菜单
Pre-landing code review. Finds bugs that pass CI but break in prod. Runs after implementation and before ship. Maps to Gate ② (mutual review) for code artifacts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | review |
| description | Pre-landing code review. Finds bugs that pass CI but break in prod. Runs after implementation and before ship. Maps to Gate ② (mutual review) for code artifacts. |
구현이 끝난 diff 를 착륙 전 최종 검토 하는 skill. Gate ② 의 실제 운영자.
runtime.json → gates.implementation_verified == trueship 전 마지막 점검Implement.md 의 validation loop 가 먼저).claude/sealed-prompts/review-code.md 를 따른다. 아래는 운영 가이드.
claude 면 reviewer 는 user 또는 isolated claude-reviewer 세션.claude/test-runs/run-*.log.claude/learnings.jsonl 마지막 20줄review-code.md 의 7가지 항목을 explicit 하게 확인:
구현 + 테스트가 같은 커밋 에서 바뀌면 red flag. reviewer 는:
revisepython3 scripts/harness/event_log.py 02 pass <reviewer-actor> <reviewed-file> <<JSON
{
"reviewer_file": ".claude/reviews/<ts>.md",
"summary": "<verdict + top finding>",
"reviewed_file": "<path>",
"verdict": "accept|revise|reject"
}
JSON
review-code.md sealed prompt 형식 그대로 .claude/reviews/<ts>.md 에
작성. 주요 섹션:
<INSUFFICIENT_OBJECTIONS> 로 stop.claude/sealed-prompts/review-code.mdgit diff)Plan.md (원래 scope 와 일치하는지)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.