메뉴
Use when scout-report.md exists and TDD/Build hasn't started yet. Runs four lenses (CEO, Eng, Design, Security) in parallel on the task list and produces a verdict (PROCEED, REVISE, ABORT) before code is written. Catches misaligned plans before they cost cycles.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when the user invokes /evo:loop or asks to run autonomous improvement cycles, self-evolving development, compound discovery, or multi-cycle code improvement with research, build, audit, and learning phases
Use after build has produced build-report.md. Validates the build via four parallel sub-auditors (eval-replay, lint, regression, build-quality) and produces ALL-PASS verdict. Adversarial mode default-on per CLAUDE.md.
Use when the user asks to explain how a feature/subsystem works and how the loops built it, or what the concurrent loops/lanes/cycles did and why. Default output = per-FEATURE HTML explainer pages (two movements — how it works today, then how it got built, with verified file:line claims and drift callouts) under docs/explain/; per-batch/per-lane story pages are the fallback framing. Derived from geoffreylitt/explain-diff-html, customized for evolve-loop.
Use when writing or changing any production code or tests — new features, bug fixes, refactors, or test authoring, in any language, by any model on any CLI.
Use when running any LLM agent below Fable 5 — Claude (Opus/Sonnet/Haiku), GPT via codex, Gemini via agy, or local models via ollama — to adopt Fable 5's operating discipline — evidence-first investigation, premise verification, root-cause-only fixes, adversarial self-review, calibrated autonomy, and honest failure reporting. Load at session start or as a persona overlay for phase agents on any CLI.
Use after ship completes. Three sub-reflectors (instinct, gene, failure) run in parallel to extract lessons, update gene pool, and analyze any failures. Off the latency-critical path.
| name | plan-review |
| description | Use when scout-report.md exists and TDD/Build hasn't started yet. Runs four lenses (CEO, Eng, Design, Security) in parallel on the task list and produces a verdict (PROCEED, REVISE, ABORT) before code is written. Catches misaligned plans before they cost cycles. |
Sprint 2 multi-lens review (v8.16+). Inspired by
garrytan/gstack/autoplan. Default-off; enable viaworkflow.phase_enables.plan-review=onin policy.json.
<workspace>/scout-report.md, before TDD/Build| Step | Action | Exit criteria |
|---|---|---|
| 1 | Verify <workspace>/scout-report.md exists + fresh | scout-report.md valid |
| 2 | Dispatch 4 lenses in parallel via subagent-run.sh dispatch-parallel plan-reviewer | 4 worker artifacts |
| 3 | Aggregator computes verdict (PROCEED/REVISE/ABORT) | <workspace>/plan-review-report.md present, first line is Verdict: <X> |
| 4 | Phase gate gate_plan_review_to_tdd enforces verdict | Gate passes only on PROCEED |
| Verdict | Trigger | Orchestrator action |
|---|---|---|
PROCEED | Avg score ≥ 7 AND no lens < 5 | Advance to TDD |
REVISE | Avg ≥ 5 AND any lens < 5 | Re-run Scout (max 2 retries) |
ABORT | Any lens explicit ABORT, OR avg < 5 | End cycle |
First line Verdict: <X>, second Average Score: <N.N>, then per-lens reports.
| Fact | Value |
|---|---|
| Phase | plan-review (plan archetype, optional, gated by workflow.phase_enables.plan-review=on) |
| Persona | agents/plan-reviewer.md |
| Profile | .evolve/profiles/plan-reviewer.json — CLI claude-tmux, tier deep, fan-out ×4 |
| Inputs | scout-report.md · triage-report.md |
| Artifact | plan-review-report.md (cycle workspace) |
plan-review-report.md — no required sections (classified by the phase runner).
Invoked by:
/evo:plan-reviewloop macro (between Scout and TDD when workflow.phase_enables.plan-review=on)The plan-reviewer persona uses parallel_subtasks (see .evolve/profiles/plan-reviewer.json) — the lens sub-personas (count projected into Phase facts above) run concurrently and merge via aggregator.sh phase=plan-review.
.evolve/profiles/plan-reviewer.json for lens prompt templateslegacy/scripts/dispatch/aggregator.sh plan-review merge modelegacy/scripts/lifecycle/phase-gate.sh:gate_plan_review_to_tdddocs/architecture/tri-layer.md (anti-patterns)