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 Miaoge-Ge/coding-agent-skills --skill accessibility-expertgit clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-skillsWrote 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/miaoge-ge/coding-agent-skills/accessibility-expert)<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/accessibility-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/accessibility-expert.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.01125 |
| Opus 5 | $0.00048 | $0.00562 |
| Sonnet 5 | $0.00019 | $0.00225 |
| Haiku 4.5 | $0.00010 | $0.00112 |
Grade A, and why
accessibility-expert 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Accessibility Expert
The first rule of ARIA is don't use ARIA — a native
<button>beats<div role="button">every time. Target WCAG 2.2 AA. If it doesn't work with the keyboard, it isn't done.
When to Use
- Building UI you want accessible from the start.
- Auditing/fixing issues: keyboard traps, unlabeled controls, low contrast, missing focus.
- Adding accessible behavior to custom widgets (modal, menu, tabs, combobox, accordion, tooltip).
- Forms, images, dynamic updates, and motion.
When NOT to Use
- Pure visual styling without semantics →
tailwind-expert. - Component state logic →
react-expert.
Core Principles
1. Semantics first, ARIA last
- Use the native element for the job (
<button>,<a href>,<label>,<nav>,<main>,<dialog>,<input type>). They bring role, state, and keyboard behavior for free. - No ARIA is better than bad ARIA. Don't add roles to elements that already have them; don't override native semantics. ARIA changes how AT announces — it does not add behavior (you still wire keyboard/focus yourself).
2. Keyboard operability (WCAG 2.1.1)
- Everything actionable is reachable and operable by keyboard: Tab to move, Enter/Space to activate, Esc to dismiss, arrows within composite widgets (menus, tabs, radios).
- Keep a visible focus indicator (
:focus-visible). Neveroutline:nonewithout a clear replacement. - Logical tab order = DOM order. Avoid positive
tabindex; usetabindex="-1"for programmatic focus,0to add non-interactive elements to tab order only when necessary.
3. Focus management for overlays
- Dialogs/menus: move focus in on open, trap within, restore to the trigger on close, and make background
inert/aria-hidden. Prefer the native<dialog>element.
4. Name, role, value (WCAG 4.1.2)
- Every control has an accessible name:
<label for>, wrapping<label>,aria-label, oraria-labelledby. Icon-only buttons need an accessible name (visually-hidden text oraria-label). - Images: meaningful
alt; decorative →alt="". Communicate state witharia-expanded/-selected/-checked/-current/-pressed, and announce async changes via a live region (aria-live="polite", orrole="alert"for errors).
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 · 75 lines · 97 tokens per session scan A 0dd987912ca9
accessibility-expert is a skill published in the GitHub repository Miaoge-Ge/coding-agent-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 1,125 once invoked, about $0.0005 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
ai-ui-generation
AI-assisted UI generation patterns for json-render, v0.app, Google Stitch, Bolt Cloud, and Cursor workflows. Covers prompt engineering for component and full-stack app generation, review checklists for AI-generated code, design token injection, refactoring for design system conformance, and CI gates for quality…
design-directions
A workflow for producing several deliberately different single-file HTML prototypes of a page or interface. Each prototype uses realistic sample data so a user can compare layouts and interactions before real implementation.
accessibility-audit
Audit web accessibility using ARIA snapshots, AX tree analysis, and WCAG validation. Use when the user asks about accessibility, a11y, WCAG compliance, screen reader compatibility, ARIA roles, or keyboard navigation.
accessibility
Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible". Do NOT use for SEO (use seo), performance (use core-web-vitals), or comprehensive site audits covering…
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.