What is accessibility-audit?

An accessibility audit tool for a live web page or user flow. It combines an automated axe-core scan with checks of the accessibility tree, keyboard movement, focus order, contrast, labels, headings, landmarks, skip links, and image descriptions.

Use it to audit a URL before release, support a legal or compliance review, investigate reported accessibility problems, or check a component in its real page context.

It gives a release or compliance review one report of both automated and manual-style accessibility checks. It helps reveal problems that automated scanning alone may miss.

accessibility-audit — Skill for Claude Code and Codex by tahirraufkeey

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.

Any agent

npx skills add tahirraufkeeyu/software-development-agent-stack--sdas --skill accessibility-audit

Clone the repo

git clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdas

Made for: Claude Code, Codex.

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/skills/tahirraufkeeyu/software-development-agent-stack--sdas/accessibility-audit.svg)](https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/accessibility-audit)

Your own site

<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/accessibility-audit"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/accessibility-audit.svg" alt="Measured on agentmods" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,026 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	$0.00083	$0.02026
Opus 5	$0.00042	$0.01013
Sonnet 5	$0.00017	$0.00405
Haiku 4.5	$0.00008	$0.00203

Measured 8d ago against content hash 529df6ba87c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

accessibility-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 8d 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.

departments/qa/skills/accessibility-audit/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use

Invoke this skill when:

A route is approaching release and needs a WCAG 2.1 AA gate.
A legal/compliance review requires an accessibility report.
A design-system component needs a manual a11y check in context.
A user report cites keyboard, screen-reader, or contrast issues.

Do NOT use when: the check can be automated inline in an e2e test (use e2e-test-generator and embed axe); the request is a full manual audit by a certified auditor (this skill assists, does not replace).

Inputs

url (required): Full URL of the page to audit.
viewport (optional): { width, height }. Default { 1366, 768 } desktop and { 375, 667 } mobile; audit both when unspecified.
auth_cookie (optional): Session cookie for gated routes.
axe_tags (optional): Axe tag list. Default ["wcag2a", "wcag2aa", "wcag21a", "wcag21aa", "best-practice"].
include_selectors / exclude_selectors (optional): CSS selectors to scope the scan.

Outputs

A Markdown report with:
- Summary (critical / serious / moderate / minor counts).
- Violations table with: rule id, WCAG SC, impact, element selector, failure summary, suggested fix.
- Keyboard-navigation map (tab order + any focus-trap issues).
- Contrast failures with measured ratio and required ratio.
- Heading outline + landmark map.
- Copy-paste-ready fix snippets per violation.

Tool dependencies

mcp__chrome-devtools__new_page, mcp__chrome-devtools__navigate_page, mcp__chrome-devtools__emulate.
mcp__chrome-devtools__evaluate_script (to inject axe-core).
mcp__chrome-devtools__take_snapshot (accessibility-tree snapshot).
mcp__chrome-devtools__press_key (Tab walk for focus order).
mcp__chrome-devtools__take_screenshot (attach to contrast violations).
Write for the report.

Procedure

Open page with cookie. Navigate, set auth_cookie if provided.
Inject axe-core. Via evaluate_script, load axe from a CDN (https://cdnjs.cloudflare.com/ajax/libs/axe-core/4.10.0/axe.min.js) and run axe.run({ runOnly: { type: 'tag', values: <axe_tags> } }).
Collect accessibility tree. take_snapshot to capture the a11y tree; confirm landmarks (banner, navigation, main, complementary, contentinfo) are present.
Heading outline. evaluate_script to collect h1..h6 in DOM order; verify exactly one h1, no skipped levels.
Form labels. For each input, textarea, select — verify id matches a <label for> or has aria-label/aria-labelledby.
Alt text. For each <img> — require alt (empty for decorative, descriptive otherwise). Flag alt="image" / alt="picture" / filename-as-alt.
Skip link. The first focusable element on load should link to #main (or the main landmark). If absent, flag.
Keyboard walk. Send Tab 20 times via press_key; record each focused element via evaluate_script(document.activeElement). Verify:
- Focus is always visible (outline not removed without replacement).
- No keyboard trap (Shift+Tab reverses cleanly).
- Tab order matches visual order.
Contrast. Axe reports contrast; cross-check any visual components using getComputedStyle + WCAG formula. Required: 4.5:1 for body text, 3:1 for large text (>=18pt or >=14pt bold), 3:1 for UI component and graphical object boundaries.
ARIA roles. Flag invalid combinations (role="button" on an actual <button>, aria-hidden="true" on a focusable element, redundant roles on native semantics).
Write report. One Markdown file under reports/a11y/<yyyy-mm-dd>-<host>-<path>.md.

Read the full file on GitHub · 155 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.

8d ago First seen · 155 lines · 83 tokens per session scan A 529df6ba87c7

Subscribe to this mod's changes

accessibility-audit is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 2,026 once invoked, about $0.0004 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

accessibility-audit