Borrowing it
Nothing to install: this file belongs to silverThunder09/jdsnack-agent-os-project. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/silverThunder09/jdsnack-agent-os-project/main/.agents/skills/review-loop/SKILL.mdgit clone --depth 1 https://github.com/silverThunder09/jdsnack-agent-os-projectWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/silverthunder09/jdsnack-agent-os-project/review-loop)<a href="https://agentmods.dev/skills/silverthunder09/jdsnack-agent-os-project/review-loop"><img src="https://agentmods.dev/badge/skills/silverthunder09/jdsnack-agent-os-project/review-loop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/silverthunder09/jdsnack-agent-os-project/review-loop"><img src="https://agentmods.dev/badge/skills/silverthunder09/jdsnack-agent-os-project/review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.01146 |
| Opus 5 | $0.00058 | $0.00573 |
| Sonnet 5 | $0.00023 | $0.00229 |
| Haiku 4.5 | $0.00012 | $0.00115 |
Grade A, and why
review-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-loop (Codex = 게이트키퍼)
역할 분담: Codex는 리뷰·판정·PR·merge만, Codex는 코딩·수정·푸시만 담당합니다.
이 스킬은 Codex 쪽 오케스트레이터입니다. Codex는 소스 코드를 직접 수정하지 않습니다. 4점 미만이면 변경요청을 만들어 Codex에 넘기고, 푸시되면 다시 리뷰합니다.
규칙 정본은 .agent-os/이며 여기서 재서술하지 않습니다.
0. 전제
- Codex가 에이전트 코딩을 끝내고 작업 브랜치에 커밋·푸시한 상태여야 함.
- 위험도·PR 흐름은
.agent-os/operations/pr-automation-loop.md를 따름.
1. 결정론 게이트 (LLM 호출 전 — 실패 시 리뷰 토큰 0)
Codex가 검증 목적으로 실행. 하나라도 실패하면 리뷰를 시작하지 않고 2번 형식의 변경요청을 만들어 Codex에 넘김:
- diff 줄수 한도 — 변경 1,000줄 초과면 PR 분할을 Codex에 요구하고 중단.
git diff --stat origin/main...HEAD합계(또는gh pr diff <N> | wc -l) 확인. - backend 변경 시 —
cd backend && ./gradlew test - frontend 변경 시 —
cd frontend && npm run lint && npm test - 셋 다 통과해야 2단계로 진행. (게이트용 재실행은 Codex가 수행, 코드 수정은 하지 않음)
2. 리뷰 핸드오프 루프 (최대 5회)
attempt = 1로 시작. 각 회차:
- diff 추출 — 로컬이면
git diff origin/main...HEAD, PR이면gh pr diff <N>. - code-reviewer 서브에이전트 호출 — 입력은 오직:
- 위 diff
- 대상 spec의
acceptance-criteria.md/test-scenarios.md경로 attempt > 1이면 직전 회차 findings 중 미해결분(델타)만- 전체 레포·
.agent-os전체·대화 전사를 넣지 말 것.
- 점수 분기:
score ≥ 4→ 루프 종료(통과). 3단계로.score < 4→ Codex는 수정하지 않는다. code-reviewer의 findings를 그대로 Codex용 변경요청으로 정리해 출력:
이후 Codex가 같은 브랜치에서 수정·커밋·푸시한다. 푸시 완료를 확인하면→ Codex 변경요청 (attempt N) score: N/5 수정 항목(blocker/major 우선): - 파일:라인 — 무엇을 어떻게 고쳐야 하는가attempt += 1후 1번(결정론 게이트 포함)부터 재리뷰. 재리뷰는 델타만 평가.
- 시도 소진 —
attempt == 5인데도score < 4면 루프 중단. 자동 merge 금지:- 마지막 점수·미해결 findings를 사용자에게 에스컬레이션.
pr-automation-loop.md기준 실패 Issue 생성 여부 판단.
3. 통과 후 (Codex 담당)
- PR 생성/갱신은 Codex가 수행. High-risk PR은
scripts/pr-review-gate.sh <N>와merge-rules.md머지 조건을 따름. - 통과 점수·회차 수를 PR 본문 검증 섹션에 한 줄로 기록.
- merge도 Codex가 수행.
경계 규칙 (반드시 준수)
- Codex는 소스 코드를 수정/커밋하지 않는다. 수정의 주체는 항상 Codex.
- 리뷰어에 diff + 합격기준 + 루브릭만 전달. 레포 전체 주입 금지.
- 회차 간에는 델타(미해결 findings)만 넘기고 누적 전사 금지.
- 외부 리뷰 봇(Greptile 등)을 같이 쓰면 이 로컬 루프와 둘 중 하나만 매 회 실행.
- 리뷰어 출력은
code-reviewer의 구조화 형식만 허용. 산문 리뷰 금지.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +3 tokens per session 9e965361baf0
- 8d ago First seen · 61 lines · 113 tokens per session scan A 760d93396c1d
review-loop is a skill published in the GitHub repository silverThunder09/jdsnack-agent-os-project (5 stars, last pushed 5d ago), licensed MIT. It adds 116 tokens to every session and 1,146 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
test-review
You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.
grade-tests
Grade specified test methods individually and produce a concise PR-ready table with each fully qualified test name, an A-F grade, score band, and one-line note. USE FOR per-test feedback on a curated list such as new or modified tests in a pull request, not a suite-wide audit. Polyglot: .NET, Python, TS/JS, Java, Go…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
refactor
Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.