القائمة
Use after PRD is ready but before implementation. Locks architecture, data flow, edge cases, and test plan so scope cannot silently creep during build.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Explicit GPT-5.6 native-first router for auditing, designing, installing, or validating Codex skill combinations, global skill setup, routing fixtures, and harness behavior. Use when the user explicitly invokes $codex-skill-router or asks to change or inspect Codex skills, routing, AGENTS guidance, or global harness configuration. Do not use for ordinary coding, review, debugging, research, or UI work merely because the task is complex.
Use when work introduces or changes shared nouns, states, IDs, ownership, authority, or customer-facing vocabulary.
Use when changing harness gates, routing rules, skills, or automation behavior and benchmark/eval evidence is needed to avoid slowing normal coding performance. Do not use for ordinary app code changes.
Use when a request is early, ambiguous, or lacks a codebase-backed shared language; interview the user to expose assumptions before planning.
Use when a codebase, docs, ADRs, tests, prior reviews, or team traces exist; align new work with existing shared language before implementation.
Use first for normal or high-risk natural-language work to choose task mode, tier, grill path, spec layers, team-rule scan, and required gates before implementation.
| name | plan-eng-review |
| description | Use after PRD is ready but before implementation. Locks architecture, data flow, edge cases, and test plan so scope cannot silently creep during build. |
구현 시작 전에 architecture / data flow / edge cases / test plan 을 잠그는 skill. Scope freeze 직전 단계.
/office-hours 로 돌아가기Plan.md 를 적대적으로 읽고 다음을 잠근다.
명시적으로 다음을 점검:
size_check.py 로 예상 tier / complexity 확인# Plan-Eng Review — <날짜>
## Architecture verdict
- Accept / Revise
- Issues found: <list>
## Data flow verdict
- Accept / Revise
- Missing boundaries: <list>
## Edge cases checklist
- [x] empty input
- [x] large input
- [x] concurrency
- [ ] <항목> — NOT covered in plan
## Test plan verdict
- Accept / Revise
- AC → test mapping: <table>
- Risky test modifications: <list>
## Tier confirmation
- Classified: <tier> / <complexity>
- Plan says: <tier>
- Match: yes / no
## Blocking issues (must fix before scope_lock)
1. ...
## Non-blocking suggestions
1. ...
## Next gate
If Accept → `runtime_gate.py lock-scope` + `runtime_gate.py review-plan`
<INSUFFICIENT_OBJECTIONS>.lock-scope / review-plan gate flag 를 flip.planner 의 required_reviewers 역할을 수행.Plan.mdPRD.mdCLAUDE.md, AGENTS.md.claude/sealed-prompts/plan-redteam.md