.

package/skills/peaks-rd/references/external-references.md

@@ -0,0 +1,11 @@
+# External references (RD)
+
+> Body of `## External references`. **Matt Pocock skills** (`diagnose`, `triage`, `tdd`, `improve-codebase-architecture`, `prototype`): Engineering references only. Inspect before applying; Peaks-Cli RD gates remain authoritative.
+
+**Understand Anything**: Consume via `peaks understand status/show --json`. Fall back to `peaks codegraph context` or local project scan when absent.
+
+**Codegraph**: Optional local analysis via `peaks codegraph context/affected`. Output as untrusted supporting evidence; never commit `.codegraph/` artifacts.
+
+**Other external resources** (Context7, SearchCode, everything-claude-code, GitNexus, etc.): Use `peaks capabilities --source access-repo/mcp-server --json` for capability discovery before recommending. References only — do not execute upstream installers, do not install upstream resources, do not persist sensitive examples. Peaks-Cli RD gates remain authoritative.
+
+**OpenSpec CLI**: Route through Peaks-Cli CLI (`peaks openspec show/to-rd/render`). Do not hand-edit `openspec/changes/**`. Recipes: `references/openspec-cli.md`.

package/skills/peaks-rd/references/frontend-project-generation.md

@@ -0,0 +1,11 @@
+# Frontend project generation (RD)
+
+> Body of `## Frontend project generation`. When RD work creates a frontend application and the user has not specified a technology stack, and the current scan plus existing project standards still do not establish a frontend stack, default to React + Vite + shadcn/ui with:
+
+- `peaks shadcn init --preset [CODE] --template vite`
+
+`[CODE]` is the preset code supplied by the shadcn registry or user workflow; if it is unknown, stop and resolve the intended preset before scaffolding.
+
+If the user specifies a frontend stack or scaffold command, use the specified technology. If the scaffold emits JavaScript, convert generated application files to TypeScript before continuing; if conversion is not practical, ask for a TypeScript-compatible scaffold.
+
+Application projects generated through this skill must not contain JavaScript source or config files. Generate TypeScript only (`.ts`, `.tsx`, and TypeScript config equivalents), including when adapting examples from libraries or templates.

package/skills/peaks-rd/references/karpathy-reviewer-prompt.md

@@ -0,0 +1,2 @@
+# Canonical karpathy-reviewer prompt lives at: agents/karpathy-reviewer.md
+# This file is a 2-line pointer. Edit the canonical file instead. (peaks-cli 2.0 rules convention)