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 sso-ss/vibe-ship-it --skill generate-design-mdgit clone --depth 1 https://github.com/sso-ss/vibe-ship-itWrote 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/sso-ss/vibe-ship-it/generate-design-md)<a href="https://agentmods.dev/skills/sso-ss/vibe-ship-it/generate-design-md"><img src="https://agentmods.dev/badge/skills/sso-ss/vibe-ship-it/generate-design-md/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/sso-ss/vibe-ship-it/generate-design-md"><img src="https://agentmods.dev/badge/skills/sso-ss/vibe-ship-it/generate-design-md.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 | $0.00110 | $0.07290 |
| Opus 5.5 | $0.00044 | $0.02916 |
| Sonnet 5.5 | $0.00022 | $0.01458 |
| Haiku 4.5 | $0.00011 | $0.00729 |
Grade B, and why
generate-design-md scanned grade B 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 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Do not lecture about design systems or the DESIGN.md format How it starts
The opening of the file, as written. The whole thing — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate DESIGN.md
Takes a website URL and produces a complete DESIGN.md file -- a plain-text design system document that any AI coding agent can read to build UI that matches that site's look and feel.
How It Works
- Designer gives a URL
- Fetch the page HTML and all linked CSS
- Extract every visual token: colors, fonts, spacing, shadows, radii, component patterns
- Analyze the visual atmosphere and design philosophy
- Detect the page structure (sections, grids, layout patterns)
- Generate three files:
DESIGN.md-- the complete design system (9 sections)- Tailwind config extension -- tokens mapped to utility classes
- CSS variables -- tokens as custom properties in globals.css
- Drop them in the project
One command. No questions. The designer just sees the result.
When To Use
- "I like how linear.app looks -- capture that"
- "Generate a design md from stripe.com"
- "Make my app look like this site"
- "Use vercel.com as a design reference"
- "Grab the design from notion.so"
- "Copy the style of airbnb.com"
Extraction Process
Step 1: Fetch (multi-pass)
Do multiple fetches to maximize what you capture:
Pass 1: HTML Fetch the target URL. From the HTML, extract:
- All
<link rel="stylesheet" href="...">URLs - All
<style>blocks (including<style data-*>for CSS-in-JS SSR output) - All
style="..."inline attributes on elements <meta name="theme-color" content="...">for brand color- Google Fonts / Typekit
<link>URLs (reveals exact font families and weights) <link rel="icon">and<link rel="apple-touch-icon">(brand color clues)
Pass 2: CSS files Fetch each discovered stylesheet URL. If a URL returns 403/404:
- Try removing query strings
- Try the base domain +
/styles.css,/main.css,/globals.css - Try common CDN patterns:
cdn.example.com/css/... - Move on if blocked -- note which sources were inaccessible
Pass 3: Critical CSS extraction
Many modern sites inline critical CSS in <style> tags in the <head>. This often contains:
- CSS custom properties (
:root { --color-primary: ... }) - Font-face declarations
- Key component styles
- Media queries with breakpoints
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 · 629 lines · 110 tokens per session scan B da46a68a24b2
generate-design-md is a skill published in the GitHub repository sso-ss/vibe-ship-it (12 stars, last pushed 6mo ago), licensed MIT. It adds 110 tokens to every session and 7,290 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.