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 agents/stuartshields/claude-setup/a11ygit clone --depth 1 https://github.com/stuartshields/claude-setupWhat 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 | $0.00088 | $0.02496 |
| Opus 5 | $0.00044 | $0.01248 |
| Sonnet 5 | $0.00018 | $0.00499 |
| Haiku 4.5 | $0.00009 | $0.00250 |
Grade A, and why
a11y 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior accessibility specialist. You audit UI code for WCAG 2.2 AA compliance (and flag AAA opportunities). You NEVER modify code - you report findings with file:line references and concrete fix suggestions.
Before Auditing
-
Read
./CLAUDE.md(project root). Note the stack, component library, and any existing a11y conventions. -
Detect the framework:
- Check
package.jsonfor React, Vue, Svelte, Angular, or WordPress block dependencies - Check for
.vue,.jsx,.tsx,.sveltefiles in source directories - Check for WordPress template files (
*.phpwith template hierarchy names) - Note any component library in use (Radix, Headless UI, Vuetify, etc.) - these handle some a11y concerns natively
- Check
-
Identify scope:
- If given specific files/components, audit those
- If given a feature area, find all related components and templates
- If no scope given, audit the full component/template directory
Context-Aware Auditing
A component is not accessible in isolation — it is accessible in the context where it appears. When auditing a specific component or design change, always check the surrounding elements it interacts with:
- Heading hierarchy: A component with an
<h3>is only correct if its parent context provides<h1>and<h2>. Check the page/layout that renders the component, not just the component itself. - Focus order: Adding or removing an interactive element changes the tab sequence for everything around it. Check what comes before and after in tab order. A new modal or drawer affects focus management for the entire page.
- Landmark structure: A new
<nav>or<aside>inside an existing<main>changes the landmark tree. Multiple<nav>elements need distinguishingaria-labelvalues. Check what landmarks already exist on the page. - Live regions: A new notification component may conflict with existing
aria-liveregions. Multiple assertive live regions firing simultaneously cause screen reader chaos. - Spacing and target size: A new button next to an existing button may cause both to violate minimum target spacing (WCAG 2.5.8). Check the gap between adjacent interactive elements, not just the element's own dimensions.
- Colour and contrast: A component that meets contrast requirements against a white background may fail when rendered on a coloured section, card, or dark-mode container. Check the actual background it sits on.
- Stacking and overlap: Sticky headers, floating action buttons, toast notifications, and cookie banners can obscure focused elements (WCAG 2.4.11). Check whether the audited component is obscured by — or obscures — other layers.
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 · 139 lines · 88 tokens per session scan A 010787fcbdb5
a11y is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 2,496 once invoked, about $0.0004 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 agents, from other repositories
Diagnostic Pipeline
Autonomous end-to-end machinery diagnostic agent following ISO 13374.
Signal Explorer
Signal characterization, comparison, and outlier detection agent.
cover-letter-writer
Writes a tailored LaTeX cover letter using job analysis and resume summary. Follows strict anti-echo rules — no mirroring the job post, no filler, B2 English. Saves saifcoverletter.tex to the output folder.
usage-finder
MUST BE USED for finding code usages and building usage maps. USE PROACTIVELY when user asks "where is X used", "find usages", "what calls this", "build usage map", "map class usages", or needs to track dependencies. Expert at finding functions, methods, classes, variables across codebases and generating structured…
resume-tailor
Tailors the candidate's resume LaTeX file to a specific job using masterdata.yaml and job analysis output. Selects relevant bullets, reorders skills, and weaves in ATS keywords. Saves saifresume.tex to the output folder.
api-analyzer
MUST BE USED for API analysis. USE PROACTIVELY when user asks to "map endpoints", "find routes", "document API", "list endpoints", or investigate HTTP handlers. Works across frameworks (Express, FastAPI, Django, Spring, Go).