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 Shiven0504/claude-skills-collection --skill a11y-auditgit clone --depth 1 https://github.com/Shiven0504/claude-skills-collectionWrote 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/shiven0504/claude-skills-collection/a11y-audit)<a href="https://agentmods.dev/skills/shiven0504/claude-skills-collection/a11y-audit"><img src="https://agentmods.dev/badge/skills/shiven0504/claude-skills-collection/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.
<a href="https://agentmods.dev/skills/shiven0504/claude-skills-collection/a11y-audit"><img src="https://agentmods.dev/badge/skills/shiven0504/claude-skills-collection/a11y-audit.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 | $0.00109 | $0.03093 |
| Opus 5.5 | $0.00044 | $0.01237 |
| Sonnet 5.5 | $0.00022 | $0.00619 |
| Haiku 4.5 | $0.00011 | $0.00309 |
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 2mo 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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Audit & Fix
Help users identify and fix accessibility issues in React/Next.js components with Tailwind CSS. The goal is practical, actionable guidance — not an exhaustive WCAG spec dump.
Quick Audit Checklist
When auditing a component or page, check these areas in order. Each section below explains what to look for and how to fix it.
- Semantic HTML — are the right elements used?
- Keyboard navigation — can everything be reached and operated with keyboard alone?
- ARIA attributes — are labels, roles, and states correct?
- Color and contrast — does it meet minimum contrast ratios?
- Focus management — is focus visible and logical?
- Screen reader experience — does it make sense when read aloud?
- Motion and animation — is reduced motion respected?
Semantic HTML
Using the right HTML elements is the single highest-impact accessibility improvement because it gives you keyboard support, screen reader announcements, and proper roles for free.
Common mistakes and fixes
| Instead of... | Use... | Why |
|---|---|---|
<div onClick> |
<button> |
Buttons are focusable, respond to Enter/Space, announced as "button" |
<div> for navigation |
<nav> |
Screen readers can jump to nav landmarks |
<div> for main content |
<main> |
Landmark navigation — users can skip to main content |
<span> for headings |
<h1>–<h6> |
Screen readers build a page outline from headings |
<div> for lists |
<ul>/<ol> |
Screen readers announce "list, 5 items" |
<a> without href |
<button> |
Links navigate, buttons perform actions |
Heading hierarchy
Headings should form a logical outline. Don't skip levels for styling — use Tailwind to style any heading however you want:
// Bad — skips h2, uses headings for styling
<h1>Dashboard</h1>
<h3 className="text-lg">Recent Activity</h3>
// Good — proper hierarchy, styled independently
<h1 className="text-2xl font-bold">Dashboard</h1>
<h2 className="text-lg font-semibold">Recent Activity</h2>
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.
- 2mo ago First seen · 417 lines · 109 tokens per session scan A fdb67655f4ae
a11y-audit is a skill published in the GitHub repository Shiven0504/claude-skills-collection (6 stars, last pushed 7mo ago), licensed MIT. It adds 109 tokens to every session and 3,093 once invoked, about $0.0004 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.
a11y-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| a11y-auditShiven0504/claude-skills-collection | Skill | 6 | 7mo ago | MIT | A | 109 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 4d ago | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |