A heuristic accessibility checker for a page running on your computer. Accessibility means making websites usable by people with disabilities, including people who use screen readers or touch controls.

Use it to inspect missing image descriptions, unnamed controls, unlabeled form fields, heading order, possible contrast issues, and small touch targets on desktop and mobile page captures.

It catches common page problems without requiring a full accessibility testing setup. It also states what its screenshot and page-structure checks cannot prove, such as keyboard behavior or full WCAG compliance.

a11y-audit — Skill for Claude Code by soumyachk101

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 soumyachk101/VibeLens --skill a11y-audit

Clone the repo

git clone --depth 1 https://github.com/soumyachk101/VibeLens

Made for: Claude Code.

Or install vibelens, the plugin that ships this one along with the rest of its 12 skills, 4 agents, 1 hook.

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/soumyachk101/vibelens/a11y-audit/github.svg)](https://agentmods.dev/skills/soumyachk101/vibelens/a11y-audit)

Your own site

<a href="https://agentmods.dev/skills/soumyachk101/vibelens/a11y-audit"><img src="https://agentmods.dev/badge/skills/soumyachk101/vibelens/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/skills/soumyachk101/vibelens/a11y-audit"><img src="https://agentmods.dev/badge/skills/soumyachk101/vibelens/a11y-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,316 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	$0.00071	$0.01316
Opus 5	$0.00036	$0.00658
Sonnet 5	$0.00014	$0.00263
Haiku 4.5	$0.00007	$0.00132

Measured 11d ago against content hash 3d23b9125c20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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.

plugin/skills/a11y-audit/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility audit

Target: $ARGUMENTS (if empty, ask for the URL).

What this skill can and cannot do

inspect_localhost_ui gives you a rendered screenshot and a sanitized DOM with real ids, classes, role and aria-* attributes. That is enough to catch the common, high-frequency failures listed below by inspection.

It is not a substitute for axe-core, Lighthouse or a screen-reader pass. You cannot compute contrast ratios from a JPEG, you cannot tab through the page (the tool is read-only — no clicking, typing or scrolling), and you cannot observe focus order, live-region announcements or the computed accessibility tree. Say this in your report. Never claim a page is "WCAG compliant" on the strength of this audit; claim only that the issues you found are real.

Steps

Capture the page twice: once viewport: "desktop" and once viewport: "mobile", both with fullPage: true. Desktop shows the full structure; mobile is where tap-target and reflow failures appear. Raise delay to 2000–3000 if the DOM comes back nearly empty — you cannot audit an unhydrated page.
Check summary.domTruncated. If it is true the tree is partial, so scope your findings to what you actually saw and say which regions you could not reach.
Work the DOM snapshot for structural failures:
- Images without alt. Every <img> needs alt. A decorative image needs alt="" — absent and empty are different findings, so do not report an intentional alt="" as a bug.
- Controls with no accessible name. Icon-only <button>s and <a>s with no text child and no aria-label / aria-labelledby announce as "button". Look for buttons whose only child is a collapsed <svg> placeholder — the sanitizer empties SVG internals, so an SVG-only button is easy to spot.
- Inputs with no label. For each <input>, <select> and <textarea>, find one of: a <label for="..."> matching its id, an aria-label, or an aria-labelledby pointing at an id that exists in the tree. A placeholder is not a label — it disappears on input and many screen readers skip it.
- Heading order. List the headings in document order and flag skips (h1 → h3), multiple h1s, and pages with no h1 at all. Also flag text that looks like a heading in the screenshot (large, bold) but is a <div> or <p> in the DOM — that is invisible to a screen reader.
- Landmarks. Note a page with no <main>, <nav> or role="main"; it forces screen-reader users to read linearly from the top.
- aria-hidden on interactive elements and role values that contradict the tag (role="button" on a <div> with no tabindex).

Read the full file on GitHub · 103 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.

11d ago First seen · 103 lines · 71 tokens per session scan A 3d23b9125c20

Subscribe to this mod's changes

a11y-audit is a skill published in the GitHub repository soumyachk101/VibeLens (0 stars, last pushed 4d ago), licensed MIT. It adds 71 tokens to every session and 1,316 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 2026-08-31.

Claude Code Frontend Testing antigravity codex cursor mcp model-context-protocol

accessibility-testing

Run automated WCAG audits, manual keyboard/screen reader testing, and CI a11y gates.

sawrus/agent-guides · 24 tokens

test-driven-development

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

addyosmani/agent-skills · 57 tokens

frontend-ui-engineering

Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

addyosmani/agent-skills · 58 tokens

accesslint-diff

Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [ ] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use scan for a full audit with no diffing.

sickn33/agentic-awesome-skills · 68 tokens

screen-reader-testing

Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.

wshobson/agents · 39 tokens

browser-testing-with-devtools

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…

addyosmani/agent-skills · 68 tokens