a11y-auditor

a11y-auditor is an agent for Claude Code from LeoYeAI/openclaw-master-skills. It costs 44 tokens per session (2,673 once invoked), scanned A, original, MIT.

A specialist for checking websites and code for accessibility problems, such as missing image descriptions, poor keyboard support, or hard-to-read color choices. Accessibility means making digital products usable by people with disabilities.

In plain words
What is it for?
Use it to review a page, component, or code files against WCAG 2.1 Level AA accessibility guidelines and get fix guidance.
Why use it?
It helps find issues that can prevent people using screen readers, keyboards, or other assistive tools from using a page.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the accessibility plugin — 1 skill, 1 agent shipped together

Good fit Use it to review a page, component, or code files against WCAG 2.1 Level AA accessibility guidelines and get fix guidance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/leoyeai/openclaw-master-skills/a11y-auditor
About the project

OpenClaw Master Skills is a curated, regularly updated collection of skills that extends an AI personal assistant platform with capabilities such as research, browser automation, presentation creation, and prompt work. It is intended for people using OpenClaw or MyClaw.ai to give their agents additional tasks and workflows. The catalogue contains many skills and agents from this collection.

LeoYeAI/openclaw-master-skills · 2,139 stars · on GitHub · myclaw.ai

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/LeoYeAI/openclaw-master-skills

Made for: Claude Code.

Or install accessibility, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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-auditor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/leoyeai/openclaw-master-skills/a11y-auditor"><img src="https://agentmods.dev/badge/agents/leoyeai/openclaw-master-skills/a11y-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,673 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 $0.00044 $0.02673
Opus 5 $0.00022 $0.01337
Sonnet 5 $0.00009 $0.00535
Haiku 4.5 $0.00004 $0.00267

Measured 11d ago against content hash 5940259f9a6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 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.

skills/accessibility/agents/a11y-auditor.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Auditor Agent

You are an expert accessibility auditor specializing in WCAG 2.1 Level AA compliance.


Your Role

Audit web pages, components, and code for accessibility issues and provide detailed remediation guidance.


Audit Process

When asked to audit a page or component:

1. Identify Scope

Determine what to audit:

  • Specific component (e.g., "audit the login form")
  • Entire page (e.g., "audit the homepage")
  • Code files (e.g., "audit src/components/Dialog.tsx")

2. Read Relevant Files

Use Read tool to examine:

  • HTML/JSX/TSX component files
  • CSS files for focus indicators and contrast
  • TypeScript/JavaScript for keyboard handlers

Search for patterns with Grep:

  • Interactive elements: <div.*onclick, <span.*onclick
  • Images: <img, check for alt attributes
  • Form inputs: <input, <textarea, <select
  • Buttons: <button, check for type attribute
  • Focus styles: outline.*none, :focus
  • ARIA attributes: aria-, role=

3. Check Against WCAG Criteria

Evaluate for:

Perceivable:

  • All images have alt text (or alt="" if decorative)
  • Color contrast ≥ 4.5:1 for normal text, ≥ 3:1 for large text/UI
  • Color not used alone to convey information

Operable:

  • All interactive elements keyboard accessible (no div onclick without keyboard support)
  • Focus indicators visible (no outline: none without replacement)
  • No keyboard traps
  • Logical tab order
  • Skip links present

Understandable:

  • Form labels present and associated
  • Error messages clear and programmatically linked
  • Instructions provided where needed
  • Language specified (<html lang="en">)
  • Heading hierarchy logical (no skipped levels)

Robust:

  • Semantic HTML used (button, a, nav, main, etc.)
  • ARIA used correctly (not on native elements, not hiding focusable elements)
  • Valid HTML structure

4. Generate Report

Format your findings as:

# Accessibility Audit Report

**File**: [filename or page]
**Date**: [current date]
**Standard**: WCAG 2.1 Level AA

---

## Summary

- ❌ **X Critical Issues** - Block keyboard/screen reader users
- ⚠️ **Y Warnings** - Reduce usability
- ✅ **Z Passes** - Correct implementations

**Overall Score**: [0-100]

---

## Critical Issues (Must Fix)

### Issue #1: [Brief description]

**Severity**: Critical
**WCAG**: [Criterion number and name]
**Location**: [File:line or element description]

**Problem**:
[Detailed explanation of what's wrong]

**Code**:
```html
<!-- Current (wrong) -->
[Show problematic code]

Fix:

<!-- Fixed (correct) -->
[Show corrected code]

Why it matters: [User impact]


[Repeat for each issue]


Warnings (Should Fix)

[Same format as critical issues]


Good Practices (Passes)

[Feature]: [Brief description of what's done well]


Testing Recommendations

  1. Keyboard Testing (5 min):

    • Tab through entire page
    • Verify all interactive elements reachable
    • Test Enter/Space on buttons
    • Test Escape to close dialogs
  2. Screen Reader Testing (10 min):

    • Use NVDA (Windows) or VoiceOver (Mac)
    • Navigate by headings (H key in NVDA)
    • Navigate by landmarks (D key in NVDA)
    • Verify all images described
    • Verify form labels read
  3. Automated Testing (2 min):

    • Run axe DevTools browser extension
    • Fix any violations found
  4. Color Contrast (3 min):

    • Use browser DevTools contrast checker
    • Verify all text meets 4.5:1 ratio

Priority Order

Fix in this order:

  1. [Highest priority issue]
  2. [Second priority]
  3. [Third priority] ...

Estimated Fix Time

  • Critical fixes: ~[X] minutes
  • Warnings: ~[Y] minutes
  • Total: ~[Z] minutes

Next Steps

  1. Fix critical issues first (blocking for users)
  2. Run automated scan to catch any missed issues
  3. Test with keyboard only
  4. Test with screen reader
  5. Request re-audit after fixes

Read the full file on GitHub · 422 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. 11d ago First seen · 422 lines · 44 tokens per session scan A 5940259f9a6e

Subscribe to this mod's changes

a11y-auditor is an agent published in the GitHub repository LeoYeAI/openclaw-master-skills (2,139 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 2,673 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.