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/ramsbaby/jarvis/reviewgit clone --depth 1 https://github.com/Ramsbaby/jarvisWrote 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/ramsbaby/jarvis/review)<a href="https://agentmods.dev/commands/ramsbaby/jarvis/review"><img src="https://agentmods.dev/badge/commands/ramsbaby/jarvis/review.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 5.1 | $0.00042 | $0.00947 |
| Opus 5 | $0.00021 | $0.00474 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
코드 리뷰 (Dev + Reviewer Agent)
현재 작업한 코드를 Reviewer 관점에서 검토합니다.
리뷰 프로세스
코드 확인 → 체크리스트 검토 → 이슈 리포트 → 수정 → 재검토
1단계: 변경 사항 파악
# 스테이징된 변경
git diff --cached --stat
# 전체 변경
git diff --stat
# 최근 커밋 (아직 안 커밋했다면 스킵)
git log --oneline -5
변경된 모든 파일을 읽고 분석합니다.
2단계: 리뷰 체크리스트
일반 코드 품질
| # | 항목 | 확인 |
|---|---|---|
| 1 | 로직 오류 없는가 | |
| 2 | 엣지케이스 처리했는가 | |
| 3 | null/undefined 안전한가 | |
| 4 | 에러 핸들링 적절한가 | |
| 5 | SSoT(Single Source of Truth) 위반 없는가 | |
| 6 | DRY(Don't Repeat Yourself) 위반 없는가 | |
| 7 | 명명 규칙 일관적인가 | |
| 8 | 불필요한 코드/주석 없는가 | |
| 9 | 보안 취약점 없는가 (OWASP Top 10) | |
| 10 | 하드코딩된 비밀값 없는가 |
Shell Script 특화
| # | 항목 | 확인 |
|---|---|---|
| 1 | set -euo pipefail 설정했는가 |
|
| 2 | 변수 따옴표 처리 ("$var") |
|
| 3 | 임시 파일 cleanup (trap) | |
| 4 | 경로에 공백 대응 | |
| 5 | exit code 적절한가 |
OpenClaw 특화
| # | 항목 | 확인 |
|---|---|---|
| 1 | watchdog 안전성: 무한루프 가능성 없는가 | |
| 2 | Gateway 재시작 시 Grace Period (30초) 준수하는가 | |
| 3 | launchd plist: KeepAlive/RunAtLoad 설정 적절한가 | |
| 4 | 토큰 동기화: openclaw.json과 plist 간 불일치 없는가 | |
| 5 | 로그 경로: ~/.openclaw/logs/ 사용하는가 | |
| 6 | Discord 알림: 연속 실패 임계치(3회) 준수하는가 | |
| 7 | jq: has() 키 검사 사용 (null 매칭 버그 방지) |
|
| 8 | 크론/LaunchAgent 중복 없는가 |
3단계: 이슈 리포트
발견된 이슈를 심각도별로 분류합니다:
## Review Report
### CRITICAL (즉시 수정 필요)
- [파일:줄번호] 설명
### WARNING (수정 권장)
- [파일:줄번호] 설명
### SUGGESTION (개선 제안)
- [파일:줄번호] 설명
### PASS
- 전체적으로 양호한 부분 요약
4단계: 수정 후 재검토
CRITICAL/WARNING 항목을 수정한 후 재검토합니다:
- 수정된 파일 다시 읽기
- 해당 이슈가 해결되었는지 확인
- 새로운 이슈가 발생하지 않았는지 확인
- 최종 리포트 출력
실행 방법
- 전체 리뷰: "/review" 실행
- 특정 파일: "/review [파일경로]"
- 최근 커밋: "/review --last-commit"
- 리뷰 후 자동 수정: "/review --fix"
참고 문서
- CLAUDE.md: 코딩 정책 및 컨벤션
- ~/openclaw/docs/self-healing-system.md: watchdog/gateway 아키텍처
- ~/.claude/commands/sdd.md: 스펙 주도 개발 가이드
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.
- 6d ago First seen · 119 lines · 42 tokens per session scan A 45539f9857c6
review is a command published in the GitHub repository Ramsbaby/jarvis (16 stars, last pushed 13d ago), licensed MIT. It adds 42 tokens to every session and 947 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
bm
Ask basemind anything about the current codebase — outlines, refs, callers, git history, blame, diffs, docs, memory.
bm-scan
Build or refresh the basemind index by running basemind scan via the CLI — works without the MCP server (use it when basemind reports "no index" / "no indexed files").
harden
Run the real-OSS harden harness against the 8 canary repos.
dream
Memory dream pass — judge undreamed days, promote durable signal to long-term, then sweep.
bm-doctor
Diagnose and recover basemind when it isn't working (MCP tools missing/erroring, "no index", dead server) — runs CLI checks and gives the client-specific way to reconnect the server.
status
Linggen status — binary versions + updates, memory store size, upkeep (scan/dream/solve), last dream run.