a11y-audit

a11y-audit is a skill for Claude Code from viknesh20-20/claude-code-tool-kit. It costs 68 tokens per session (2,614 once invoked), scanned A, original, MIT.

A checklist and review process for finding accessibility problems in user interfaces against WCAG 2.1 Level AA, a widely used standard for making websites usable by people with disabilities. It checks both source code and running sites.

In plain words
What is it for?
Checking a UI before release, investigating an accessibility complaint, or reviewing findings from tools such as axe or Lighthouse.
Why use it?
Automated tools catch only some accessibility issues. This review looks for problems such as keyboard access, focus, contrast, labels, alternative text, and screen-reader behavior, then ranks them and suggests fixes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Checking a UI before release, investigating an accessibility complaint, or reviewing findings from tools such as axe or Lighthouse.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/viknesh20-20/claude-code-tool-kit/a11y-audit
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 viknesh20-20/claude-code-tool-kit --skill a11y-audit
Clone the repo
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kit

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/a11y-audit.svg)](https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/a11y-audit)
Your own site
<a href="https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/a11y-audit"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/a11y-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,614 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 $0.00068 $0.02614
Opus 5 $0.00034 $0.01307
Sonnet 5 $0.00014 $0.00523
Haiku 4.5 $0.00007 $0.00261

Measured 7d ago against content hash dc7add008f80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

a11y-audit 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 7d 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.

.claude/skills/a11y-audit/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/a11y-audit

Walk a UI for accessibility issues against WCAG 2.1 Level AA — the legal bar in most jurisdictions and the right bar everywhere. Output is a severity-graded list with concrete code fixes, not a generic "improve accessibility" lecture.

When to use

  • Before shipping any new UI to production.
  • Before a launch in EU / UK (European Accessibility Act applies June 2025).
  • Before any government / education / healthcare deal — those usually require Section 508 / EN 301 549.
  • After axe-core or Lighthouse flagged issues and you want a complete walk, not just the automated catches.
  • When the user reports a specific accessibility complaint.

Operating method

1. Confirm scope

  • What's the target? Source code (/path/to/component.tsx), a route URL, a running app, or all of the above.
  • What WCAG level? Default AA. AAA only if the user explicitly asks (some criteria have meaningful trade-offs at AAA).
  • What user agents matter? Default: latest Chrome, Safari, Firefox + VoiceOver (Mac/iOS), NVDA (Windows). Add more if the user serves specific audiences.

2. Run the deterministic scans first

Whenever feasible:

  • axe-core via Playwright or browser extension on every route.
  • Lighthouse accessibility audit (Chrome DevTools or lhci).
  • html-validate on rendered output to catch invalid markup that screen readers misinterpret.
  • Color-contrast checker (axe / Stark / WCAG Contrast Checker) on every text/bg pair.

Capture the output. The automated tools catch ~30% of issues — necessary but not sufficient.

3. Walk WCAG 2.1 AA by relevant criteria

These are the criteria that come up in 90% of audits. Walk each that applies.

Perceivable

1.1.1 Non-text Content (A)

  • Every meaningful image has alt. Decorative images have alt="".
  • Icons that convey meaning have aria-label or accompanying text.
  • Charts/graphs have a text alternative or detailed description.

1.3.1 Info and Relationships (A)

  • Form labels associated via <label for=…> or aria-labelledby.
  • Tables use <th> with scope.
  • Headings in order, no skipped levels.
  • Lists marked up as <ul> / <ol>, not styled <div>s.

Read the full file on GitHub · 251 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. 7d ago First seen · 251 lines · 68 tokens per session scan A dc7add008f80

Subscribe to this mod's changes

a11y-audit is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 2,614 once invoked, about $0.0003 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 skills, from other repositories

frontend-design

Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.

Hmbown/CodeWhale · 21 tokens

frontend-design

Use this as the design-lead layer for VideoStudio COMPOSE work. It shapes project/composition/composition-manifest.json::artdirection and the model-authored HTML/SVG motion graphics in index.html.

Orkas-AI/Orkas · 2 tokens

ui-design-contract

Use this skill before rendering when the direction must persist across multiple screens/components, brand or system work, conflicting references, formal handoff, or a genuinely vague visual system. Ordinary single-screen screenshots and clear briefs use ui-design-executor's compact source/visual thesis instead of…

Orkas-AI/Orkas · 3 tokens

ui-design-source

Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live Figma runtime.

Orkas-AI/Orkas · 3 tokens

design-system-importer

Use this when COMPOSE or an AUTO compose segment has any external reference media or style source: a reference image, reference video, DESIGN.md, brand guide, screenshot, existing website, design notes, or an explicit named visual direction.

Orkas-AI/Orkas · 4 tokens

ui-design-system

Use this skill when creating, extending, or auditing a product UI system. It adapts Better Design-style design-system discipline without requiring an external runtime package.

Orkas-AI/Orkas · 3 tokens