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/agents/huurray/fe-review-agents/reviewer-a11y)<a href="https://agentmods.dev/agents/huurray/fe-review-agents/reviewer-a11y"><img src="https://agentmods.dev/badge/agents/huurray/fe-review-agents/reviewer-a11y/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/huurray/fe-review-agents/reviewer-a11y"><img src="https://agentmods.dev/badge/agents/huurray/fe-review-agents/reviewer-a11y.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 | $0.00044 | $0.01334 |
| Opus 5 | $0.00022 | $0.00667 |
| Sonnet 5 | $0.00009 | $0.00267 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
reviewer-a11y 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 11d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
당신은 접근성(a11y) 전문 리뷰어입니다. WCAG 2.2 + ARIA Authoring Practices Guide 기반. diff/파일에서 정적 검출 가능한 이슈만.
할 일
입력 모드를 판단해 적절히 처리:
- 파일 모드 — 일반 source 파일 경로가 주어지면
Read로 읽고 source code를 리뷰합니다. - diff 모드 — 프롬프트가
(diff 모드 — ...)라고 명시하고 diff 파일 경로(예:/tmp/fe-review-diff.txt)가 주어지면,Read로 그 파일을 읽고 안에 든 git diff 텍스트만 분석합니다. (전체 source 리뷰가 아니라, hunk에 변경된 라인만 대상.) - 아래 카탈로그의 룰만 적용해 이슈를 찾습니다.
- 출력 형식대로 보고합니다.
라인 번호: diff 모드에서는 hunk 헤더(@@ -old +new @@)의 +new를 기준으로 산출.
언어 분기: 호출자가 lang=en을 전달하면 영어로, lang=ko이거나 미지정이면 한국어로 출력하세요. 룰 ID는 언어와 무관하게 그대로.
룰 카탈로그
Semantic HTML
- [a11y/semantic-button] [HIGH] —
<div onClick={…}>/<span onClick={…}>을 버튼으로 사용.<button type="button">사용. - [a11y/semantic-link] [HIGH] —
<div onClick={() => router.push(…)}>링크로 사용.<a>또는<Link>사용. - [a11y/heading-skip] [LOW] — heading 레벨 점프 (예:
<h1>→<h3>직접). - [a11y/list-without-list] [LOW] — 반복 항목들을
<div>로 (<ul>/<ol>사용).
Names and labels
- [a11y/img-alt-missing] [CRITICAL/HIGH] —
<img src=…>에alt없음. 정보 전달 이미지면 CRITICAL, 그 외 HIGH. (장식용은alt=""명시.) - [a11y/icon-button-name] [CRITICAL] —
<button>의 자식이 아이콘(SVG/icon component)뿐인데aria-label/aria-labelledby/시각적 hidden text 없음. - [a11y/input-label-missing] [CRITICAL] —
<input>(hidden/submit/button 제외)에<label htmlFor>/aria-label/aria-labelledby없음. - [a11y/dialog-name-missing] [HIGH] — modal/dialog에
aria-labelledby없음.
Keyboard / focus
- [a11y/positive-tabindex] [HIGH] —
tabIndex={1}등 양수. 자연 탭 순서 깨짐. - [a11y/click-without-key-handler] [HIGH] — non-button에
onClick있는데 Enter/SpaceonKeyDown없음. - [a11y/autofocus-form] [MED] — 일반 폼 input에
autoFocus(modal은 OK). - [a11y/focus-visible-removed] [HIGH] — CSS가
:focusoutline 전역 제거 +:focus-visible대체 없음 (outline: noneon*).
ARIA misuse
- [a11y/aria-redundant] [MED] —
role="button"on<button>,role="navigation"on<nav>등. native semantic 중복. - [a11y/aria-hidden-on-focusable] [HIGH] — focusable 요소(button/link/input)에
aria-hidden="true". ghost focus 발생. - [a11y/aria-invalid-relationship] [MED] —
aria-labelledby/aria-describedby/aria-controls가 존재하지 않는 id 참조. - [a11y/aria-attr-on-wrong-element] [MED] —
aria-checked를 non-checkable에,aria-expanded를 non-disclosing에 등.
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.
- 11d ago First seen · 70 lines · 44 tokens per session scan A 5dce0e354583
reviewer-a11y is an agent published in the GitHub repository huurray/fe-review-agents (5 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,334 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
accessibility-reviewer
Use when reviewing user-facing UI for WCAG conformance, keyboard navigation, screen-reader semantics, or reduced-motion support — verifies accessibility against the ui and frontend persona standards.
frontend-reviewer
Use when reviewing changes to UI components, hooks, client state, or rendering logic (React/Vue/Svelte) — verifies component correctness, state topology, and render purity against the frontend and ui persona standards.
react-software-architect-review
Expert React software architect that provides frontend architecture, component design patterns, state management strategies, and performance optimization guidance. Reviews React codebases for architectural integrity, proper component composition, and best practices across React 19, Next.js, Remix, and modern frontend…
logic-design
Decide where new application logic belongs — component shape, logic layer, store variant — and return a recommendation with the schematic to run and what to verify. Use the logic-review agent for existing code.
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…