accessibility-checker

accessibility-checker is a skill for Claude Code, Codex from khalilbenaz/claude-skills-collection. It costs 86 tokens per session (1,859 once invoked), scanned A, original, MIT.

A guide to checking websites against accessibility standards such as WCAG, which describe how people with disabilities should be able to use web pages. It covers automated checks and keyboard review.

In plain words
What is it for?
Use it to audit pages, check keyboard navigation and visible focus, review color contrast and ARIA usage, and add accessibility checks to development workflows.
Why use it?
It helps find problems that can block screen-reader users, keyboard users, or people with limited vision from using a site.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to audit pages, check keyboard navigation and visible focus, review color contrast and ARIA usage, and add accessibility checks to development workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/khalilbenaz/claude-skills-collection/accessibility-checker
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.

Any agent
npx skills add khalilbenaz/claude-skills-collection --skill accessibility-checker
Clone the repo
git clone --depth 1 https://github.com/khalilbenaz/claude-skills-collection

Made for: Claude Code, Codex.

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 accessibility-checker

README.md
[![agentmods](https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/accessibility-checker/github.svg)](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/accessibility-checker)
Your own site
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/accessibility-checker"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/accessibility-checker/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 accessibility-checker

Your own site · 80×15
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/accessibility-checker"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/accessibility-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,859 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 98
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00086 $0.01859
Opus 5 $0.00043 $0.00929
Sonnet 5 $0.00017 $0.00372
Haiku 4.5 $0.00009 $0.00186

Measured 8d ago against content hash ba5ad00c947c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

accessibility-checker 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 8d 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.

dev-skills/accessibility-checker/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Checker

Workflow en étapes

1. Audit automatisé — base de départ

Lancer les outils automatisés pour couvrir ~30-40 % des problèmes détectables :

# axe-core CLI (Node)
npx axe http://localhost:3000 --tags wcag2aa --reporter json > axe-report.json

# pa11y (CI-friendly)
npx pa11y http://localhost:3000 --standard WCAG2AA --reporter json

# Lighthouse (headless)
npx lighthouse http://localhost:3000 --only-categories=accessibility --output json --quiet

Critère de décision : score Lighthouse >= 90 ET zéro violation axe critical/serious avant merge.

2. Navigation clavier (manuelle, ~5 min)

Parcourir la page uniquement au clavier (Tab / Shift+Tab / Enter / Espace / Flèches).

Checklist :

  • Focus visible sur chaque élément interactif (ne pas faire outline: none sans alternative)
  • Ordre de tab logique — suit le flux visuel de gauche à droite, haut en bas
  • Skip link présent et fonctionnel (<a href="#main-content" class="skip-link">Aller au contenu</a>)
  • Aucun keyboard trap (modale fermable avec Echap, focus retourné à l'élément déclencheur)
  • Composants custom (datepicker, slider) utilisables sans souris
/* Focus visible minimal — ne jamais supprimer sans remplacement */
:focus-visible {
  outline: 3px solid #005fcc;
  outline-offset: 2px;
}

3. Sémantique HTML et landmarks

<!-- Structure minimale correcte -->
<header role="banner">…</header>
<nav aria-label="Navigation principale">…</nav>
<main id="main-content">
  <h1>Titre de la page</h1>   <!-- Un seul h1 par page -->
  …
</main>
<footer role="contentinfo">…</footer>

Pièges fréquents :

  • Sauts de niveau de titre (h1h3) : interdit
  • Plusieurs <main> sans hidden sur les inactifs
  • <div> et <span> cliquables sans role ni tabindex

4. ARIA — règle d'or

Utiliser ARIA uniquement si le HTML natif ne peut pas exprimer le comportement.

<!-- MAL : ARIA redondant -->
<button role="button" aria-label="Envoyer">Envoyer</button>

<!-- BIEN : HTML natif seul -->
<button type="submit">Envoyer</button>

<!-- BIEN : ARIA nécessaire (état dynamique) -->
<button aria-expanded="false" aria-controls="menu-id">Menu</button>
<ul id="menu-id" hidden>…</ul>

<!-- Live region pour les notifications -->
<div role="status" aria-live="polite" aria-atomic="true">
  <!-- Injecté dynamiquement par JS après action utilisateur -->
</div>

Read the full file on GitHub · 207 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. 8d ago First seen · 207 lines · 86 tokens per session scan A ba5ad00c947c

Subscribe to this mod's changes

accessibility-checker is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 86 tokens to every session and 1,859 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 2026-09-03.