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-optimizegit 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 | $0.00011 | $0.01330 |
| Opus 5 | $0.00005 | $0.00665 |
| Sonnet 5 | $0.00002 | $0.00266 |
| Haiku 4.5 | $0.00001 | $0.00133 |
Grade A, and why
css-optimize 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSS Performance Optimization
I'll analyze and optimize your CSS for better performance, smaller bundle size, and faster rendering.
Target Files
Optimizing: $ARGUMENTS
If no specific files provided, I'll optimize all CSS files in the project.
Optimization Strategy
Phase 1: Analysis
I'll first analyze your CSS to identify optimization opportunities:
-
Bundle Size Analysis
- Current size (uncompressed, minified, gzipped)
- Unused CSS detection
- Duplicate rule identification
- Optimization potential calculation
-
Performance Audit
- Selector complexity analysis
- Render-blocking detection
- Critical CSS identification
- Animation performance check
-
Opportunity Assessment
- Prioritize optimizations by impact
- Estimate size savings
- Calculate performance improvements
Phase 2: Optimization
Based on analysis, I'll apply these optimizations:
1. Remove Unused CSS
Tool: PurgeCSS / Manual analysis
Expected savings: 30-70% of bundle size
Actions:
- Scan HTML/JS/templates for used classes
- Remove unused rules
- Keep safelist patterns (dynamic classes)
2. Eliminate Duplicates
Expected savings: 5-15% of bundle size
Actions:
- Find duplicate rules
- Merge identical selectors
- Extract common patterns
3. Optimize Selectors
Performance impact: 20-50% faster style calculation
Actions:
- Reduce selector depth (max 3 levels)
- Remove universal selectors
- Simplify attribute selectors
- Flatten deeply nested rules
4. Minify & Compress
Expected savings: 60-80% with gzip
Actions:
- Remove whitespace and comments
- Shorten color values (#ffffff → #fff)
- Combine similar rules
- Optimize property values
5. Extract Critical CSS
Performance impact: 1-2s faster FCP
Actions:
- Identify above-the-fold styles
- Extract critical CSS (< 14KB)
- Set up async loading for remaining CSS
6. Optimize Animations
Performance impact: Smooth 60fps animations
Actions:
- Convert layout-triggering to transform/opacity
- Add will-change appropriately
- Remove/limit expensive properties
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 · 245 lines · 11 tokens per session scan A 66574853a2ee
css-optimize is a command published in the GitHub repository andronics/claude-plugin-css-pro (2 stars, last pushed 10mo ago), licensed MIT. It adds 11 tokens to every session and 1,330 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.