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 supercharge-growth/ai-design-skills --skill design-token-extractor-by-strangergit clone --depth 1 https://github.com/supercharge-growth/ai-design-skillsWrote 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/supercharge-growth/ai-design-skills/design-token-extractor-by-stranger)<a href="https://agentmods.dev/skills/supercharge-growth/ai-design-skills/design-token-extractor-by-stranger"><img src="https://agentmods.dev/badge/skills/supercharge-growth/ai-design-skills/design-token-extractor-by-stranger/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/supercharge-growth/ai-design-skills/design-token-extractor-by-stranger"><img src="https://agentmods.dev/badge/skills/supercharge-growth/ai-design-skills/design-token-extractor-by-stranger.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 | $0.00078 | $0.00874 |
| Opus 5 | $0.00039 | $0.00437 |
| Sonnet 5 | $0.00016 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00087 |
Grade A, and why
design-token-extractor-by-stranger 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 12d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Token Extractor
Turns a visual reference (Figma URL, screenshot, or pasted CSS) into a normalized tokens.json that downstream code-gen skills can consume.
When to use
- "Pull design tokens from this Figma file"
- "What colors and fonts are in this screenshot?"
- "Extract the design system before I start coding"
- As a first step before figma-to-tailwind or similar code-gen skills
When NOT to use
- The user already has a
tokens.jsonor design system spec — use it directly - The user wants pixel-perfect implementation of a single component (use figma-to-tailwind instead)
Inputs
One of:
- A Figma frame or file URL (use the Figma MCP if connected)
- An uploaded screenshot (PNG/JPG)
- A pasted CSS/SCSS/Tailwind config
Steps
- Identify the source. If Figma URL and the Figma MCP is connected, fetch styles directly. Otherwise inspect the image or text.
- Extract by category:
color— name + hex, group by role (brand, neutral, semantic)typography— font family, weights, sizes (px and rem), line-heights, letter-spacingspacing— scale used for padding/margin/gapradius— corner radii in useshadow— elevation/shadow styles
- Normalize names. Use semantic names where intent is clear (
color.brand.primary), neutral names otherwise (color.gray.900). Never invent values — if uncertain, markTODO: confirm. - Output
tokens.jsonin the format below. - Print a summary of what was extracted and flag anything ambiguous.
Output format
{
"color": {
"brand": { "primary": "#0B5FFF", "primaryHover": "#0848C2" },
"neutral": { "0": "#FFFFFF", "100": "#F5F6F8", "900": "#0E1116" },
"semantic": { "success": "#1DB954", "danger": "#E5484D" }
},
"typography": {
"fontFamily": { "sans": "Inter, system-ui, sans-serif" },
"fontSize": { "xs": "12px", "sm": "14px", "base": "16px", "lg": "18px" },
"fontWeight": { "regular": 400, "medium": 500, "semibold": 600 },
"lineHeight": { "tight": 1.2, "normal": 1.5 }
},
"spacing": { "1": "4px", "2": "8px", "3": "12px", "4": "16px", "6": "24px", "8": "32px" },
"radius": { "sm": "4px", "md": "8px", "lg": "12px", "full": "9999px" },
"shadow": {
"sm": "0 1px 2px rgba(0,0,0,0.06)",
"md": "0 4px 12px rgba(0,0,0,0.08)"
}
}
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.
- 12d ago First seen · 71 lines · 78 tokens per session scan A 54760671cfa2
design-token-extractor-by-stranger is a skill published in the GitHub repository supercharge-growth/ai-design-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 874 once invoked, about $0.0004 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 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 $ultragoal 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.