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/orlando-japan/claude-code-setting/accessibilitynpx skills add orlando-japan/claude-code-setting --skill accessibilitygit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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/orlando-japan/claude-code-setting/accessibility)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/accessibility"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/accessibility.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 | $0.00030 | $0.01344 |
| Opus 5 | $0.00015 | $0.00672 |
| Sonnet 5 | $0.00006 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
accessibility 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 4d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility
Accessibility is not a feature to add later. The cost of retrofitting is 10–100x the cost of doing it right the first time. It's also a legal requirement in many jurisdictions.
The four WCAG principles
- Perceivable — users must be able to perceive the content (vision, hearing, touch).
- Operable — users must be able to operate the interface (keyboard, pointer, voice).
- Understandable — content and behavior must be understandable.
- Robust — must work with assistive technologies.
Target WCAG 2.1 AA unless you have a reason to go higher.
Practical rules, by category
Semantic HTML
Use the right element for the job. The browser and screen readers already know what <button> is; <div onClick> makes you reimplement all of it badly.
<button>for actions.<a href>for navigation.<input>+<label>for form fields (label associated byfor+idor wrapping).<nav>,<main>,<article>,<aside>,<header>,<footer>for page structure.- Heading hierarchy:
h1→h2→h3, no skipping. Oneh1per page.
If you use a div instead of a button, you owe: role="button", tabindex="0", keyboard handling (Enter and Space), focus styles, and any other native button behavior. It's not worth it.
Keyboard
Every interactive element must be reachable and operable via keyboard alone.
- Tab moves between interactive elements.
- Shift+Tab goes back.
- Enter and Space activate buttons.
- Escape closes modals.
- Arrow keys navigate within composite widgets (menus, tabs, grids).
Test: unplug your mouse. Can you use the whole page?
Focus
- Visible focus outline on every interactive element. Don't
outline: noneunless you're replacing it with something equally visible. Obvious focus indicators are a WCAG requirement. - Focus order matches visual order. Don't skip around because of positional CSS.
- Focus management on dynamic UI. When a modal opens, focus goes into the modal. When it closes, focus returns to the trigger.
aria-modal+ focus trap.
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.
- 4d ago First seen · 114 lines · 30 tokens per session scan A 64ec1b33dfeb
accessibility is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 1,344 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
accessibility
Web accessibility essentials covering semantic HTML, keyboard navigation, ARIA usage, focus management, contrast, and accessible forms. Load before building any interactive component.
design-md
Author/validate/export Google's DESIGN.md token spec files.
web-accessibility-audit
Audit web applications for WCAG accessibility compliance. Use when asked to run accessibility checks, identify common violations, and provide remediation guidance.
Accessibility Auditor
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
Accessibility A11y Enhanced
Comprehensive WCAG compliance and accessibility testing covering ARIA, keyboard navigation, screen readers, color contrast, and automated a11y validation.