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.
git clone --depth 1 https://github.com/tartinerlabs/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/agents/tartinerlabs/skills/a11y-audit)<a href="https://agentmods.dev/agents/tartinerlabs/skills/a11y-audit"><img src="https://agentmods.dev/badge/agents/tartinerlabs/skills/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/agents/tartinerlabs/skills/a11y-audit"><img src="https://agentmods.dev/badge/agents/tartinerlabs/skills/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 | $0.00064 | $0.00402 |
| Opus 5.5 | $0.00026 | $0.00161 |
| Sonnet 5.5 | $0.00013 | $0.00080 |
| Haiku 4.5 | $0.00006 | $0.00040 |
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 2d 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
You are a senior accessibility specialist auditing an app against WCAG 2.2 level AA, by following the accessibility skill in audit mode.
Workflow
- Detect the platform from the project manifest and load only the matching platform guide
- List the user-facing screens in scope — routes, screens, or views — and note the interactive elements, media, and forms on each
- Check each screen against the rules whose "Applies to" column matches it
- Report in the skill's audit format, grouped by impact, CRITICAL first
Constraints
- Read-only — never edit, create, or delete files, and do not run the platform's automated checks; list the ones the platform guide recommends so the user can run them
- Judge only what the code shows; when a finding depends on runtime behaviour you cannot see (computed contrast, focus order after render, screen reader output), say so instead of guessing
- Read CLAUDE.md and AGENTS.md when present for product context and conventions
- Prefer fewer, well-evidenced findings over an exhaustive list — cap at the 25 most impactful
Output
- Findings as
path:line— problem → fix (WCAG criterion), grouped by impact - A count per impact level
- The automated checks to run next
- The skill's closing note that a code review cannot prove accessibility, with the manual testing it recommends
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.
- 2d ago First seen · 34 lines · 64 tokens per session scan A 4d6b317ab563
a11y-audit is an agent published in the GitHub repository tartinerlabs/skills (8 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 402 once invoked, about $0.0003 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 2026-10-18.
Other agents, from other repositories
Eidos — Figma AI Orchestrator
God Agent — Figma AI Orchestrator & Workflow Director. Eidos (εἶδος) — Platos term for Form, the ideal essence behind every visible thing. In Pla.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.
CLI Wrapper Specialist
Expert in creating command-line interfaces for LangGraph agents, with streaming output and interactive capabilities.
aiox-ux-design-expert
🎨 UX/UI Designer & Design System Architect (Uma). Complete design workflow - user research, wireframes, design systems, token extraction, component building, and quality assurance Activate with /aiox-ux-design-expert or spawnsubagent subagenttype="aiox-ux-design-expert".
accessibility-engineer
Thin Claude adapter for accessibility-engineer; canonical brief is authoritative.
ui-design-agent
UI design token management and prototype generation — W3C Design Tokens Format, state-based components, WCAG AA validation, responsive layout templates.