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 commands/andronics/claude-plugin-css-pro/css-auditgit clone --depth 1 https://github.com/andronics/claude-plugin-css-proWhat 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 | $0.00013 | $0.02224 |
| Opus 5 | $0.00006 | $0.01112 |
| Sonnet 5 | $0.00003 | $0.00445 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
css-audit 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 yesterday.
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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSS Comprehensive Audit
I'll perform a complete audit of your CSS covering all aspects: performance, accessibility, best practices, browser compatibility, and code quality.
Audit Scope
This is a comprehensive audit that examines:
✓ Performance - Bundle size, render speed, critical CSS ✓ Accessibility - WCAG 2.2 compliance, contrast, focus ✓ Best Practices - Code quality, methodology, maintainability ✓ Browser Compatibility - Cross-browser support, fallbacks ✓ Security - CSS injection risks, safe patterns
Audit Categories
1. Performance Audit
Metrics I'll Measure:
- Bundle size (uncompressed, minified, gzipped)
- Unused CSS percentage
- Selector complexity
- Render-blocking resources
- Critical CSS opportunities
- Animation performance
Performance Checks:
- Bundle size < 50KB (gzipped)
- Unused CSS < 20%
- No universal selectors
- Animations use transform/opacity only
- Critical CSS identified and separated
- CSS loading optimized
2. Accessibility Audit (WCAG 2.2)
Level A Checks:
- Color not sole indicator of information
- All functionality keyboard accessible
- Skip navigation available
- No keyboard traps
Level AA Checks:
- Text contrast ≥ 4.5:1 (7:1 for AAA)
- Large text contrast ≥ 3:1
- UI components contrast ≥ 3:1
- Focus indicators visible
- Touch targets ≥ 44x44px
- Text can resize to 200%
Level AAA Checks:
- Text contrast ≥ 7:1
- Enhanced visual presentation
- No time limits on interactions
Motion & Animation:
- prefers-reduced-motion support
- No auto-playing animations
- No flashing content (seizure risk)
- Parallax warnings
3. Best Practices Audit
Code Quality:
- Consistent naming convention
- Appropriate methodology (BEM, etc.)
- Low specificity (average < 30)
- Minimal nesting depth (≤ 3 levels)
- No !important abuse
- Proper code organization
Maintainability:
- Clear file structure
- Documented complex logic
- No duplicate rules
- Modular, reusable patterns
- Version control friendly
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.
- yesterday First seen · 357 lines · 13 tokens per session scan A 1de0e6996a47
css-audit is a command published in the GitHub repository andronics/claude-plugin-css-pro (2 stars, last pushed 10mo ago), licensed MIT. It adds 13 tokens to every session and 2,224 once invoked, about $0.0001 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 commands, from other repositories
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
status
Show 3d-design team status and recent activity.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
frontend-3d
You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.