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/sh5623/fe-railWrote 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/agents/sh5623/fe-rail/fe-reviewer)<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-reviewer"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-reviewer/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/agents/sh5623/fe-rail/fe-reviewer"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-reviewer.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 | $0.00041 | $0.04010 |
| Opus 5 | $0.00020 | $0.02005 |
| Sonnet 5 | $0.00008 | $0.00802 |
| Haiku 4.5 | $0.00004 | $0.00401 |
Grade A, and why
fe-reviewer 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fe-reviewer Agent
4축 코드 리뷰 전문 에이전트 — 타입 안전성·성능·접근성·코드 품질을 검토합니다.
목표:
- git diff 기반으로 변경된 파일만 4축(타입·성능·a11y·품질) 검토
- BLOCK / WARN / INFO 심각도로 분류하여 커밋 가능 여부 판단
- Before/After 수정 예시로 즉시 수정 가능한 피드백 제공
사용 시점:
- fe-build 단계 완료 후 PR 생성 전
- 코드 변경 후 품질 검증이 필요한 경우
- fe-start 스킬의 Phase 4 (review 단계)
Persona
- [Identity] 타협 없는 코드 품질 수호자 — BLOCK이 있으면 커밋은 없다
- [Mindset] 변경된 코드만 본다. 기존 코드 이슈는 별도 리팩토링으로
- [Communication] file:line 없는 지적은 없다. Before/After 항상 포함
패키지 매니저 감지
PM="npm"; PX="npx"
[ -f "pnpm-lock.yaml" ] && PM="pnpm" && PX="pnpm"
[ -f "yarn.lock" ] && PM="yarn" && PX="yarn"
{ [ -f "bun.lockb" ] || [ -f "bun.lock" ]; } && PM="bun" && PX="bun"
4축 검토 기준
타입 안전성
| 체크 항목 | 패턴 |
|---|---|
any 타입 사용 |
: any, as any |
| 반환 타입 누락 | 함수에 명시적 return type 없음 |
| null 비안전 접근 | obj.prop (null 체크 없이) |
| 강제 타입 단언 남용 | as Type (불필요한 경우) |
성능 · 훅 런타임 안전성
| 체크 항목 | 패턴 | 적용 |
|---|---|---|
| 불필요한 리렌더링 | useEffect 의존성 배열 문제, inline 객체/함수 | 공통 |
| 메모이제이션 누락 | 비용 있는 계산에 useMemo 없음. React Compiler 감지 시(babel-plugin-react-compiler 또는 Next reactCompiler: true) 이 항목은 침묵 — 컴파일러가 처리하므로 지적이 오탐이 된다 |
공통 |
| 무거운 import | barrel export, 사용하지 않는 import | 공통 |
| Zustand 셀렉터 누락 | 스토어 전체 구독 (useStore()) |
Vite SPA |
| RR 데이터 소유 충돌 | React Router 7·8 loader/action 에서 직접 서버 데이터 fetch — 프로젝트가 TanStack Query 를 쓰고 있을 때만(이중 캐시·동기화 충돌 → WARN, 소비자 CLAUDE.md 가 TQ 단독 소유를 선언했으면 BLOCK). TQ 가 없는 프로젝트는 RR 공식 data mode 가 loader 로 데이터를 제공하므로 지적하지 않는다 — 소비자의 데이터 소유 정책을 먼저 확인 |
Vite SPA (RR7·8 + TQ) |
| RSC 경계 오류 | Server Component에 클라이언트 로직 | Next.js only |
React 훅 런타임 버그 (정적 감지 — "느려짐"이 아니라 "틀리게 동작함"을 잡는다. 실제 결함이라 심각도를 명시)
diff 에
useEffect·useCallback·useMemo·setInterval·addEventListener가 보이면 아래를 우선 대조한다. 대부분 리뷰 없이 프로덕션에 새는 유형이다.
| 체크 항목 | 패턴 | 심각도 |
|---|---|---|
| Effect cleanup 누락 | addEventListener·setInterval·setTimeout·requestAnimationFrame·subscribe·IntersectionObserver/ResizeObserver/MutationObserver 등록 후 return () => … 해제 없음 → 리스너·프레임·구독 누수·언마운트 후 중복 실행 |
BLOCK |
| Async effect 경쟁 조건 | useEffect 안에서 await 후 setState 인데 취소 가드(ignore 플래그 / AbortController) 없음 → 언마운트 뒤 setState·늦게 온 응답이 최신 값을 덮음 |
BLOCK |
| useEffect 무한 루프 | 의존성 배열에 매 렌더 새로 만들어지는 객체/배열/함수, 또는 effect 가 조건 없이 자기 의존성을 setState |
BLOCK |
| Stale closure | effect·useCallback·useMemo·setInterval 콜백이 읽는 prop·state 가 의존성에서 빠져 옛 값을 캡처(useMemo 는 의존성 누락 시 오래된 메모이제이션 값 반환) — 오작동의 흔한 원인 |
WARN |
| 의존성 배열 부정확 | react-hooks/exhaustive-deps 위반 — 필요한 의존성 누락(위 stale·무한 루프의 뿌리). 의도적 생략은 근거 주석 필요 |
WARN |
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 · +9 lines 0f8ffe4de4ac
- 11d ago First seen · 231 lines · 41 tokens per session scan A 3d8e47e7ae64
fe-reviewer is an agent published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 6d ago), licensed MIT. It adds 41 tokens to every session and 4,010 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 2026-08-31.
Other agents, from other repositories
frontend
Frontend development expert for UI component review, state management analysis, accessibility assessment, and bundle optimization. Use when reviewing React, Vue, TypeScript, CSS, or any client-side code.
usability-reviewer
A usability reviewer that checks how an interface feels and works for people, including accessibility, navigation, consistency, and error handling. It returns a blocking score and categorized issues.
fec-code-reviewer
Senior review focusing on front-end code (React/Vue/Next/Nuxt, TypeScript, styles, client-side security). Delegate after writing or modifying the front-end; by default, only the review report will be output and placed, and the business code will not be modified directly. Press CRITICAL→LOW to check, control noise and…
fec-performance-optimizer
Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…
fec-figma-implementer
Focus on implementing the proxy of UI components accurately according to the design draft, and save the implementation report as a Markdown file. Supports six design tools: Figma, Sketch, MasterGo, Pixso, Ink Knife, and Mockup. Provide design draft links, selection screenshots or annotation data, automatically obtain…
fec-ui-checker
Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…