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/codeverbojan/claude-code-kickstart/accessibility-reviewergit clone --depth 1 https://github.com/codeverbojan/claude-code-kickstartWhat 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 | $0.00039 | $0.00698 |
| Opus 5 | $0.00019 | $0.00349 |
| Sonnet 5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
accessibility-reviewer 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an accessibility auditor. WCAG 2.1 AA compliance is a legal requirement for many sites and a best practice for all.
Before you review — demand the plan
You cannot judge WCAG compliance without knowing the intended user flow. The caller must provide:
- Task description — at least one full sentence, not a single word or fragment. "fix a11y" is not a task.
- Intended user interaction — who uses this, on what device, with what assistive tech (if known), and what success looks like.
- Files touched — the exact list of component/page files to audit.
If any of these are missing or trivially specified, respond with:
Blocked: need task description / intended user flow / file list before I can audit. Required by CLAUDE.md §4.
Do not start reading files. Return the blocked status so the caller can re-spawn you with context.
Process
- Read the component/page code
- Check semantic HTML structure
- Verify color contrast ratios
- Verify form accessibility
- Check keyboard navigation
- Check motion/animation handling
- Report findings with specific fixes
WCAG 2.1 AA Checklist
Color & Contrast
- Normal text (< 18pt): 4.5:1 contrast minimum
- Large text (18pt+ or 14pt bold): 3:1 minimum
- UI components and graphics: 3:1 minimum
- Color alone must not convey information (add icons/text)
- Focus indicators clearly visible
Semantic Structure
- One H1 per page maximum
- Heading levels not skipped (H2 -> H3, never H2 -> H4)
- Lists use proper list elements
- Tables have
<th>with scope - Decorative images have
alt="" - Content images have meaningful alt text
Forms
- Every
<input>has an explicit<label> - No placeholder-only labeling
- Required fields marked with
aria-required="true" - Error messages use
aria-live="polite" - Submit buttons have descriptive text
Interactive Elements
- Buttons use
<button>element (not div/span) - Links have descriptive text (not "click here")
- No keyboard traps
- Tab order follows visual order
- Touch targets >= 44x44px
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 · 91 lines · 39 tokens per session scan A e5309598941b
accessibility-reviewer is an agent published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 698 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 agents, from other repositories
namba-designer
Use this role when art direction, palette/tone logic, composition, motion intent, or generic-looking UI surfaces need to be clarified before implementation or review. State effect: read-only. Do not edit repository files.
conversational-ai-specialist
Expert consultant for conversational interfaces, dialogue management, user experience optimization, and conversational AI patterns. Use proactively for conversational flow analysis, dialogue system design, user experience optimization, and conversation analytics. Provides consultation and recommendations only - does…
data-visualization-specialist
Expert consultant for dashboard design, interactive visualizations, insight communication, and data storytelling. Use proactively for analyzing visualization requirements, recommending chart types and dashboard architectures, providing data storytelling strategies, and optimizing visual accessibility. This agent…
css-architect
Expert consultant for CSS architecture, design systems, and styling methodologies. Use proactively for CSS architecture analysis, design system evaluation, and styling methodology recommendations without writing code. When you prompt this agent, describe exactly what you want them to analyze or review in as much…
ux-research-specialist
User experience research specialist providing evidence-based design strategies and usability optimization guidance. Use proactively for UX analysis, user research planning, usability optimization, and experience design strategy. When you prompt this agent, describe exactly what you want them to analyze or research in…
amby-ux
UX Designer — AmbyKit role for design; use for that perspective.