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 mae616/design-skills --skill accessibility-engineergit clone --depth 1 https://github.com/mae616/design-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/mae616/design-skills/accessibility-engineer)<a href="https://agentmods.dev/skills/mae616/design-skills/accessibility-engineer"><img src="https://agentmods.dev/badge/skills/mae616/design-skills/accessibility-engineer/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/mae616/design-skills/accessibility-engineer"><img src="https://agentmods.dev/badge/skills/mae616/design-skills/accessibility-engineer.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 | $0.00038 | $0.00956 |
| Opus 5.5 | $0.00015 | $0.00382 |
| Sonnet 5.5 | $0.00008 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
accessibility-engineer 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Engineer Skill
When to Apply
Apply this skill when the request involves:
- Accessibility, a11y, WAI-ARIA, screen reader support, semantic HTML, keyboard navigation, focus management
- アクセシビリティ対応、WAI-ARIA、スクリーンリーダー対応、セマンティックHTML、キーボード操作、フォーカス管理
- Any UI implementation (should be applied alongside other skills)
Core Principles (Most Important)
- Native elements first. Solve with proper HTML elements (
button,a,label,input, etc.) before reaching for ARIA. - ARIA is minimal. Don't add
role/aria-*to make things "seem" accessible. Only add when there's a real requirement. - Operable = Communicable. Not just visually—assistive tech must receive state, name, and purpose. This is the Definition of Done.
- Keyboard is the baseline. Mouse-only UI is incomplete. Design focus movement and operations first.
Implementation Rules
1) Semantic Structure
- Maintain heading order (
h1→h2→ ...). Don't skip levels for styling. - Create landmarks for main regions (
header,nav,main,footer,asideif needed). - Use
ul/ol/lifor lists,dl/dt/ddfor definitions—notdivsubstitutes.
2) Accessible Names
- Buttons, links, inputs need "names" (labels read by screen readers).
- Priority: Visible text
- Fallback:
aria-label(when visible text isn't possible) - Composition:
aria-labelledby(referencing existing elements)
- Icon-only buttons/links MUST have names (e.g., "Search", "Close").
3) Forms (Required)
- Associate
labelwithinput(for/id). Never use placeholder as the only label. - Communicate required/optional, errors, hints machine-readably (e.g.,
aria-describedbyfor helper text). - Errors must explain: what's wrong, why, and how to fix.
4) States and Announcements (Dynamic UI)
- Use native
disabledattribute first (button disabled, etc.). - For toggles, use
aria-pressed/aria-expandedonly when native elements aren't sufficient. - Use
aria-livefor async completion/failure announcements—but don't overuse.
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 · 87 lines · 38 tokens per session scan A 3ab7144acb19
accessibility-engineer is a skill published in the GitHub repository mae616/design-skills (11 stars, last pushed 9mo ago), licensed MIT. It adds 38 tokens to every session and 956 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.
accessibility-engineer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| accessibility-engineermae616/design-skills | Skill | 11 | 9mo ago | MIT | A | 38 | Claude Code |
| 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 |