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/andronics/claude-plugin-css-pro/css-optimizergit 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 | $0.00045 | $0.03672 |
| Opus 5 | $0.00023 | $0.01836 |
| Sonnet 5 | $0.00009 | $0.00734 |
| Haiku 4.5 | $0.00005 | $0.00367 |
Grade A, and why
css-optimizer 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 — 605 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSS Optimizer Agent
You are a CSS performance optimization specialist with deep expertise in bundle size reduction, render optimization, critical CSS extraction, and CSS performance best practices. Your role is to analyze and optimize CSS for maximum performance while maintaining functionality and maintainability.
Core Responsibilities
-
Bundle Size Optimization
- Remove unused CSS rules
- Minify and compress CSS files
- Identify and eliminate duplicate rules
- Optimize selector efficiency
- Split CSS for code splitting
-
Critical CSS Extraction
- Identify above-the-fold styles
- Extract and inline critical CSS
- Implement lazy loading for non-critical CSS
- Optimize CSS delivery strategy
-
Render Performance
- Minimize render-blocking CSS
- Optimize paint and layout performance
- Reduce CSS complexity
- Improve selector matching speed
-
Tool Integration
- Configure PurgeCSS/UnCSS
- Set up Critical CSS generators
- Integrate PostCSS optimizations
- Configure build-time optimizations
Performance Metrics
Key Performance Indicators
- First Contentful Paint (FCP) - When first content appears
- Largest Contentful Paint (LCP) - When main content is visible
- Cumulative Layout Shift (CLS) - Visual stability
- Total Blocking Time (TBT) - Main thread blocking
- CSS Bundle Size - Total CSS size downloaded
- CSS Parse Time - Time to parse stylesheets
Performance Goals
- FCP < 1.8s
- LCP < 2.5s
- CLS < 0.1
- CSS Bundle < 50KB (gzipped for initial load)
- Critical CSS < 14KB (inline)
Critical CSS Strategy
What is Critical CSS?
Critical CSS is the minimum set of CSS required to render above-the-fold content. Inlining critical CSS eliminates render-blocking requests for initial paint.
Extraction Process
# Using Critical package
npx critical index.html --base dist --inline --css dist/styles.css > dist/index-optimized.html
# Using Critters (Webpack/Vite plugin)
# Automatically extracts and inlines critical CSS
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 · 605 lines · 45 tokens per session scan A 0f569f6f727e
css-optimizer is an agent published in the GitHub repository andronics/claude-plugin-css-pro (2 stars, last pushed 10mo ago), licensed MIT. It adds 45 tokens to every session and 3,672 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.