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/lesleslie/css-mcp/css-audit-projectgit clone --depth 1 https://github.com/lesleslie/css-mcpWhat 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 | $0.00020 | $0.00280 |
| Opus 5 | $0.00010 | $0.00140 |
| Sonnet 5 | $0.00004 | $0.00056 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
css-audit-project 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 2d 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.
What it actually says
/css-audit-project
Run a comprehensive CSS audit across a project directory.
Usage
/css-audit-project <project-path> [--include PATTERN] [--exclude PATTERN]
What it does
- Calls
mcp__css__list_capabilitiesto confirm the server is healthy and surface the available tool set. - Calls
mcp__css__analyze_project_csswith the project path and any include/exclude glob patterns. - For any file the project scanner flags as a complexity hotspot, falls back to
mcp__css__analyze_css_summaryon the individual file to give the user a quick-mode breakdown without re-walking the directory. - Returns per-file metrics plus the project-wide rollup (total rules, average specificity, complexity distribution, top optimization opportunities).
Example
/css-audit-project /Users/les/Projects/my-app --include '**/*.css' --exclude '**/dist/**'
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.
- 2d ago First seen · 25 lines · 20 tokens per session scan A 833a215946fc
css-audit-project is a command published in the GitHub repository lesleslie/css-mcp (1 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 20 tokens to every session and 280 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
polish
Final quality pass: alignment, spacing, consistency, design system adherence, typography, interaction states, and code cleanup. Replaces polish + normalize + distill.
ux-evolve
Auto-iterate the lint→polish→re-lint loop on a generated artifact until score crosses 90 or plateaus. Triggers on "polish this", "evolve this surface", "improve until score 90+", "auto-fix", "run the loop". Use when the user has a freshly generated surface that needs automatic refinement to ship-ready quality. Skip…
seo-speed
Analyzes the site load performance — bundle size, unoptimized images, render-blocking scripts, missing lazy loading and estimated Core Web Vitals. TRIGGER when the user enters /seo-speed or asks to analyze speed, performance or Core Web Vitals.
review-css-complexity
Scan codebase for overly complex CSS/styling patterns that should be simplified.
dark-mode-specialist
Use when dark mode looks wrong. Pure black surfaces, elevation that disappears, brand colours that vibrate against dark, a white flash on load, or a mode toggle that does not persist.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.