The FIRST thing you do, before anything else in this file — before the scope detection: ask **web console** (browser page, suggested) or **terminal**? Console → run `node "<D>/console.mjs" open --workflow review` before reading (<D>: references/web-console/ beside this SKILL.md — ~/.agents/skills/plan2code-review/references/web-console/ globally — or the dir in ~/.plan2code/console/console-dir), then read <D>/console.md and <D>/notes/review.md. Scope questions, the findings report and the pick-what-gets-fixed menu all go through it; the report lands on the page as a doc. Switchable anytime. If the argument already says which — `--web` or `Use the web console for this session.` — take it and do not ask; drop the flag. Launched by the dashboard? Its session is already open — resume it (console-launches.md), then Process. Read inside a build session for its review button? Skip this section — building-review.md's overrides govern, the session is already running. On the console, a `__stop` action is the person ending the session (console-stop.md); at every session end post `finish` BEFORE `stop`; unless it is a pause, the finish carries `"dashboard": true` (the Back to the dashboard button) and you keep waiting for the press (console-finish.md).
`<S>` is `scripts/` beside the SKILL.md that loaded this file (`~/.agents/skills/<skill>/scripts/` globally; when this file is a reference inside implement, implement-review or quick-task, that skill's own `<skill>/scripts/`, never `references/scripts/`). Run from the project root. Each prints one JSON object; on a non-zero exit read `message` and do what `next` says.
-`node "<S>/review-scope.mjs" [--base <branch>]`: the branch-review scope from git (Step 1).
-`node "<S>/specs.mjs" list` / `status <spec>`: spec state on disk (Step 2, Session End routing).
-`node "<S>/commit-msg.mjs" --subject "<subject>" --files <path> [--files <path> ...]`: the commit command (one `--files` per path).
- **Evidence-based only.** Every finding references file, line, code. No fabrication.
- **Concrete fixes.** Every finding includes a fix with severity ranking.
- **Standards & docs.** Flag deprecated APIs, anti-patterns. Verify docs match code.
- **Read-only.** Document findings only. Fix when user requests, verify, present for approval.
- **Research first.** Research tech stack docs, known issues, deprecations before finalizing findings.
- **Confidence bar.** Every finding must be High confidence -- verified in source code. Architectural/design findings additionally require use-case tracing. Investigate until certain or drop.
- **Zero findings = justification.** Per-dimension explanation of what was checked and why clean.
## Scope
Three levels -- auto-detected, always respect explicit user override:
| Scope | Trigger | Reviews |
|-------|---------|---------|
| **Focused** | User names files/functions, or conversation work detected | Specified files only |
**Detection:** 1) User prompt wins. 2) Conversation context = `focused`. 3) Scope already decided by a host workflow (a build's review, `building-review.md`) = use it. 4) Standalone with nothing named = scan, then ask (Step 1). Never default to `branch` silently. Ambiguous? Ask.
**Doc review:** >70% doc files = editorial critique. >70% code = also verify related docs match. (`review-scope.mjs` reports this as `mix`: `docs`, `code` or `mixed`; for a Focused scope, count the named files the same way.)
**Pre-flight:** Check AGENTS.md — use conventions if found, note if missing. Determine review target from user prompt or conversation context. If neither provides clear signal, scan and use `ask_user_question` (Step 1) — never guess.
3.**Standalone, nothing named** — do not assume a target. Do a quick scan (no file reading): `review-scope.mjs`, `specs.mjs list`, recent commits. Then ask what to review (`ask_user_question`; a `choice` on the console, scope questions up front), offering only options the scan supports, each with its size: the branch's changes vs base (files, ~lines, `commits`), uncommitted changes only (when any), a spec/plan under `specs/` (when any), a named subsystem or full codebase, or specific files/folders (free text via Other). Recommend the likeliest first. Nothing found (`empty: true`, no specs)? Ask for files or a subsystem. Use the answer as the scope, then continue.
4.**Scan details** — `review-scope.mjs` diffs the branch against its base (`main`, else `master`, or `--base`) plus staged, unstaged and untracked changes: `files`, `counts`, `commits`, `mix`, `batchByRisk`. `empty: true` or exit 3 `not-a-repo`? Ask user what to review. Exit 3 `no-base`? Rerun with `--base <trunk>`, asking which branch is the trunk if unclear.
**Who reviews:** when your tool can start a helper (subagent) and helpers are not switched off for this skill run, fill references/reviewer-brief.md and hand the analysis to ONE fresh helper; do not analyze in parallel. The brief carries the review-depth references, the dimensions and the finding format: send only the filled brief. With no helper, or one that fails or returns nothing usable, run this step in this session.
Group by severity (Critical first). For 15+ findings, present top 10 by severity, list rest as one-line bullets.
**Adversarial self-check:**
Read references/false-positives.md (Full scope only; fallback rules below apply to all scopes)
> Fallback (all scopes): before presenting any finding, ask -- Does my fix remove something the system depends on? Am I optimizing for the wrong metric?
Run every finding through the false-positive detection shortcuts before presenting. Drop findings that fail.
**Helper's findings:** when a helper ran the analysis, open every finding's cited `file:line` yourself and confirm it with verification-protocol.md and the false-positive shortcuts (fallback above). Drop any you cannot confirm; adjust severity if needed, never add unverified findings. Note how many you dropped for the report.
**Reviewed by:** a fresh helper (N findings checked, M dropped) · or this session (helpers off) · or this session (this tool cannot start helpers) · or this session (helper failed). In-session, add once: this review was not independent of the work it reviewed.
Render this section only when the session is over: fix options resolved (fixes applied and verified, or user declined) or the review had zero findings. Step 5 ends at fix options — stop there and wait.
**Next step** — suggest what genuinely helps next. Principles to reason from, not a lookup table — adapt; when a case doesn't fit cleanly, say what you verified and ask.
> Fallback: route plan2code artifacts (plan/spec docs/phases) on the reviewed feature's own `specs/<feature>/` state to the earliest unmet pipeline stage whose input exists — `PLAN-*` or `overview.md` without `phase-*.md` → `/plan2code-2-document`; unchecked `- [ ]` phase tasks → `/plan2code-3-implement`; all checked → `/plan2code-4-finalize`; archived → complete, summary only. Read the state with `specs.mjs status <spec>` (gitignored `specs/` defeats search tools). Non-pipeline artifacts (code/PRs/docs/logs) → summary only. Unresolved Criticals → fixing them (H/A/S) is the next step. Ambiguous or multiple candidate specs → ask one targeted question. Output: "Next (NEW conversation): `/plan2code-<step>` — [why + how you know]", appending ` --web` when the routed step offers the web console; else "Review complete -- [summary]."
- **Commit** (code changes): the `command` from `commit-msg.mjs --subject "fix: [desc]" --files <file>` repeated once per fixed file. On Windows PowerShell 5.1 (no `&&`), give `add` and `commit` as two commands.