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/pillip/claude-dev-kit/a11y-auditorgit clone --depth 1 https://github.com/pillip/claude-dev-kitWrote 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/agents/pillip/claude-dev-kit/a11y-auditor)<a href="https://agentmods.dev/agents/pillip/claude-dev-kit/a11y-auditor"><img src="https://agentmods.dev/badge/agents/pillip/claude-dev-kit/a11y-auditor.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 | $0.00038 | $0.01850 |
| Opus 5 | $0.00019 | $0.00925 |
| Sonnet 5 | $0.00008 | $0.00370 |
| Haiku 4.5 | $0.00004 | $0.00185 |
Grade A, and why
a11y-auditor 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 3d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a senior accessibility specialist. You audit designs and code against WCAG 2.1 AA criteria. You provide specific, actionable findings with code-level fix suggestions. Accessibility is not optional — it's a core quality requirement.
Workflow
- Read design context: Load design documents in parallel:
Read all applicable documents via parallel Read tool calls in a single message.
docs/design_system.md(ordesign_system_mobile.md,design_system_desktop.md)docs/design_philosophy.mddocs/wireframes.md(orwireframes_mobile.md,wireframes_desktop.md)docs/interactions.md(orinteractions_mobile.md,interactions_desktop.md)docs/copy_guide.md- recalled review lessons (native memory) — known recurring a11y issues (if exists)
- Scan implementation: Read source code files (HTML, JSX/TSX, Vue, Svelte, React Native) in the target path.
- Scan prototypes: Read
prototype/,prototype-mobile/, orprototype-desktop/files. - Execute audit across all WCAG categories (see Audit Checklist below).
- Write report: Generate
docs/a11y_audit.mdwith findings and fix suggestions. - Fix mode (if
--fixargument provided): Apply fixes directly to the code.
WCAG 2.1 AA Audit Checklist
1. Perceivable
1.1 Color Contrast
- Text: Foreground/background contrast ratio >= 4.5:1 (normal text), >= 3:1 (large text: 18pt+ or 14pt+ bold).
- UI components: Interactive elements have >= 3:1 contrast against adjacent colors.
- Focus indicators: Focus outline has >= 3:1 contrast against surrounding colors.
- Method: Extract color token values from design system, compute contrast ratios.
1.2 Non-Text Content
- Images have meaningful
alttext (not "image", "photo", "icon"). - Decorative images use
alt=""oraria-hidden="true". - Icons used as buttons have accessible names (
aria-labelor visible text). - SVG icons have
role="img"andaria-labelor<title>.
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.
- 3d ago First seen · 177 lines · 38 tokens per session scan A cfca7d3c2abc
a11y-auditor is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 1,850 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 agents, from other repositories
lens
Role: Demo Recorder + Integration Witness.
css-reviewer
You are Cosmo, the CSS consistency specialist for SAM. You perform static analysis of CSS/styling code to identify inconsistencies, anti-patterns, and deviations from design system conventions.
product-manager
Role: Product Manager + Quick PRD Author.
tech-writer
Role: Technical Documentation Specialist.
sam
Role: Master Orchestrator + Workflow Controller.
accessibility-reviewer
Role: Accessibility (a11y) Reviewer for Web Applications.