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 renky1025/agent-skills --skill design-md-extractorgit clone --depth 1 https://github.com/renky1025/agent-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/renky1025/agent-skills/design-md-extractor)<a href="https://agentmods.dev/skills/renky1025/agent-skills/design-md-extractor"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/design-md-extractor/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/renky1025/agent-skills/design-md-extractor"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/design-md-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 11 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 20 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 63 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 171 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 189 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 192 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 196 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 198 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00160 | $0.02376 |
| Opus 5 | $0.00080 | $0.01188 |
| Sonnet 5 | $0.00032 | $0.00475 |
| Haiku 4.5 | $0.00016 | $0.00238 |
Grade A, and why
design-md-extractor 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design MD Extractor
Extract a visual design system from any website URL and generate a DESIGN.md conforming to the google-labs-code/design.md specification.
Do's
- Follow the spec exactly. The output must have valid YAML front matter (color hex values, typography objects with complete properties) and correct section order. Every generated file should pass
npx @google/design.md lint. - Include fontFeature and fontVariation when observed in the source site's
@font-faceor computed styles. These are part of the Typography token spec. - Use token references in components. Component properties like
backgroundColormust use{colors.primary}syntax, not hardcoded hex values, per the spec. - Document every observed component state. Hover, focus, active, selected, pressed — each state maps to a separate component entry (e.g.,
button-primary,button-primary-hover). - Capture full CSS for shadows. Write
0 4px 6px rgba(0,0,0,0.1)not "subtle shadow". Downstream consumers need parseable box-shadow values. - Verify colors against screenshots. CSS inspection can miss overlay effects and gradient blends. Cross-check with visual evidence.
- Provide open-source font substitutes. Proprietary fonts need documented alternatives (Inter, DM Sans, etc.).
- Write brand voice as design critique. The Overview section should read like a designer describing visual personality, not a feature list.
- Name tokens by role (primary, secondary, surface, ink) not by appearance — unless the descriptive name is the brand's own convention.
Don'ts
- Don't invent placeholder values. If a token category is missing, skip it. Fabricated values break the design system.
- Don't mix tokens from multiple themes. If a site has light and dark modes, ask the user which to document. Never blend both into one DESIGN.md.
- Don't use generic Do's/Don'ts. Every rule must reference a specific token or property. "Use good contrast" is useless; "Reserve
{colors.tertiary}for primary actions only" is actionable. - Don't omit lineHeight or letterSpacing. Typography tokens without these are incomplete per the spec.
- Don't flatten layered shadows. Multiple box-shadow layers must be preserved as-is with commas.
- Don't skip the Overview. It's the design rationale that guides future decisions. Without it, the document is just a token dump.
- Don't use duplicate section headings. The spec errors on duplicate
##headings (e.g., two## Colorssections). - Don't use unknown YAML keys at the top level. Only
version,name,description,colors,typography,rounded,spacing, andcomponentsare valid in front matter.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 236 lines · 160 tokens per session scan A f7e01370c6e6
design-md-extractor is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 160 tokens to every session and 2,376 once invoked, about $0.0008 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
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.