What is extract-design-md?

A design-document generator that records a brand's visual style from a website URL or screenshot. DESIGN.md is a structured file describing colors, typography, layout, motion, and other visual details.

Use it to document a brand's colors, fonts, container widths, corner styles, tone, and distinctive design details in the standard DESIGN.md format.

It creates a consistent reference for rebuilding or reusing a brand's look instead of relying on memory or scattered observations.

extract-design-md — Skill for Claude Code by realmpastai-web

Install

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.

Clone the repo

git clone --depth 1 https://github.com/realmpastai-web/claude-design-suite

agentmods

npx agentmods add skills/realmpastai-web/claude-design-suite/extract-design-md

Made for: Claude Code.

Or install brand-intelligence, the plugin that ships this one along with the rest of its 8 skills, 4 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/realmpastai-web/claude-design-suite/extract-design-md/github.svg)](https://agentmods.dev/skills/realmpastai-web/claude-design-suite/extract-design-md)

Your own site

<a href="https://agentmods.dev/skills/realmpastai-web/claude-design-suite/extract-design-md"><img src="https://agentmods.dev/badge/skills/realmpastai-web/claude-design-suite/extract-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/realmpastai-web/claude-design-suite/extract-design-md"><img src="https://agentmods.dev/badge/skills/realmpastai-web/claude-design-suite/extract-design-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 435 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00059	$0.00435
Opus 5	$0.00030	$0.00217
Sonnet 5	$0.00012	$0.00087
Haiku 4.5	$0.00006	$0.00044

Measured 11d ago against content hash b56104ad7a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

extract-design-md 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 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.

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.

plugins/brand-intelligence/skills/extract-design-md/SKILL.md · 42 lines

What it actually says

Extract DESIGN.md

Context

You are a design-systems archivist documenting a brand's visual language from $ARGUMENTS (URL or screenshot). Use the canonical template at design-refs/_template/DESIGN.md.

Domain Context

DESIGN.md is the emerging standard for machine-readable brand references (see getdesign.md).
Extraction is part automation (scraping computed styles, OG images), part expert judgment (naming voice adjectives, spotting signature motion).
Screenshots are lossy for color — always ask for a URL if one exists.

Instructions

Ask for a URL (preferred) or screenshot. Capture what category this brand belongs in.
Run:
```
python scripts/generate_design_md.py "<url-or-path>" --out design-refs/<category>/<brand>/DESIGN.md
```
The script will:
- Fetch the page + screenshot (if URL)
- Parse computed styles for the top-3 most-used colors
- Detect web-font imports for typography
- Grab container widths + common radii from the CSS
- Use a vision pass to name tone adjectives
Review the generated DESIGN.md and fill gaps manually:
- Brand voice (always needs human judgment)
- Signature details (the thing users remember)
- Further reading links
Run python scripts/lint.py design-refs/<category>/<brand>/DESIGN.md to validate frontmatter.
Offer to add the brand to design-refs/README.md's category table.

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 · 42 lines · 59 tokens per session scan A b56104ad7a54

Subscribe to this mod's changes

extract-design-md is a skill published in the GitHub repository realmpastai-web/claude-design-suite (2 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 435 once invoked, about $0.0003 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.

Design and UX

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.

nexu-io/open-design · 41 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

extract-design-md