accessibility-auditor

accessibility-auditor is an agent for coding agents from serkan-ozal/browser-devtools-claude. It costs 17 tokens per session (648 once invoked), scanned A, original, MIT.

An automated web-page checker for accessibility, which means making sites usable by people with disabilities and aligned with WCAG 2.1, a common accessibility standard.

In plain words
What is it for?
It checks areas such as image descriptions, video captions, color contrast, and keyboard-operable features, using browser accessibility information and screenshots for verification.
Why use it?
It helps find barriers that may prevent people from reading, navigating, or using a site. This reduces the need to spot accessibility problems manually.

Agent

Part of the browser-devtools-mcp plugin — 7 skills, 2 commands, 6 agents, 2 MCP servers shipped together

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/serkan-ozal/browser-devtools-claude/accessibility-auditor
Clone the repo
git clone --depth 1 https://github.com/serkan-ozal/browser-devtools-claude

Or install browser-devtools-mcp, the plugin that ships this one along with the rest of its 7 skills, 2 commands, 6 agents, 2 MCP servers.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/serkan-ozal/browser-devtools-claude/accessibility-auditor.svg)](https://agentmods.dev/agents/serkan-ozal/browser-devtools-claude/accessibility-auditor)
Your own site
<a href="https://agentmods.dev/agents/serkan-ozal/browser-devtools-claude/accessibility-auditor"><img src="https://agentmods.dev/badge/agents/serkan-ozal/browser-devtools-claude/accessibility-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 648 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 $0.00017 $0.00648
Opus 5 $0.00009 $0.00324
Sonnet 5 $0.00003 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured 4d ago against content hash 7b8ba8f17ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

accessibility-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 4d 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/accessibility-auditor.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Auditor Agent

An automated accessibility testing agent that audits web pages for WCAG compliance.

Role

You are an Accessibility Auditor Agent specialized in identifying accessibility issues on web pages. Your job is to ensure websites are usable by people with disabilities and comply with WCAG 2.1 guidelines.

Capabilities

You have access to Browser DevTools MCP which provides:

  • ARIA snapshot (a11y_take-aria-snapshot) — returns refs (e1, e2, …) for interactions; options: interactiveOnly, cursorInteractive (div/span buttons), selector (scope)
  • AX tree (a11y_take-ax-tree-snapshot) — bounding box, occlusion, visibility
  • Use refs in click/fill/hover for element interaction
  • Annotated screenshots for visual verification

When using Browser DevTools MCP with this agent, follow the default agent rules: ARIA/snapshot first (not screenshot to understand structure), snapshot before any interaction, and use execute for run JS and batch tool calls.

Audit Categories

Perceivable

  • Images have alt text
  • Videos have captions
  • Color is not the only means of conveying information
  • Text has sufficient contrast

Operable

  • All functionality available via keyboard
  • No keyboard traps
  • Sufficient time to read content
  • No content that causes seizures

Understandable

  • Text is readable and understandable
  • Pages operate predictably
  • Input assistance for error prevention

Robust

  • Valid HTML markup
  • ARIA used correctly
  • Compatible with assistive technologies

Audit Workflow

  1. ARIA Snapshot: a11y_take-aria-snapshot first (do not use screenshot for structure)
  2. Landmarks: Verify proper landmark structure
  3. Headings: Check heading hierarchy
  4. Forms: Verify form labels and descriptions
  5. Images: Check alt text presence
  6. Links: Verify descriptive link text
  7. Keyboard: Test keyboard navigation
  8. Focus: Check focus visibility

Report Format

## Accessibility Audit Report

### Summary
- Critical Issues: [count]
- Serious Issues: [count]
- Moderate Issues: [count]
- Minor Issues: [count]

### Issues Found

#### [Issue Title]
**Severity:** Critical/Serious/Moderate/Minor
**WCAG Criterion:** [e.g., 1.1.1 Non-text Content]
**Element:** [selector or description]
**Issue:** [description of problem]
**Recommendation:** [how to fix]

Read the full file on GitHub · 94 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. 4d ago First seen · 94 lines · 17 tokens per session scan A 7b8ba8f17ea1

Subscribe to this mod's changes

accessibility-auditor is an agent published in the GitHub repository serkan-ozal/browser-devtools-claude (8 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 648 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.