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 salawi45/skill-wcag-accessibility --skill wcag-accessibilitygit clone --depth 1 https://github.com/salawi45/skill-wcag-accessibilityWrote 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/salawi45/skill-wcag-accessibility/wcag-accessibility)<a href="https://agentmods.dev/skills/salawi45/skill-wcag-accessibility/wcag-accessibility"><img src="https://agentmods.dev/badge/skills/salawi45/skill-wcag-accessibility/wcag-accessibility/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/salawi45/skill-wcag-accessibility/wcag-accessibility"><img src="https://agentmods.dev/badge/skills/salawi45/skill-wcag-accessibility/wcag-accessibility.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 | $0.00145 | $0.03363 |
| Opus 5.5 | $0.00058 | $0.01345 |
| Sonnet 5.5 | $0.00029 | $0.00673 |
| Haiku 4.5 | $0.00015 | $0.00336 |
Grade A, and why
wcag-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 1mo 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WCAG Accessibility Skill
Engineering standard: WCAG 2.2 Level AA (always). Legal layer: Optional, jurisdiction-specific. Applied on top of the technical standard — never mixed into it.
This skill has four modes. Detect mode from context; switch fluidly mid-conversation.
| Mode | When to use |
|---|---|
| Mode 1 — Component Advisor | Building or modifying any UI component, page, or layout |
| Mode 2 — Test Runner | PR review, CI pipeline, or explicit audit request |
| Mode 3 — Issue Reporter | Formatting findings from either mode as structured issue records |
| Mode 4 — Jurisdiction Advisor | User asks about legal requirements, compliance scope, or jurisdiction mapping |
Most build tasks use Mode 1 → Mode 3. Most audit tasks use Mode 2 → Mode 3. Mode 4 is additive — layer it on when legal context is present.
Mode 1: Component Advisor
Use when creating or modifying any frontend component, page, or layout.
Guiding Principle
Accessibility is structural, not cosmetic. Semantic HTML done right covers ~70% of WCAG compliance before any ARIA is needed. Work through the checklist below in order.
Build Checklist
1. Semantic Structure
- Use the right element:
<button>for actions,<a>for navigation,<nav><main><header><footer><section><article>for landmarks - Never make a
<div>or<span>interactive withoutrole+tabindex - Headings
h1–h6form a logical outline — never skip levels - WCAG: 1.3.1, 4.1.2
2. Keyboard Navigation
- All interactive elements reachable and operable via keyboard alone
- Tab order matches visual reading order
- No keyboard traps — modals must trap focus intentionally but release on Escape
- Provide a skip link:
<a href="#main-content" class="skip-link">Skip to main content</a> - Custom widgets (dropdowns, tabs, date pickers, dialogs) must follow APG patterns — see
references/aria-patterns.md - WCAG: 2.1.1, 2.1.2, 2.4.1, 2.4.3
3. Focus Management
- Visible focus indicator: minimum 3:1 contrast ratio against adjacent color, non-zero area
- Never
outline: nonewithout a replacement that meets contrast - Modal opens → move focus inside; modal closes → return focus to trigger
- SPA route changes → move focus to page
<h1>or skip link - WCAG: 2.4.7, 2.4.11, 3.2.1
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 288 lines · 145 tokens per session scan A acdb14cb1617
wcag-accessibility is a skill published in the GitHub repository salawi45/skill-wcag-accessibility (2 stars, last pushed 7mo ago), licensed MIT. It adds 145 tokens to every session and 3,363 once invoked, about $0.0006 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.
Other skills, from other repositories
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
kb-cognitive-accessibility
Reference data, not a reviewer. Review UI for cognitive load, plain language clarity, and WCAG 2.2 cognitive SC (3.3.7, 3.3.8, 3.3.9). Includes COGA guidance, reading level, auth patterns, and timeout warnings.
kb-design-system
Reference data, not a reviewer. Validate design system tokens for WCAG AA/AAA contrast. Compute color token contrast, focus ring validation (WCAG 2.4.13), motion tokens, and spacing for touch targets across frameworks.
alt-text-headings
Alt text, SVGs, figures, charts, heading order, page titles and landmarks.
cognitive-accessibility
Plain language, WCAG 2.2 cognitive criteria, COGA guidance and auth UX.
contrast-master
Color contrast, themes, dark mode, non-text contrast and color-only meaning.