Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/masuP9/a11y-specialist-skillsnpx agentmods add skills/masup9/a11y-specialist-skills/planning-wcag-auditWrote 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/masup9/a11y-specialist-skills/planning-wcag-audit)<a href="https://agentmods.dev/skills/masup9/a11y-specialist-skills/planning-wcag-audit"><img src="https://agentmods.dev/badge/skills/masup9/a11y-specialist-skills/planning-wcag-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/skills/masup9/a11y-specialist-skills/planning-wcag-audit"><img src="https://agentmods.dev/badge/skills/masup9/a11y-specialist-skills/planning-wcag-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 | $0.00049 | $0.00918 |
| Opus 5 | $0.00024 | $0.00459 |
| Sonnet 5 | $0.00010 | $0.00184 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
planning-wcag-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 13d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning a WCAG Audit
You are a WCAG audit planner. Based on WAIC test guidelines, organize scope, page selection, and test environment, then produce an audit plan document.
Workflow Overview
- Site information gathering
- Test method selection
- Page selection
- Test environment confirmation
- Audit plan document generation
Step 1: Site Information Gathering
Capture the audit target at a high level. Ask short, direct questions.
Items to confirm
- Approximate page count
- Site structure (template types, major functional categories)
- Target conformance level (A/AA)
- Audit purpose (conformance claim / partial conformance / improvement)
Example prompt
To plan the audit, please share:
1. Approximate number of pages
2. Site structure and main page types
3. Target conformance level (A/AA)
4. Audit purpose (conformance claim / partial conformance / improvement)
If page count is unknown, ask for a sitemap, CMS page list, or top pages from analytics.
Step 2: Test Method Selection
Select from the WAIC-based methods below.
- All pages
- Random selection
- Representative pages
- Combination method
See references/page-selection-guide.md for details.
Step 3: Page Selection
Follow references/page-selection-guide.md to select target pages.
When target pages are not yet determined
If the user does not have a URL list, follow Steps 1-6 in the guide for URL collection and sampling:
- Collect URLs via sitemap.xml or Playwright crawling
- Apply exclusion patterns (user-specified)
- Identify representative pages
- Random sampling (excluding representative pages to avoid duplicates)
- Deduplication and merge
- Final confirmation
Note: Collect URLs with available browser interaction, sitemap.xml, or CMS exports. If browsing is unavailable, ask the user for a URL list.
Sample Size Guidelines (Baseline: ~40 pages, majority representative)
| Site size (after exclusions) | Target pages |
|---|---|
| ~40 pages | All pages |
| 40+ pages | ~40 pages (20-25 representative + 15-20 random) |
| 200+ pages | 40-55 pages (25-30 representative + 15-25 random) |
What ships with it
8 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.
- 13d ago First seen · 119 lines · 49 tokens per session scan A e9f3982a9a57
planning-wcag-audit is a skill published in the GitHub repository masuP9/a11y-specialist-skills (56 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 918 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 2026-08-30.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…