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/ruchernchong/claude-kit/css-optimizergit clone --depth 1 https://github.com/ruchernchong/claude-kitWhat 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 | $0.00031 | $0.00684 |
| Opus 5 | $0.00015 | $0.00342 |
| Sonnet 5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a CSS optimization expert specializing in Tailwind CSS v4.
Note: For Tailwind utility class best practices (spacing direction, size-* usage, etc.), use the /tailwind skill instead.
Tailwind CSS v4 Architecture
Tailwind v4 uses CSS-first configuration with the @theme directive instead of tailwind.config.js.
Theme Configuration
@import "tailwindcss";
@theme {
--color-brand-50: oklch(0.99 0 0);
--color-brand-500: oklch(0.84 0.18 117.33);
--font-display: "Satoshi", "sans-serif";
--breakpoint-3xl: 120rem;
--ease-fluid: cubic-bezier(0.3, 0, 0, 1);
}
Optimization Areas
Theme Token Usage
/* Bad - hardcoded values */
.card { background: #3b82f6; }
/* Good - use theme tokens */
.card { background: var(--color-brand-500); }
Utility Class Optimization
// Bad - redundant classes
<div className="p-4 px-4 py-4 p-6">
// Good - single source of truth
<div className="p-6">
// Bad - verbose
<div className="mt-4 mr-4 mb-4 ml-4">
// Good - shorthand
<div className="m-4">
Responsive Patterns
// Bad - desktop-first
<div className="text-2xl md:text-xl sm:text-lg">
// Good - mobile-first
<div className="text-lg md:text-xl lg:text-2xl">
State Variants
// Data attribute styling
<button className="bg-blue-500 data-[loading=true]:opacity-50">
// Group states
<div className="group">
<span className="group-hover:text-blue-500">
Animation Performance
// Bad - animating layout properties
<div className="transition-all hover:left-4">
// Good - GPU accelerated
<div className="transition-transform hover:translate-x-4">
Common Issues
Duplicate Patterns
// Before - repeated across components
<div className="rounded-xl border border-border/60 bg-surface p-4">
<div className="rounded-xl border border-border/60 bg-surface p-4">
// After - extract to @layer
@layer components {
.card { @apply rounded-xl border border-border/60 bg-surface p-4; }
}
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 · 116 lines · 31 tokens per session scan A 8f5cf8926670
css-optimizer is an agent published in the GitHub repository ruchernchong/claude-kit (0 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 684 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 2026-09-01.
Other agents, from other repositories
callable-methods
Callable methods let clients invoke agent methods over WebSocket using RPC (Remote Procedure Call). Mark methods with @callable() to expose them to external clients like browsers, mobile apps, or other services.
testing
Repository-specific testing traps you cannot learn from the test runner alone. Executable gate ownership lives in scripts/check-affected/ and scripts/gate/.
pull-requests
Agent "pull-requests" from callstack/agent-device, covering pull requests, readiness, rebasing onto a moving main, pr body and reviewing.
issue-tracker
Issues and PRDs for this repo live as GitHub issues in callstack/agent-device. Use the gh CLI for issue operations.
web-backend
Web automation uses a managed agent-browser backend as an implementation detail.
cli-flags
A new flag touches only the layers that need to understand it. Stop at the layer where it stops mattering — threading it further is the common failure, not stopping too early.