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.
npx skills add Notysoty/openagentskills --skill accessibility-audit-helpergit clone --depth 1 https://github.com/Notysoty/openagentskillsWrote 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.
[](https://agentmods.dev/skills/notysoty/openagentskills/accessibility-audit-helper)<a href="https://agentmods.dev/skills/notysoty/openagentskills/accessibility-audit-helper"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/accessibility-audit-helper/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.
<a href="https://agentmods.dev/skills/notysoty/openagentskills/accessibility-audit-helper"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/accessibility-audit-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00023 | $0.01946 |
| Opus 5 | $0.00012 | $0.00973 |
| Sonnet 5 | $0.00005 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
Accessibility Audit Helper 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Audit Helper
What this skill does
This skill directs the agent to review HTML, JSX, or React component code for WCAG 2.1 accessibility violations. It checks for missing alt text, improper heading hierarchy, ARIA misuse, keyboard trap risks, color contrast hints, missing focus indicators, and more. Every finding is categorized by severity with a concrete before/after code fix included.
Use this before shipping any UI feature, during code review, or as a regular accessibility sweep of your component library.
How to use
Claude Code / Cline
Copy this file to .agents/skills/accessibility-audit-helper/SKILL.md in your project root.
Then share the component or page code and ask:
- "Run an accessibility audit on
src/components/Modal.tsxusing the Accessibility Audit Helper skill." - "Use the Accessibility Audit Helper skill to check this form for a11y issues."
Paste the component code directly or provide a file path for the agent to read.
Cursor
Add the "Prompt / Instructions" section to your .cursorrules file. Open the component you want audited and ask Cursor to run an accessibility audit.
Codex
Paste the component or page HTML/JSX into the chat along with the instructions below.
The Prompt / Instructions for the Agent
When asked to audit UI code for accessibility, follow these steps:
-
Read the full component or file. If it references child components or imports, note them but focus the audit on the provided code.
-
Check each of these categories systematically:
Images and Media
- All
<img>elements must have analtattribute; decorative images usealt="" - Icons used as buttons or links must have an
aria-labeloraria-labelledby - SVGs used for meaning must have a
<title>oraria-label; decorative SVGs needaria-hidden="true"
Heading Hierarchy
- Headings must not skip levels (e.g., H1 → H3 with no H2)
- Each page should have exactly one
<h1> - Headings must describe the section content, not just style large text
- All
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.
- 10d ago First seen · 217 lines · 23 tokens per session scan A 544d42765d2c
Accessibility Audit Helper is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 26d ago), licensed MIT. It adds 23 tokens to every session and 1,946 once invoked, about $0.0001 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.
Other skills, from other repositories
web-a11y-authoring
Builds accessible pages and components with semantic HTML, correct names/roles/states, keyboard support, focus management, links, images, SVG, media, and native controls first. Use when implementing or refactoring frontend UI.
web-a11y-review
Reviews frontend changes for accessibility regressions across semantics, keyboard/focus behavior, forms, dynamic updates, styling, ARIA, and tests. Use for pull requests, diffs, audits, and pre-merge sign-off.
web-a11y-css
Reviews and writes CSS that preserves accessibility across contrast, focus styles, reduced motion, forced colors, zoom, target size, semantic integrity, and custom-styled controls. Use for UI styling and design-system changes.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
Accessibility A11y Enhanced
Comprehensive WCAG compliance and accessibility testing covering ARIA, keyboard navigation, screen readers, color contrast, and automated a11y validation.