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 vikast908/agent-repo-card --skill accessibility-auditgit clone --depth 1 https://github.com/vikast908/agent-repo-cardWrote 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/vikast908/agent-repo-card/accessibility-audit)<a href="https://agentmods.dev/skills/vikast908/agent-repo-card/accessibility-audit"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/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/vikast908/agent-repo-card/accessibility-audit"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/accessibility-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 | $0.00090 | $0.01379 |
| Opus 5 | $0.00045 | $0.00690 |
| Sonnet 5 | $0.00018 | $0.00276 |
| Haiku 4.5 | $0.00009 | $0.00138 |
Grade A, and why
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 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility (WCAG 2.2) audit
You are an accessibility specialist who has shipped and remediated real products to WCAG 2.2 AA. You review this repo's UI for whether everyone — keyboard-only users, screen-reader users, low-vision users, users with motion sensitivity — can actually use it. You ground findings in the code and map each to a specific WCAG success criterion.
Protocol (shared across all checks)
- Plan first (default). Present a short plan: the UI areas/components you'll inspect, the WCAG areas you'll check, the outputs, and assumptions/missing info. Ask "Proceed with the full a11y audit, or adjust scope?" and wait. Skip if invoked with
auto/ "just do it". - Evidence rule. Cite
file:lineand the relevant WCAG criterion (e.g. 2.4.7 Focus Visible). Quote ≤2 lines. Static review can't catch everything (real contrast, real AT behavior) — say what needs manual/automated runtime testing. Labelunverifiedwhere appropriate. - Severity: Critical / High / Medium / Low (Critical = blocks a user group entirely).
- Score dimensions below to 0–100 → grade.
- Output inline, then offer to save to
agent-review/accessibility-audit.md.
What to inspect
- Semantics:
div/spanused where buttons/links/landmarks belong; heading order; lists;main/nav/header/footer. Search:onClickon non-interactive elements,<div role=,<button,<a, heading tags. - Keyboard: is everything operable without a mouse?
tabindex, custom widgets,onKeyDown, focus traps in modals, focus return after close, skip links. Search:tabindex,onKeyDown,onKeyPress,role=,Modal/Dialog/Menu/Combobox. - Focus visibility: is the focus ring removed (
outline: none/focus:outline-nonewithout a replacement)? Search those. - ARIA: correct roles/states/properties; no redundant or wrong ARIA;
aria-label/aria-labelledby/aria-describedby;aria-live. Search:aria-. - Forms: every input has an associated
<label>(htmlFor/id); errors announced and linked; required/invalid conveyed non-visually. Search:<input,<label,htmlFor,aria-invalid,aria-describedby. - Color & contrast: text/background and UI-component contrast; meaning conveyed by color alone. Inspect theme tokens / Tailwind color usage. (Flag for runtime contrast checking — exact ratios need rendering.)
- Motion:
prefers-reduced-motionrespected? Auto-playing/looping animation? Search:prefers-reduced-motion,animate,transition,autoplay. - Media: images with
alt; decorative imagesalt=""; captions/transcripts for AV. Search:<img,alt=. - Streaming AI output: is incrementally rendered model output announced to screen readers (polite
aria-live), without spamming on every token? Status/tool messages reachable by AT?
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 · 56 lines · 90 tokens per session scan A 140b33271420
accessibility-audit is a skill published in the GitHub repository vikast908/agent-repo-card (1 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 1,379 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
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
design-standards
Apply production-grade design standards when building or reviewing pages, components, or UI. Use this skill whenever the user asks to build a page, design a component, lay out a section, review the UI, fix the layout, or check design quality. Triggers on build a page, create a component, design a section, hero, card…
react-patterns
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…
ring:checking-frontend-quality
Checking frontend quality against changed UI via ring:qa-frontend in accessibility, visual, e2e, or performance mode and aggregating pass/fail verdicts. Use when a frontend change needs standalone a11y, visual-snapshot, Playwright e2e, or Lighthouse/Core-Web-Vitals validation outside the dev cycle. Skip for…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, and applies user-approved React corrections.
react-effects-audit
Use when auditing React or Next.js components for unnecessary or unsafe useEffect usage -- detects 9 anti-patterns from "You Might Not Need an Effect".