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 skills add punkadillo/figma-code-composer --skill vanilla-extractgit clone --depth 1 https://github.com/punkadillo/figma-code-composerWrote 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/skills/punkadillo/figma-code-composer/vanilla-extract)<a href="https://agentmods.dev/skills/punkadillo/figma-code-composer/vanilla-extract"><img src="https://agentmods.dev/badge/skills/punkadillo/figma-code-composer/vanilla-extract/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/skills/punkadillo/figma-code-composer/vanilla-extract"><img src="https://agentmods.dev/badge/skills/punkadillo/figma-code-composer/vanilla-extract.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 | $0.00084 | $0.04937 |
| Opus 5.5 | $0.00034 | $0.01975 |
| Sonnet 5.5 | $0.00017 | $0.00987 |
| Haiku 4.5 | $0.00008 | $0.00494 |
Grade A, and why
vanilla-extract 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 2mo 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 — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vanilla Extract for React Components
Use this skill when implementing or refactoring React component styling with Vanilla Extract. It emphasizes zero-runtime CSS generation, strong TypeScript ergonomics, scalable variants, and safe theming patterns.
When to Apply
Use this skill when tasks include:
- Setting up Vanilla Extract with Vite + React
- Creating component styles in
.css.tsfiles - Building typed variant systems (
styleVariants,recipes) - Implementing design tokens and themes (
createTheme,createThemeContract) - Runtime variable updates (
@vanilla-extract/dynamic) - Global/reset styles (
globalStyle,createGlobalTheme) - Utility-first typed atoms with optional
@vanilla-extract/sprinkles
Core Mental Model
Vanilla Extract generates static CSS at build time from TypeScript style definitions.
style(...)=> one scoped classstyle([ ... ])=> composed class list, but still selector-safe inside Vanilla Extract- Theme helpers create typed CSS variable contracts, then classes/selectors assign values
- Runtime theming via
@vanilla-extract/dynamiconly assigns values to pre-defined vars; it does not generate new CSS rules
Setup (React + Vite)
- Install base package:
@vanilla-extract/css
- Install Vite integration:
@vanilla-extract/vite-plugin(dev dependency)
- Add plugin in
vite.config.ts:vanillaExtractPlugin()
Vite plugin identifiers
Choose identifier strategy depending on environment:
short: compact hashes (smaller output)debug: human-readable class/var names in development- custom function: fully custom naming based on
{ hash, filePath, debugId, packageName }
Use debug during active development and switch to short for production when needed.
File Conventions
- Put styles in
*.css.ts - Export class names and theme contracts from style modules
- Keep component logic in
*.tsxand import classes/contracts from style files - Co-locate styles next to components when component-specific; centralize tokens/themes in shared modules
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.
- 2mo ago First seen · 588 lines · 84 tokens per session scan A d6e215a7551f
vanilla-extract is a skill published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 4,937 once invoked, about $0.0003 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.
vanilla-extract compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vanilla-extractpunkadillo/figma-code-composer | Skill | 3 | 2mo ago | MIT | A | 84 | Claude Code, Codex |
| moai-design-toolsmodu-ai/moai-adk | Skill | 1.3k | 4d ago | Apache-2.0 | A | 45 | Claude Code |
| landing-page-generatorhybridlabor-api/bdb-dev-optimized-agent-skills | Skill | 6 | 5d ago | Apache-2.0 | A | 50 | Claude Code, Codex |
| rn-stylinglukedj78/dev-flow | Skill | 5 | yesterday | MIT | A | 195 | Claude Code |
| fintech-frontend-engineerpranav8494/team-of-agents | Skill | 7 | 1mo ago | MIT | A | 41 | Claude Code |
| web-artifacts-builderJasonxzWen/harness-hub | Skill | 69 | 3mo ago | none | A | 43 | Claude Code, Codex |
| artifacts-buildersaajunaid/caddis-plugin | Skill | 0 | yesterday | MIT | A | 40 | Claude Code, Codex |