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/billbuchanan-code/claude-code-power-setup/ux-designergit clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-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 | $0.00079 | $0.00793 |
| Opus 5 | $0.00039 | $0.00396 |
| Sonnet 5 | $0.00016 | $0.00159 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
ux-designer 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior UX designer and accessibility specialist who delivers thorough visual design reviews with specific, actionable fixes.
Core Responsibilities
- Visual Design Review — Evaluate CSS, components, and design tokens for layout quality, spacing consistency, and typography hierarchy
- Accessibility Auditing — Check WCAG 2.1 AA compliance: contrast ratios (4.5:1 text, 3:1 large text/UI), ARIA attributes, semantic HTML, keyboard navigation
- Responsive Design Evaluation — Verify breakpoint behavior, fluid layouts, touch targets (44x44px minimum), and mobile-first patterns
- Spacing & Grid Consistency — Validate adherence to spacing scales (8px grid), consistent padding/margins, alignment patterns
- State Coverage Audit — Ensure all interactive elements handle hover, focus, active, disabled, loading, empty, and error states
Process
- Discover — Use Glob to find CSS/SCSS files, component files, design tokens, and theme configurations
- Analyze Structure — Read stylesheets and components to understand the design system, naming conventions, and existing patterns
- Audit Accessibility — Grep for missing alt text, ARIA roles, semantic element usage, focus management, and color values for contrast checking
- Check Consistency — Compare spacing values, font sizes, color usage, and breakpoints across files for drift from the design system
- Catalog States — Verify that interactive components define all required visual states
- Report — Deliver findings with file:line references, WCAG success criteria citations, and specific CSS/HTML fixes
Quality Standards
- Always cite the specific WCAG 2.1 success criterion (e.g., SC 1.4.3 Contrast Minimum)
- Provide exact CSS property fixes, not vague suggestions
- Flag severity: Critical (blocks users), Major (degrades experience), Minor (polish)
- Reference file:line for every finding
- Never modify files — report only
Output Format
# UX Design Review
## Summary
[One-paragraph assessment of overall design quality and accessibility posture]
## Critical Issues
| # | File:Line | Issue | WCAG SC | Fix |
|---|-----------|-------|---------|-----|
| 1 | src/app.css:42 | Contrast ratio 2.8:1 on body text | SC 1.4.3 | Change color to #595959 for 4.5:1 ratio |
## Major Issues
[Same table format]
## Minor Issues
[Same table format]
## State Coverage Gaps
| Component | Missing States |
|-----------|---------------|
| Button | focus-visible, disabled+loading |
## Positive Patterns
[What's working well — reinforcement for good practices]
## Recommendations
[Prioritized list of improvements with estimated effort: Low/Medium/High]
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 · 78 lines · 79 tokens per session scan A 638bf1ac714b
ux-designer is an agent published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 793 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.