wcag-audit

wcag-audit is a command for Claude Code from ncklrs/claude-chrome-user-testing. It costs 33 tokens per session (2,343 once invoked), scanned A, original, MIT.

A web-page checker for WCAG 2.1, the accessibility guidelines used to make websites usable by people with disabilities. It checks Level A and AA requirements and produces a report.

In plain words
What is it for?
Use it to audit a page by URL, choose Level A or AA checks, and receive a summary, detailed report, or JSON output. You can also save the report to a file.
Why use it?
It finds accessibility problems that may otherwise be missed during development. The report explains what needs fixing and can include screenshots marking violations.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the user-testing-agent plugin — 14 skills, 10 commands shipped together

Good fit Use it to audit a page by URL, choose Level A or AA checks, and receive a summary, detailed report, or JSON output. You can also save the report to a file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ncklrs/claude-chrome-user-testing/wcag-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.

Clone the repo
git clone --depth 1 https://github.com/ncklrs/claude-chrome-user-testing

Made for: Claude Code.

Or install user-testing-agent, the plugin that ships this one along with the rest of its 14 skills, 10 commands.

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 wcag-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/ncklrs/claude-chrome-user-testing/wcag-audit/github.svg)](https://agentmods.dev/commands/ncklrs/claude-chrome-user-testing/wcag-audit)
Your own site
<a href="https://agentmods.dev/commands/ncklrs/claude-chrome-user-testing/wcag-audit"><img src="https://agentmods.dev/badge/commands/ncklrs/claude-chrome-user-testing/wcag-audit/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 wcag-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/ncklrs/claude-chrome-user-testing/wcag-audit"><img src="https://agentmods.dev/badge/commands/ncklrs/claude-chrome-user-testing/wcag-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,343 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 $0.00033 $0.02343
Opus 5 $0.00016 $0.01171
Sonnet 5 $0.00007 $0.00469
Haiku 4.5 $0.00003 $0.00234

Measured 9d ago against content hash 2ea7e5d812e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wcag-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 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.

commands/wcag-audit.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WCAG Audit Command

Perform a comprehensive WCAG 2.1 accessibility audit on a web page to identify compliance issues and generate an actionable report.

Arguments

Parse the following from $ARGUMENTS:

  • --url <url> (required): URL to audit
  • --level <a|aa> (optional): Conformance level to check (default: aa, which includes a)
  • --format <format> (optional): Output format - summary | detailed | json (default: detailed)
  • --save <filename> (optional): Save report to file
  • --annotate (optional): Take annotated screenshots of violations

Prerequisites

This command requires:

  1. Claude running with --chrome flag
  2. Playwright MCP tools available

Audit Flow

Step 1: Initialize

  1. Navigate to the target URL using browser_navigate
  2. Wait for page to fully load
  3. Take initial accessibility snapshot with browser_snapshot
  4. Initialize counters for passed/failed criteria

Step 2: Run Level A Checks

Check these essential WCAG 2.1 Level A criteria:

1.1.1 Non-text Content

Check all images have appropriate alt text:

Use browser_evaluate to find:
- Images without alt attribute
- Images with empty alt on non-decorative images
- Background images conveying information without text alternative

Severity: Critical if functional images lack alt text

1.3.1 Info and Relationships

Check semantic HTML usage:

Use browser_snapshot to verify:
- Proper heading hierarchy (h1 → h2 → h3)
- Lists use ul/ol/li elements
- Tables have proper th/caption
- Form fields have associated labels

Severity: Major

1.3.2 Meaningful Sequence

Check reading order:

Use browser_evaluate to compare:
- Visual order vs DOM order
- CSS doesn't create confusing reordering

Severity: Major

2.1.1 Keyboard Accessible

Check all interactive elements work with keyboard:

Use browser_press_key to Tab through page:
- Can reach all interactive elements
- Buttons, links, form fields are focusable
- Custom widgets have keyboard support

Severity: Critical

Read the full file on GitHub · 414 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 · 414 lines · 33 tokens per session scan A 2ea7e5d812e2

Subscribe to this mod's changes

wcag-audit is a command published in the GitHub repository ncklrs/claude-chrome-user-testing (19 stars, last pushed 8mo ago), licensed MIT. It adds 33 tokens to every session and 2,343 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.