A command for checking a web page, project, or changed files against WCAG 2.2 accessibility rules. WCAG 2.2 is a standard for making websites usable by people with disabilities.

Use it to inspect HTML, URLs, or changes in a branch, review examples and fixes, and optionally create a hash that lets others verify the report.

It finds accessibility problems and groups them by severity instead of relying only on a code review. It also shows what automated checks did not cover and still needs human review.

a11y-audit — Command for Claude Code by kinti/a11y-toolkit

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/kinti/a11y-toolkit

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/kinti/a11y-toolkit/a11y-audit/github.svg)](https://agentmods.dev/commands/kinti/a11y-toolkit/a11y-audit)

Your own site

<a href="https://agentmods.dev/commands/kinti/a11y-toolkit/a11y-audit"><img src="https://agentmods.dev/badge/commands/kinti/a11y-toolkit/a11y-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/kinti/a11y-toolkit/a11y-audit"><img src="https://agentmods.dev/badge/commands/kinti/a11y-toolkit/a11y-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 253 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.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.00253
Opus 5.5	$0.00007	$0.00101
Sonnet 5.5	$0.00004	$0.00051
Haiku 4.5	$0.00002	$0.00025

Measured 6d ago against content hash 3cebddcc5eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

a11y-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 6d 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/a11y-audit.md · 21 lines

What it actually says

Audit what we're working on with a11y-toolkit and report honestly.

Steps

If auditing the open file: run a11ytoolkit audit --file <file> (CLI) or the a11y_audit MCP tool over the file's HTML.
If auditing a URL: a11y_audit_url / a11ytoolkit audit --url <url>.
If auditing only what changed in this branch: a11ytoolkit audit --changed --base main.
Read the report: for each finding show criterion, severity, examples and the remediation. Group by severity. Do NOT restate findings we can't see.
For contrast failures, propose the fix with a11y_suggest_color.
Optional seal: a11y_evidence over the report(s) → give the user the pack sha256 so anyone can re-verify later.
End with the honest line: what automation covered, what still needs a human (the report's manual_pending list).

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.

6d ago First seen · 21 lines · 18 tokens per session scan A 3cebddcc5eb4

Subscribe to this mod's changes

a11y-audit is a command published in the GitHub repository kinti/a11y-toolkit (3 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 253 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-31.

Frontend Testing a11y accessibility aria-live contrast-checker en-301-549 european-accessibility-act

a11y-audit next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
a11y-auditkinti/a11y-toolkit	Command	3	3d ago	MIT	A	18	Claude Code
a11y-handoffsaralobo/rules-accessibility-handoff	Command	11	8mo ago	none	A	36	Claude Code
checklistgithub/spec-kit	Command	148k	today	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	today	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	today	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	today	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	today	MIT	A	35	Claude Code