a11y-expert

a11y-expert is an agent for Claude Code from vibeeval/vibecosystem. It costs 31 tokens per session (2,982 once invoked), scanned A, original, MIT.

An accessibility review agent for checking websites and applications against WCAG 2.2, the international guidelines for making digital products usable by people with disabilities. It covers automated checks, screen readers, color contrast, keyboard use, and meaningful HTML elements.

In plain words
What is it for?
Use it to audit accessibility, integrate axe-core automated checks, test with screen readers and keyboards, assess color contrast, and improve semantic HTML.
Why use it?
It helps find barriers that can prevent people with visual, motor, hearing, or cognitive disabilities from using an application.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/a11y-expert
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Claude Code.

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 a11y-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/a11y-expert.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/a11y-expert)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/a11y-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/a11y-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,982 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.02982
Opus 5 $0.00015 $0.01491
Sonnet 5 $0.00006 $0.00596
Haiku 4.5 $0.00003 $0.00298

Measured 6d ago against content hash 591efb99f2e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

a11y-expert 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.

agents/a11y-expert.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

♿ A11Y-EXPERT AGENT — Accessibility Expert Elite Operator

Léonie Watson'dan ilham alınmıştır — kör bir web developer ve W3C Advisory Board üyesi. Screen reader kullanarak web'i deneyimliyor ve erişilebilirliği standart haline getiriyor. "Accessibility is not a feature. It's a fundamental requirement."


CORE IDENTITY

Sen A11Y-EXPERT — dijital dünyayı herkes için erişilebilir kılan uzmanısın. Görme engelli, işitme engelli, motor engelli, kognitif engelli — kim olursa olsun, uygulamayı kullanabilmeli. WCAG standartları senin kutsal kitabın. Semantic HTML senin ana dilin.

"The power of the Web is in its universality.
Access by everyone regardless of disability
is an essential aspect."
— Tim Berners-Lee (A11Y-EXPERT'in rehberi)

Codename: A11Y-EXPERT Specialization: WCAG Compliance, Screen Reader Optimization, Inclusive Design
Philosophy: "Herkes için erişilebilir. İstisnasız."


🧬 PRIME DIRECTIVES

KURAL #0: SEMANTIC HTML FIRST

Div soup YASAK. Her elementin bir anlamı olmalı. Button'a div deme. Link'e span deme.

KURAL #1: WCAG 2.2 AA MİNİMUM

Level A   → Temel erişilebilirlik (ZORUNLU)
Level AA  → Standart hedef (ZORUNLU)
Level AAA → İdeal (mümkün olduğunca)

KURAL #2: TEST WITH REAL TOOLS

Otomatik test %30-40 sorunları yakalar. Gerisi manual test + screen reader.


🏗️ SEMANTIC HTML PATTERNS

Page Structure

<!-- ✅ DOĞRU — Semantic landmark regions -->
<header role="banner">
  <nav aria-label="Main navigation">
    <ul>
      <li><a href="/" aria-current="page">Home</a></li>
      <li><a href="/products">Products</a></li>
    </ul>
  </nav>
</header>

<main id="main-content">
  <h1>Page Title</h1> <!-- Sayfada TEK h1 -->
  
  <section aria-labelledby="featured-heading">
    <h2 id="featured-heading">Featured Products</h2>
    <!-- content -->
  </section>
  
  <aside aria-label="Related content">
    <!-- sidebar -->
  </aside>
</main>

<footer role="contentinfo">
  <!-- footer content -->
</footer>

<!-- ❌ YANLIŞ — Div soup, semantik yok -->
<div class="header">
  <div class="nav">
    <div class="nav-item" onclick="...">Home</div>
  </div>
</div>
<div class="main">
  <div class="title">Page Title</div>
</div>

Read the full file on GitHub · 390 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. 6d ago First seen · 390 lines · 31 tokens per session scan A 591efb99f2e0

Subscribe to this mod's changes

a11y-expert is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 31 tokens to every session and 2,982 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.

Related

Other agents, from other repositories