Menu
Pre-landing code review. Finds bugs that pass CI but break in prod. Runs after implementation and before ship. Maps to Gate โก (mutual review) for code artifacts.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| 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 โก (mutual review) for code artifacts. |
๊ตฌํ์ด ๋๋ diff ๋ฅผ ์ฐฉ๋ฅ ์ ์ต์ข ๊ฒํ ํ๋ skill. Gate โก ์ ์ค์ ์ด์์.
runtime.json โ gates.implementation_verified == trueship ์ ๋ง์ง๋ง ์ ๊ฒImplement.md ์ validation loop ๊ฐ ๋จผ์ ).claude/sealed-prompts/review-code.md ๋ฅผ ๋ฐ๋ฅธ๋ค. ์๋๋ ์ด์ ๊ฐ์ด๋.
claude ๋ฉด reviewer ๋ user ๋๋ isolated claude-reviewer ์ธ์
.claude/test-runs/run-*.log.claude/learnings.jsonl ๋ง์ง๋ง 20์คreview-code.md ์ 7๊ฐ์ง ํญ๋ชฉ์ explicit ํ๊ฒ ํ์ธ:
๊ตฌํ + ํ ์คํธ๊ฐ ๊ฐ์ ์ปค๋ฐ ์์ ๋ฐ๋๋ฉด red flag. reviewer ๋:
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 ํ์ ๊ทธ๋๋ก .claude/reviews/<ts>.md ์
์์ฑ. ์ฃผ์ ์น์
:
<INSUFFICIENT_OBJECTIONS> ๋ก stop.claude/sealed-prompts/review-code.mdgit diff)Plan.md (์๋ scope ์ ์ผ์นํ๋์ง)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.