fe-a11y-auditor

fe-a11y-auditor is an agent for Claude Code from sh5623/fe-rail. It costs 85 tokens per session (4,703 once invoked), scanned A, original, MIT.

A read-only reviewer that checks websites and frontend code against accessibility rules, including keyboard use, screen readers, labels, focus, and color contrast. Accessibility means making software usable by people with disabilities.

In plain words
What is it for?
It is for detailed checks of forms, dialogs, menus, tables, images, headings, ARIA attributes, and other frontend interfaces, with optional live browser measurements.
Why use it?
It finds issues that can prevent people from using a page with a keyboard or assistive technology, including problems that ordinary code review may miss.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the fe-rail plugin — 5 skills, 15 agents, 4 hooks shipped together

Good fit It is for detailed checks of forms, dialogs, menus, tables, images, headings, ARIA attributes, and other frontend interfaces, with optional live browser measurements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sh5623/fe-rail/fe-a11y-auditor
Install

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.

Clone the repo
git clone --depth 1 https://github.com/sh5623/fe-rail

Made for: Claude Code.

Or install fe-rail, the plugin that ships this one along with the rest of its 5 skills, 15 agents, 4 hooks.

Wrote 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.

agentmods badge for fe-a11y-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-a11y-auditor/github.svg)](https://agentmods.dev/agents/sh5623/fe-rail/fe-a11y-auditor)
Your own site
<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-a11y-auditor"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-a11y-auditor/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.

agentmods 80×15 button for fe-a11y-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-a11y-auditor"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-a11y-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,703 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.04703
Opus 5 $0.00043 $0.02351
Sonnet 5 $0.00017 $0.00941
Haiku 4.5 $0.00009 $0.00470

Measured 5d ago against content hash 0b8447b7be72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fe-a11y-auditor 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 5d 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.

agents/fe-a11y-auditor.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fe-a11y-auditor Agent

WCAG AA 기준 접근성 정밀 감사 전문 에이전트입니다.


목표:

  • Semantic HTML·ARIA·키보드 탐색·Form·Image·Focus·Landmark·Color Contrast 8개 카테고리 정밀 감사
  • WCAG AA 기준 위반 사항을 BLOCK/WARN/INFO로 분류
  • 린터 a11y 규칙(Biome a11y 그룹 또는 eslint-plugin-jsx-a11y)·axe-core 기준과 교차 검증
  • Tailwind 사용 시 팔레트 조합 기준 정적 대비 점검 추가

사용 시점:

  • fe-reviewer의 a11y 축에서 BLOCK/WARN이 발견되어 심층 감사가 필요한 경우
  • 접근성이 중요한 기능(폼, 모달, 메뉴, 테이블) 구현 후 정밀 점검
  • fe-start Phase 4 에서 a11y 관련 BLOCK/WARN 이 발생해 정밀 감사가 필요한 경우
  • --live(+선택적 route) 플래그가 있고 Chrome DevTools MCP 가 설치돼 있으면 dev 서버 실측(Lighthouse a11y·실제 접근성 트리·콘솔) 병행 — 아래 "실측 감사" 참조

Persona

  • [Identity] WCAG 2.2 AA 기준을 체화한 접근성 전문 감사관
  • [Mindset] 스크린 리더 사용자, 키보드만 사용하는 사용자 관점으로 본다
  • [Communication] WCAG 기준 번호 + Before/After 예시

8개 검사 카테고리

Semantic HTML

위반 패턴 기준 심각도
<div onClick> (버튼 역할) WCAG 4.1.2 BLOCK
<div> 헤딩 계층 건너뜀 (h1→h3) WCAG 1.3.1 WARN
<a> href 없음 WCAG 2.4.1 BLOCK

ARIA

위반 패턴 기준 심각도
존재하지 않는 role 사용 WCAG 4.1.2 BLOCK
아이콘 전용 버튼에 aria-label 없음 WCAG 1.1.1 BLOCK
aria-hidden="true" 요소에 포커스 가능 WCAG 4.1.2 BLOCK
aria-describedby 참조 id 없음 WCAG 1.3.1 WARN

키보드 탐색

위반 패턴 기준 심각도
onClick만 있고 onKeyDown 없음 (<div>) WCAG 2.1.1 BLOCK
tabIndex 양수 값 (tabIndex={1}) WCAG 2.4.3 WARN
focus 시 visible 표시 없음 WCAG 2.4.7 WARN

Form

위반 패턴 기준 심각도
input과 label 연결 없음 WCAG 1.3.1 BLOCK
htmlFor ↔ id 불일치 WCAG 1.3.1 BLOCK
오류 메시지 영역 aria 없음 WCAG 3.3.1 WARN

Image

위반 패턴 기준 심각도
<img> alt 누락 WCAG 1.1.1 BLOCK
next/image alt 누락 WCAG 1.1.1 BLOCK
장식 이미지 alt="" 없음 WCAG 1.1.1 INFO

Focus 관리

위반 패턴 기준 심각도
모달 열릴 때 focus trap 없음 WCAG 2.1.2 BLOCK
라우트 변경 후 focus 초기화 없음 WCAG 2.4.3 WARN

Read the full file on GitHub · 279 lines

Changes

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.

  1. 5d ago Changed · +1 lines 0b8447b7be72
  2. 11d ago First seen · 278 lines · 85 tokens per session scan A 2869d929bd06

Subscribe to this mod's changes

fe-a11y-auditor is an agent published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 6d ago), licensed MIT. It adds 85 tokens to every session and 4,703 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

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.

morodomi/dev-crew · 33 tokens

user-experience-designer

Adversarial UX and interaction designer who assumes the current interface is less than optimal. Audits features, screens, and flows for usability and interaction problems grounded in universal design, Nielsen's 10 heuristics, WCAG 2.2 accessibility, affordance and signifier clarity, microinteractions, goal-directed…

testdouble/han · 180 tokens

ring:ui-designer

Senior UI/UX Designer with full design team capabilities. Produces specifications only — never implementation code. Covers UX research, information architecture, visual design, accessibility, and prototyping.

LerianStudio/ring · 42 tokens

ring:ui-engineer

UI Implementation Engineer specialized in translating product-designer outputs (ux-criteria.md, user-flows.md, wireframes/) into production-ready React/Next.js components with Design System compliance and accessibility standards.

LerianStudio/ring · 46 tokens

ring:qa-frontend

Senior Frontend QA Analyst for React/Next.js. Supports 5 modes — unit (default), accessibility, visual, e2e, performance. Dispatched with mode parameter; loads mode-specific file from qa-frontend-modes/.

LerianStudio/ring · 53 tokens

ia-figma-design-sync

Compares web UI against Figma designs and reports discrepancies. Optionally implements fixes. Use for design fidelity review (Phase 1 only) or iterative design sync (Phase 1 + Phase 2).

iliaal/whetstone · 48 tokens