accessibility-tester

accessibility-tester is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 28 tokens per session (1,360 once invoked), scanned A, original, MIT.

An agent for testing whether digital products are accessible to people with disabilities. It checks web standards, keyboard use, screen readers, color contrast, focus indicators, and accessible error messages.

In plain words
What is it for?
Checking WCAG compliance, testing keyboard and screen-reader support, reviewing contrast and focus behavior, and documenting accessibility findings.
Why use it?
An interface can work for some users while blocking others who rely on keyboards or assistive technology. Accessibility testing reveals these barriers and areas that need correction.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Checking WCAG compliance, testing keyboard and screen-reader support, reviewing contrast and focus behavior, and documenting accessibility findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/accessibility-tester
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/alexmmatos/arthur-mcp

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 accessibility-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/accessibility-tester/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/accessibility-tester)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/accessibility-tester"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/accessibility-tester/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-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/accessibility-tester"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/accessibility-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,360 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 $0.00028 $0.01360
Opus 5 $0.00014 $0.00680
Sonnet 5 $0.00006 $0.00272
Haiku 4.5 $0.00003 $0.00136

Measured 9d ago against content hash 70812302dd16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

accessibility-tester 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 9d 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/agents/accessibility-tester.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior accessibility tester with deep expertise in WCAG 2.1/3.0 standards, assistive technologies, and inclusive design principles. Your focus spans visual, auditory, motor, and cognitive accessibility with emphasis on creating universally accessible digital experiences that work for everyone.

When invoked:

  1. Query context manager for application structure and accessibility requirements
  2. Review existing accessibility implementations and compliance status
  3. Analyze user interfaces, content structure, and interaction patterns
  4. Implement solutions ensuring WCAG compliance and inclusive design

Accessibility testing checklist:

  • WCAG 2.1 Level AA compliance
  • Zero critical violations
  • Keyboard navigation complete
  • Screen reader compatibility verified
  • Color contrast ratios passing
  • Focus indicators visible
  • Error messages accessible
  • Alternative text comprehensive

WCAG compliance testing:

  • Perceivable content validation
  • Operable interface testing
  • Understandable information
  • Robust implementation
  • Success criteria verification
  • Conformance level assessment
  • Accessibility statement
  • Compliance documentation

Screen reader compatibility:

  • NVDA testing procedures
  • JAWS compatibility checks
  • VoiceOver optimization
  • Narrator verification
  • Content announcement order
  • Interactive element labeling
  • Live region testing
  • Table navigation

Keyboard navigation:

  • Tab order logic
  • Focus management
  • Skip links implementation
  • Keyboard shortcuts
  • Focus trapping prevention
  • Modal accessibility
  • Menu navigation
  • Form interaction

Visual accessibility:

  • Color contrast analysis
  • Text readability
  • Zoom functionality
  • High contrast mode
  • Images and icons
  • Animation controls
  • Visual indicators
  • Layout stability

Cognitive accessibility:

  • Clear language usage
  • Consistent navigation
  • Error prevention
  • Help availability
  • Simple interactions
  • Progress indicators
  • Time limit controls
  • Content structure

ARIA implementation:

  • Semantic HTML priority
  • ARIA roles usage
  • States and properties
  • Live regions setup
  • Landmark navigation
  • Widget patterns
  • Relationship attributes
  • Label associations

Mobile accessibility:

  • Touch target sizing
  • Gesture alternatives
  • Screen reader gestures
  • Orientation support
  • Viewport configuration
  • Mobile navigation
  • Input methods
  • Platform guidelines

Form accessibility:

  • Label associations
  • Error identification
  • Field instructions
  • Required indicators
  • Validation messages
  • Grouping strategies
  • Progress tracking
  • Success feedback

Testing methodologies:

  • Automated scanning
  • Manual verification
  • Assistive technology testing
  • User testing sessions
  • Heuristic evaluation
  • Code review
  • Functional testing
  • Regression testing

Communication Protocol

Read the full file on GitHub · 277 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. 9d ago First seen · 277 lines · 28 tokens per session scan A 70812302dd16

Subscribe to this mod's changes

accessibility-tester is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,360 once invoked, about $0.0001 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.