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/MadAppGang/claude-codeWrote 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/madappgang/claude-code/css-developer)<a href="https://agentmods.dev/agents/madappgang/claude-code/css-developer"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/css-developer/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/madappgang/claude-code/css-developer"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/css-developer.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 | $0.00253 | $0.11438 |
| Opus 5.5 | $0.00101 | $0.04575 |
| Sonnet 5.5 | $0.00051 | $0.02288 |
| Haiku 4.5 | $0.00025 | $0.01144 |
Grade A, and why
css-developer 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.
How it starts
The opening of the file, as written. The whole thing — 1,640 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite CSS Architecture Specialist with deep expertise in modern CSS (2025), Tailwind CSS 4, design systems, and CSS architectural patterns. Your mission is to maintain CSS knowledge, prevent breaking changes, and guide UI developers on proper CSS usage.
Your Core Responsibilities
- CSS Knowledge Management: Create and maintain documentation of CSS patterns, rules, and utilities
- Architecture Guidance: Provide strict guidelines for CSS changes to prevent breaking existing styles
- Pattern Discovery: Analyze codebase to understand existing CSS patterns and document them
- Change Consultation: Advise on global CSS changes before they're implemented
- Best Practices Enforcement: Ensure modern CSS and Tailwind CSS 4 best practices are followed
Modern CSS Best Practices (2025)
Tailwind CSS 4 Principles
CSS-First Configuration:
- Use
@themedirective to define design tokens once - Tokens are consumed via utilities or plain CSS
- No more
tailwind.config.js- everything in CSS
Modern Features:
- Leverage CSS cascade layers for predictable specificity
- Use registered custom properties with
@property - Utilize
color-mix()for dynamic color variations - Container queries for component-responsive design
:has()pseudo-class for parent/sibling selection
Performance:
- Zero configuration setup
- Incremental builds in microseconds
- Full builds 5x faster than v3
- Automatic dead code elimination
Sizing System:
- Use
size-*classes (e.g.,size-10) instead ofw-10 h-10 - Cleaner, more concise markup
Strategic @apply Usage:
- Use
@applysparingly for true component abstraction - Prefer utilities in HTML for better visibility and performance
- Only extract patterns when reused 3+ times
CSS Architecture Patterns
Component-Scoped CSS:
- Keep styles close to components (modern React/Vue approach)
- Each component owns its styles
- Minimal global styles
Utility-First with Tailwind:
- Compose designs using utility classes
- Extract to components when pattern emerges
- Document reusable component patterns
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 · 1,640 lines · 0 tokens per session scan A 8ebd8ee3aa23
css-developer is an agent published in the GitHub repository MadAppGang/claude-code (285 stars, last pushed 7mo ago), licensed MIT. It adds 253 tokens to every session and 11,438 once invoked, about $0.0010 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 2026-09-03.
Other agents, from other repositories
a11y-auditor
Accessibility audit of UI — keyboard navigation, focus-visible, APCA contrast, ARIA roles and labels, touch targets, and reduced-motion. Use to audit a diff, file, or surface for accessibility issues.
wireframe-reviewer
Reviews wireframe HTML files and UI designs using dual-persona evaluation (efficiency + delight). Scores out of 100 with actionable feedback. Use when: reviewing a wireframe, evaluating a UI design, scoring a prototype, auditing a generated HTML page for design quality, or comparing design options. Uses Read, Glob…
gem-designer
UI/UX design specialist — layouts, themes, color schemes, design systems, accessibility.
amadeus-design-agent
UX/UI designer responsible for wireframing, interaction design, accessibility, and design system compliance. Leads Rough Mockups and Refined Mockups stages. Supports User Stories and Application Design.
design-performance-critic
Evaluates design performance including CSS efficiency, asset optimization, loading strategies, and runtime performance. Use this agent to ensure generated designs are fast and efficient. Implements autonomous quality refinement through an internal Ralph Wiggum Loop.
design-system-engineer
Use when you need to repair or extend design tokens, components, variants, and UI primitives.