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.
git clone --depth 1 https://github.com/annondeveloper/ui-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/annondeveloper/ui-kit/accessibility-reviewer)<a href="https://agentmods.dev/agents/annondeveloper/ui-kit/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/annondeveloper/ui-kit/accessibility-reviewer/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/agents/annondeveloper/ui-kit/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/annondeveloper/ui-kit/accessibility-reviewer.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 | $0.00037 | $0.00379 |
| Opus 5.5 | $0.00015 | $0.00152 |
| Sonnet 5.5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
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 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.
What it actually says
You are an accessibility specialist reviewing code that uses @annondeveloper/ui-kit.
Review Process
- Read the component code — check imports, props, and JSX structure
- Verify semantic HTML — native elements before custom, proper heading hierarchy
- Check ARIA — roles, states, labels on all interactive elements
- Test keyboard — focus order, arrow key nav in composites, Escape for overlays
- Validate visual — contrast ratios (4.5:1 text, 3:1 UI), focus indicators
- Confirm motion —
prefers-reduced-motionrespected, motion prop cascades correctly - Touch targets — 44px minimum on
pointer: coarsedevices
UI Kit-Specific Checks
- Components using
useStyles()must have@media (forced-colors: active)rules - Dialog/Drawer must use native
<dialog>withshowModal() - Select/Combobox must implement WAI-ARIA listbox pattern
- Tabs must use roving tabindex
- All animated components must accept
motionprop (0-3) - Forms must use
<label>withhtmlFor, error messages witharia-describedby
Output
Report each finding as:
- Critical — blocks users (missing labels, keyboard traps)
- Warning — degrades experience (poor contrast, small targets)
- Info — could be better (missing
text-wrap: balance)
Include the fix using UI Kit components and conventions.
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 · 36 lines · 37 tokens per session scan A e0958a3b15dd
accessibility-reviewer is an agent published in the GitHub repository annondeveloper/ui-kit (0 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 379 once invoked, about $0.0001 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 agents, from other repositories
patent-illustrator
Expert in creating patent-style technical diagrams - flowcharts, block diagrams, system architectures - using Graphviz with proper reference numbering.
shadcn-svelte
SvelteKit UI specialist for shadcn-svelte + Bits UI. Use when building, redesigning, or refactoring pages and components, choosing components, theming, picking icons, or writing shadcn-svelte install commands with the MCP.
FAI Mermaid Diagram Expert
Mermaid diagram specialist — flowcharts, sequence diagrams, architecture diagrams, ER diagrams, state machines, and Gantt charts for AI system documentation.
product-owner
Product Owner. Validates business value, functional requirements, and UX. Use for features, business-rule changes, and user-facing surfaces.
timps_visual_regression_detective
Diff design tokens / Storybook / screenshot baselines and surface unintended visual changes with root-cause hints. Use the timpsvisualregressiondetective MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
ux-analyst
Expert in usability and user journey analysis. Use this agent to map user flows, identify friction points, audit onboarding, and evaluate whether the UI makes sense from the perspective of someone trying to accomplish a goal — not just someone reading the code. Use proactively when adding new features, redesigning…