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 agentmods add skills/m-binimran/dev-pack/a11y-auditnpx skills add m-binimran/dev-pack --skill a11y-auditgit clone --depth 1 https://github.com/m-binimran/dev-packWrote 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/m-binimran/dev-pack/a11y-audit)<a href="https://agentmods.dev/skills/m-binimran/dev-pack/a11y-audit"><img src="https://agentmods.dev/badge/skills/m-binimran/dev-pack/a11y-audit.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 | $0.00045 | $0.00344 |
| Opus 5 | $0.00023 | $0.00172 |
| Sonnet 5 | $0.00009 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00034 |
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 3d 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.
What it actually says
a11y-audit
Check against WCAG 2.2 AA. Report findings as must-fix vs. should-fix.
Checklist
- Semantics: real elements —
<button>not a clickable<div>;<nav>/<main>/<header>landmarks; lists are lists. - Keyboard: every interactive element reachable and operable by Tab/Enter/Space; logical order; no traps.
- Focus: visible focus indicator (don't
outline: nonewithout a replacement). - Labels: every input has a
<label>/aria-label; icon-only buttons have accessible names. - Images: meaningful
alt; decorative imagesalt="". - Contrast: text ≥ 4.5:1 (≥ 3:1 for large text). State the measured ratio, don't eyeball it.
- Forms: errors announced (
aria-live), associated with their field, not color-only. - Motion: respect
prefers-reduced-motion.
Output
- Findings grouped must-fix / should-fix, each with the exact element and the fix.
- Don't claim "accessible" from reading code alone — say what was checked statically vs. needs a real screen-reader/keyboard pass.
Guardrails
- ARIA is a last resort — prefer native HTML semantics.
- Don't add
role/aria-*that contradicts the element.
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.
- 3d ago First seen · 28 lines · 45 tokens per session scan A 50e3e762ff8c
a11y-audit is a skill published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 344 once invoked, about $0.0002 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
codoop-discover
Launch a collaborative product discovery session with multi-role experts (PM, GTM, UI, Architect). Use when exploring 0-to-1 design for a new product or feature. Orchestrates expert agents in-session to draft comprehensive backlog documentation through SNAP clarification, multi-perspective analysis, and consistency…
codoop-ux-walkthrough
Simulate a real task from a chosen user persona and write an evidence-backed, non-blocking experience report. Use after building a user-facing feature, when reviewing a runnable product flow, or when product owners want user-perspective improvement ideas without changing code automatically.
atomic-ui
Design or review DESIGN.md, UI tokens, and component ownership. Use when changing styling, theming, layout, or reusable UI structure.
frontend-design-quality
Ensure frontend design work follows established repo patterns, minimizes clicks, fills real viewports, stays responsive, avoids text overflow, reduces portal UI clutter, covers content-rich surfaces such as blogs/resources, and is verified with Playwright or equivalent visual screenshots. Use when building, changing…
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.