Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dylantarre/design-system-skillsnpx agentmods add skills/dylantarre/design-system-skills/style-dictionaryWrote 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/dylantarre/design-system-skills/style-dictionary)<a href="https://agentmods.dev/skills/dylantarre/design-system-skills/style-dictionary"><img src="https://agentmods.dev/badge/skills/dylantarre/design-system-skills/style-dictionary/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/dylantarre/design-system-skills/style-dictionary"><img src="https://agentmods.dev/badge/skills/dylantarre/design-system-skills/style-dictionary.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 | $0.00044 | $0.03201 |
| Opus 5 | $0.00022 | $0.01600 |
| Sonnet 5 | $0.00009 | $0.00640 |
| Haiku 4.5 | $0.00004 | $0.00320 |
Grade C, and why
style-dictionary scanned grade C with 1 finding 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"tokens:clean": "rm -rf build/", How it starts
The opening of the file, as written. The whole thing — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Style Dictionary
Overview
Set up Style Dictionary to transform design tokens into platform-specific formats. The industry standard for design systems that need to output to web, iOS, Android, and other platforms from a single token source.
When to Use
- Setting up a new design system with multi-platform needs
- Converting Figma tokens to code
- Generating CSS, SCSS, iOS Swift, Android XML from one source
- Adding custom token transforms or formats
- Integrating tokens into a build pipeline
Quick Reference: Core Concepts
| Concept | Purpose | Example |
|---|---|---|
| Token | Design value with metadata | { "value": "#3b82f6", "type": "color" } |
| Transform | Converts token values | color/hex → color/rgb |
| Format | Outputs to file type | CSS variables, Swift, XML |
| Platform | Target environment | web, ios, android |
The Process
- Assess token sources: Where are tokens defined? (Figma, JSON, YAML)
- Identify platforms: Which platforms need tokens?
- Set up config: Create
style-dictionary.config.js - Define transforms: Add any custom value transformations
- Build: Run
style-dictionary build
Implementation Checklist
Copy this checklist when setting up Style Dictionary:
Style Dictionary Setup:
- [ ] Install: `npm install style-dictionary`
- [ ] Create tokens/ directory with source JSON files
- [ ] Create style-dictionary.config.js with source paths and platform outputs
- [ ] Add build script to package.json: `"tokens:build": "style-dictionary build"`
- [ ] Run build and verify output files are generated correctly
Project Setup
Installation
npm install style-dictionary
# or
yarn add style-dictionary
Directory Structure
tokens/
├── base/
│ ├── colors.json
│ ├── spacing.json
│ └── typography.json
├── semantic/
│ ├── colors.json
│ └── components.json
└── themes/
├── light.json
└── dark.json
build/ # Generated output
├── css/
│ └── variables.css
├── ios/
│ └── StyleDictionary.swift
└── android/
└── colors.xml
style-dictionary.config.js
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.
- 11d ago First seen · 610 lines · 44 tokens per session scan C 86317f663a2b
style-dictionary is a skill published in the GitHub repository dylantarre/design-system-skills (42 stars, last pushed 8mo ago), licensed MIT. It adds 44 tokens to every session and 3,201 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.