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.
git clone --depth 1 https://github.com/huurray/fe-review-agentsWrote 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/huurray/fe-review-agents/file-review)<a href="https://agentmods.dev/commands/huurray/fe-review-agents/file-review"><img src="https://agentmods.dev/badge/commands/huurray/fe-review-agents/file-review/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/commands/huurray/fe-review-agents/file-review"><img src="https://agentmods.dev/badge/commands/huurray/fe-review-agents/file-review.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 | $0.00069 | $0.00933 |
| Opus 5 | $0.00034 | $0.00466 |
| Sonnet 5 | $0.00014 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
file-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 10d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
단일 파일 다각도 리뷰. 여러 reviewer + synthesizer.
단계 0 — 인자 파싱
$ARGUMENTS에서 다음 두 옵션 토큰을 먼저 추출:
lang=ko|en(기본ko)severity_min=LOW|MED|HIGH|CRITICAL(기본LOW. 대소문자 무시 — 내부적으로 대문자로 정규화)
각 토큰의 값이 위 허용 목록에 없으면 default로 fallback하고 사용자에게 한 줄 경고를 그대로 출력 (예: severity_min=foo`는 무효 — `LOW`로 진행). 두 토큰을 제거한 나머지를 파일 경로로 사용.
만약 파일 경로가 비어있다면, 사용자에게 어떤 파일을 리뷰할지 먼저 물어본 뒤 진행하세요.
리뷰 대상 파일을 <FILE_PATH>로 지칭합니다.
단계 1 — 모든 reviewer를 병렬로 호출
반드시 하나의 어시스턴트 메시지 안에, 아래 나열된 모든 Agent 도구 호출을 한꺼번에 보내야 합니다. (순차 호출 금지)
각 reviewer에 다음 형식의 prompt를 전달 (<LANG>은 단계 0에서 결정한 언어):
파일 `<FILE_PATH>`를 [관점] 관점에서 리뷰하세요. (파일 모드 — Read 도구로 파일을 직접 읽으세요)
lang=<LANG>
각 호출의 정확한 파라미터:
Agent—subagent_type: reviewer-react-perf,description: "Perf review", [관점]="성능"Agent—subagent_type: reviewer-quality,description: "Quality review", [관점]="코드 품질"Agent—subagent_type: reviewer-bugs,description: "Bugs review", [관점]="잠재 버그"Agent—subagent_type: reviewer-ts,description: "TS review", [관점]="TypeScript 타입 안전성"Agent—subagent_type: reviewer-a11y,description: "A11y review", [관점]="웹 접근성"Agent—subagent_type: reviewer-security,description: "Security review", [관점]="보안"
중요: 위 subagent_type 이름을 정확히 그대로 사용하세요. general-purpose로 폴백하지 마세요.
단계 2 — synthesizer 호출
모든 reviewer 결과가 돌아오면 마지막으로 synthesizer를 한 번 더 Agent로 호출:
subagent_type:synthesizerdescription: "Synthesize review"prompt: 다음 형식으로 모든 reviewer 결과를 포함 (<LANG>은 단계 0에서 결정한 언어,<SEVERITY_MIN>은 단계 0에서 결정한 최소 심각도):파일 경로: <FILE_PATH> lang=<LANG> severity_min=<SEVERITY_MIN> 모든 reviewer의 결과를 종합해 중요도순 리포트를 작성해주세요. ## 1. Performance <reviewer-react-perf 출력 전문> ## 2. Code Quality <reviewer-quality 출력 전문> ## 3. Bugs <reviewer-bugs 출력 전문> ## 4. TypeScript <reviewer-ts 출력 전문> ## 5. Accessibility <reviewer-a11y 출력 전문> ## 6. Security <reviewer-security 출력 전문>
단계 3 — 사용자에게 출력
synthesizer가 반환한 마크다운 리포트를 그대로 사용자에게 보여주세요. 추가 설명/요약/메타 코멘트 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.
- 10d ago First seen · 80 lines · 69 tokens per session scan A a33cbf0817e1
file-review is a command published in the GitHub repository huurray/fe-review-agents (5 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 933 once invoked, about $0.0003 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 commands, from other repositories
critique
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.
check-architecture
Angular Architecture Review.
react-patterns
Review React code for performance and composition patterns — 50+ rules ranked by impact.
fec-review
Conduct a standardized review of the specified file or recently changed front-end code, output a graded review report and save it as a Markdown file.
web-review
Review a web (HTML5) project for structure, architecture, maintainability, and risk.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.