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 khasky/awesome-agent-skills --skill awesome-accessibility-auditgit clone --depth 1 https://github.com/khasky/awesome-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/khasky/awesome-agent-skills/awesome-accessibility-audit)<a href="https://agentmods.dev/skills/khasky/awesome-agent-skills/awesome-accessibility-audit"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-accessibility-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.
<a href="https://agentmods.dev/skills/khasky/awesome-agent-skills/awesome-accessibility-audit"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-accessibility-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.03535 |
| Opus 5.5 | $0.00017 | $0.01414 |
| Sonnet 5.5 | $0.00008 | $0.00707 |
| Haiku 4.5 | $0.00004 | $0.00353 |
Grade A, and why
awesome-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 7d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Audit
Review UI and markup for accessibility and give the concrete fix for each finding, aligned with WCAG, so all users can perceive, operate, and understand the interface.
Read-only: it reports findings, each with the markup or attribute change that resolves it, and never applies them. A snippet in a report is reviewable next to the criterion it satisfies; the same edit applied silently is not. Hand the report to whoever owns the component.
When to Activate
- User asks for "accessibility", "a11y", "WCAG", or "screen reader support"
- Before shipping a new page or component
- Reviewing forms, modals, or interactive UI
- After a design or UI change that affects interaction or content
Work Process
- Define scope — Page, component, or flow to review (e.g. login form, report table, modal dialog).
- Check each area — Semantic HTML, keyboard, labels and names, color and contrast, dynamic content, motion. Use the checklists below.
- Document findings — Location (component/file or element type), WCAG criterion or principle, issue, impact, and recommended fix. Severity: Critical / High / Medium.
- Give the fix, do not apply it — A code snippet or attribute change in the report where possible. Prefer native HTML and correct ARIA over custom widgets when they suffice.
- Recommend follow-up — Suggest automated tools (e.g. axe, Lighthouse, pa11y; in CI, fail the build on critical) and manual testing for broader coverage. Automated tools catch roughly 30–40% of WCAG issues — the rest is manual. Recommend a flow × assistive-tech matrix: test each key user flow across keyboard-only, a screen reader (VoiceOver on Mac/iOS, NVDA on Windows, TalkBack on Android), 200% and 400% zoom / reflow (WCAG 1.4.10), Windows High Contrast, and reduced-motion; note Voice Control/Dragon and Switch Control where relevant. Do not claim full WCAG compliance from a single review.
- For automated assertions in tests:
axe-corewith.withTags(['wcag2a','wcag2aa'])targets a specific WCAG tier and can fail CI on violations; Playwright'spage.ariaSnapshot()(1.59+) asserts the accessibility tree of dialogs, menus, and composite widgets — coverage beyond what axe/Lighthouse give. - Run automated scans at more than one viewport (mobile and desktop breakpoints, not only the default): focus-obscured, overlapping targets, and reflow violations appear or vanish with viewport size, so a single-viewport scan silently under-reports.
- For automated assertions in tests:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed ecbf833b04bd
- 9d ago Changed 928e6660bc36
- 17d ago Changed · +11 lines 24b71600edcb
- 1mo ago Changed · -71 tokens per session 4b1bef4817c5
- 1mo ago Changed fd4982385fd4
- 1mo ago Changed · +2 lines · -60 tokens per session f056ac6c642c
- 1mo ago Changed · +2 lines · +26 tokens per session 613c0f28db64
- 1mo ago First seen · 177 lines · 147 tokens per session scan A a221a3e6f1da
awesome-accessibility-audit is a skill published in the GitHub repository khasky/awesome-agent-skills (21 stars, last pushed 8d ago), licensed MIT. It adds 42 tokens to every session and 3,535 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
shadcnui
Expert shadcn/ui assistance covering Radix UI primitives, Tailwind CSS styling, copy-paste architecture, and accessibility. Use when building modern React component systems and accessible design systems.
bootstrap
Expert Bootstrap 5 assistance covering 12-column grid system, flexbox utilities, components, and responsive breakpoints. Use when rapidly prototyping responsive, mobile-first web layouts.
chakraui
Expert Chakra UI assistance covering accessible React components, theme tokens, style props, and dark mode. Use when building modular, accessible React component libraries and dashboards.
materialui
Expert Material UI (MUI) assistance covering Emotion styled components, theme customization, DataGrid, and accessible icons. Use when building React enterprise dashboards with Google's Material Design.
vuetify
Expert Vuetify assistance covering Material Design components, data tables, responsive layouts, and themes for Vue 3. Use when rapidly building enterprise dashboards and back-office tools in Vue.
tailwindcss
Expert Tailwind CSS assistance covering utility classes, responsive variants, arbitrary values, and configuration. Use when styling modern web applications with speed and consistency.