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/marcusgoll/Spec-Flownpx agentmods add skills/marcusgoll/spec-flow/design-tokensWrote 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/marcusgoll/spec-flow/design-tokens)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/design-tokens"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/design-tokens/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/marcusgoll/spec-flow/design-tokens"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/design-tokens.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 | $0.00000 | $0.12576 |
| Opus 5.5 | $0.00000 | $0.05030 |
| Sonnet 5.5 | $0.00000 | $0.02515 |
| Haiku 4.5 | $0.00000 | $0.01258 |
Grade A, and why
design-tokens 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 — 1,262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Tokens - Comprehensive Reference
Version: 2.0.0 Purpose: Generate and maintain design system tokens across all project surfaces (UI, emails, PDFs, CLI, charts, docs)
Overview
This skill provides comprehensive guidance for initializing and maintaining design tokens in design/systems/tokens.json and tokens.css. Supports both brownfield (scan existing code) and greenfield (generate new palette) modes.
Coverage:
- UI components (React/Vue/Svelte)
- MJML/HTML emails
- PDF styling (WeasyPrint, Puppeteer)
- CLI colors (chalk/colorette)
- Data visualization (d3, Chart.js, Recharts)
- Documentation assets (MD/MDX)
What Changed in v2
Non-UI surface coverage:
- MJML/HTML emails (inline CSS)
- PDF styling (WeasyPrint, Puppeteer CSS)
- CLI colors (chalk/colorette)
- Data visualization palettes (d3, Chart.js, Recharts)
- Documentation assets (MD/MDX)
Brownfield scan improvements:
- Source-agnostic: JSX/TSX, CSS/SCSS, CSS-in-JS, MD/MDX, MJML, Python/JS PDF styles
- Scans 10+ file types
- Detects arbitrary Tailwind values (
bg-[#xxx])
Contrast enforcement:
- Auto-nudges OKLCH lightness until WCAG 2.1 passes (≥4.5:1)
- Uses colorjs.io for perceptually accurate contrast calculation
Tailwind v4 alignment:
- Theme variables as CSS variables (not hardcoded palette)
- Validates tokens.css import in globals.css
Color-blind-safe palettes:
- Okabe-Ito categorical palette for charts
- 8 colors scientifically validated for color-blind users
Mental Model
Flow: detect mode → scan/generate → consolidate → validate wiring → contrast fixups → emit artifacts → report debt
Brownfield: Scan existing code for patterns across UI, emails, PDFs, CLI, charts, docs. Consolidate duplicates and propose migrations.
Greenfield: Ask minimal questions, generate OKLCH palette with contrast validation.
Prerequisites
Dependencies:
{
"devDependencies": {
"colorjs.io": "^0.5.0",
"picocolors": "^1.0.0",
"fs-extra": "^11.2.0"
}
}
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 · 1,262 lines · 0 tokens per session scan A 9997d5dff030
design-tokens is a skill published in the GitHub repository marcusgoll/Spec-Flow (96 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 12,576 tokens. 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 2026-08-30.
design-tokens compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-tokensmarcusgoll/Spec-Flow | Skill | 96 | 1mo ago | MIT | A | 0 | Claude Code |
| 3d-web-experiencesickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 45 | Claude Code |
| agent-reelssickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 31 | Claude Code |
| accesslint-scansickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 32 | Claude Code |
| anti-ui-slopsickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 39 | Claude Code |
| ux-reviewDonchitos/Claude-Code-Game-Studios | Skill | 37k | 21d ago | MIT | A | 42 | Claude Code |
| antigravity-design-expertsickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 39 | Claude Code |