wcag-audit

wcag-audit is a command for Claude Code from christopherlouet/claude-base. It costs 0 tokens per session (1,028 once invoked), scanned A, original, MIT.

A code-based accessibility audit against WCAG, the international guidelines for making websites usable by people with disabilities.

In plain words
What is it for?
Use it to check images, forms, keyboard navigation, colors, labels, page structure, and other accessibility concerns before release.
Why use it?
It finds accessibility problems in interfaces and separates automatically detectable issues from those needing human review.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to check images, forms, keyboard navigation, colors, labels, page structure, and other accessibility concerns before release.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/christopherlouet/claude-base/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/christopherlouet/claude-base

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 wcag-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/christopherlouet/claude-base/wcag-audit.svg)](https://agentmods.dev/commands/christopherlouet/claude-base/wcag-audit)
Your own site
<a href="https://agentmods.dev/commands/christopherlouet/claude-base/wcag-audit"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/wcag-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,028 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 $0.00000 $0.01028
Opus 5 $0.00000 $0.00514
Sonnet 5 $0.00000 $0.00206
Haiku 4.5 $0.00000 $0.00103

Measured 4d ago against content hash 414a59488e99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

.claude/commands/qa/wcag-audit.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WCAG-AUDIT Agent (Accessibility)

Accessibility audit based on WCAG 2.1/2.2 and the axe-core reference.

Audit target

$ARGUMENTS

Objective

Identify accessibility violations in the code and propose concrete fixes to reach WCAG 2.1/2.2 level AA.

Workflow

  • Scan UI files (components, pages, layouts, CSS)
  • Audit the 11 categories: images, forms, keyboard, buttons/links, colors, ARIA, structure, tables, frames, deprecated, WCAG 2.2
  • Classify each issue by impact (Critical/Serious/Moderate/Minor)
  • Distinguish violations (auto-detectable) from needs-review (manual verification)
  • Identify priority fixes with file:line

Impact levels

Level Definition Action
Critical Completely blocks access Fix immediately
Serious Significant impact on usability Fix before release
Moderate Hinders user experience Plan a fix
Minor Desirable improvement Backlog

Audit categories

# Category Key rules WCAG
1 Images/media alt, SVG, object, video, autoplay 1.1.1, 1.2.2, 1.4.2
2 Forms labels, select, errors, autocomplete 4.1.2, 3.3.1, 1.3.5
3 Keyboard focus, traps, skip-link, scrollable, nested 2.1.1, 2.1.2, 2.4.1
4 Buttons/links accessible names, descriptive links 4.1.2, 2.4.4
5 Colors AA ratios, color alone, UI elements 1.4.3, 1.4.1, 1.4.11
6 ARIA attrs, roles, relations, aria-hidden 4.1.2, 1.3.1
7 Structure lang, title, headings, landmarks, regions 3.1.1, 2.4.2, 1.3.1
8 Tables th, scope, headers, caption 1.3.1
9 Frames title, uniqueness, focus 4.1.2, 2.1.1
10 Deprecated blink, marquee, meta-refresh, autoplay 2.2.1, 2.2.2
11 WCAG 2.2 target-size 44x44px, focus-not-obscured 2.5.8, 2.4.11

Expected output

Summary

  • Overall score: [X/100]
  • WCAG level reached: [A/AA/AAA]
  • Violations: [N] (Critical: X, Serious: X, Moderate: X, Minor: X)
  • Needs Review: [N]

Read the full file on GitHub · 95 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 · 95 lines · 0 tokens per session scan A 414a59488e99

Subscribe to this mod's changes

wcag-audit is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,028 tokens. 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 2026-09-03.