Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/ohah/react-native-mcp/review-customergit clone --depth 1 https://github.com/ohah/react-native-mcpWrote 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/commands/ohah/react-native-mcp/review-customer)<a href="https://agentmods.dev/commands/ohah/react-native-mcp/review-customer"><img src="https://agentmods.dev/badge/commands/ohah/react-native-mcp/review-customer.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00679 |
| Opus 5 | $0.00000 | $0.00340 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
review-customer 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 3d 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.
What it actually says
Pull Request 리뷰 (AI 리뷰 요약 + 인라인 제안 게시)
현재 브랜치의 PR을 가져와 AI가 코드와 설명을 리뷰한 후, **요약 리뷰 (본문)**와 라인별 제안 (인라인 댓글) 을 PR에 게시합니다.
- 요약 리뷰: 한글로 작성. 다음 구조를 따른다.
- 목적·설명 일치: PR 설명·제목이 diff와 맞는지, 범위 creep 여부.
- 개선 제안: 버그·엣지 케이스·성능·테스트·보안·프로젝트 규칙 준수. 필수 vs 권장을 구분해 제시.
- 질문/논의: 애매한 설계·트레이드오프가 있으면 질문 형태로 남긴다.
- 라인별 제안: 한글로 작성. 다음을 지킨다.
- 영향 큰 것만 인라인: 버그·잠재 오류·명확한 개선에만 인라인 댓글. 사소한 스타일·포맷은 요약 리뷰에 묶어서 언급.
- 이유 명시: "이렇게 하면 ~ 때문입니다"처럼 왜 수정하는지 한 줄 포함.
- 제안 블록: 수정안이 명확하면
```suggestion ```블록을 넣어 커밋 가능하게 한다.
- 리뷰 시 참고:
docs/guides/coding-style.md,.cursor/rules/behavioral-guidelines.mdc,AGENTS.md를 기준으로 프로젝트 규칙·스타일 준수 여부를 검토한다.
이 레포의 gh 계정 (ohah 전용)
이 레포(ohah/react-native-mcp)는 ohah GitHub 계정으로 리뷰를 게시합니다.
- 리뷰 제출 전:
gh api user -q .login으로 현재 사용자를 확인합니다.ohah가 아니면gh auth switch --hostname github.com --user ohah로 전환하고 이전 로그인을 기억합니다. - 리뷰 제출 후: ohah로 전환했다면
gh auth switch --hostname github.com --user <이전_사용자>로 복원합니다.
실행 순서
- 브랜치 및 gh 계정 확인
- 현재 브랜치의 PR 찾기
- PR 세부사항과 diff 수집
- AI 리뷰 작성 (요약 + 라인 제안) — 위 요약·라인별·리뷰 시 참고 기준을 적용
- 리뷰 제출
- gh 계정 복원
참고
- 레포 루트에서
gh인증된 상태로 실행합니다. - 현재 브랜치에 PR이 없으면 리뷰를 게시하지 않습니다.
- 인라인 댓글의
line은 diff의 새 (오른쪽) 라인 번호여야 합니다. - 제안 블록은
```suggestion과```사이에 코드를 넣어 GitHub이 "Commit suggestion"을 표시하도록 합니다.
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.
- 3d ago First seen · 37 lines · 0 tokens per session scan A 97503a82440d
review-customer is a command published in the GitHub repository ohah/react-native-mcp (7 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 679 tokens. 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.