design-extract is a command-line tool that examines live websites with a headless browser and turns their visual and interaction rules into design-system files. It is used by developers and designers to extract tokens, component details, responsive behavior, accessibility findings, and platform-specific outputs, while the catalogue commands, skills, plugin, and rule expose that process to coding agents.
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 agentmods add commands/manavarya09/design-extract/brandgit clone --depth 1 https://github.com/Manavarya09/design-extractWrote 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/commands/manavarya09/design-extract/brand)<a href="https://agentmods.dev/commands/manavarya09/design-extract/brand"><img src="https://agentmods.dev/badge/commands/manavarya09/design-extract/brand.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00859 |
| Opus 5 | $0.00031 | $0.00430 |
| Sonnet 5 | $0.00012 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
brand 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 6d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a self-contained, hand-off-ready brand-guidelines book from any live URL.
npx designlang brand $ARGUMENTS
If no URL is provided, ask the user which site to document.
Output goes to ./design-extract-output/:
*.brand.html— the editorial book (open this — it's a self-contained, print-ready document with TOC, smooth-scroll, dark-mode toggle)*.brand.md— terse markdown summary (good for diffing snapshots)*.brand.json— structured slice of the design with the surfaces the book renders
After the run completes:
- Read
*.brand.mdto summarise what was captured (host, page intent, material language, tone, palette size, type families, WCAG score) - Tell the user the headline numbers (
X tokens · Y fonts · grade Z) - Offer to open the HTML book (
--opendoes this automatically) - Suggest pairing:
/pack <url>if they want a developer-facing bundle to drop into a project,/grade <url>for the audit,/theme-swap <url>to derive a recoloured variant
What's in the book
| § | Chapter | What it documents |
|---|---|---|
| 00 | Essence | Synthesized brand personality: positioning statement, archetype (1 of 12 Jungian, with confidence), adjectives, and a four-axis meter (warmth · energy · weight · era) — every call traced to extracted signals |
| 01 | About | Page intent, material language, imagery style, component library, stack, voice tone |
| 02 | Logo | Extracted SVG logo + clearspace + dimensions |
| 03 | Colour | Brand colours with HEX/RGB/HSL/usage, neutrals grid, full palette, A11y callout |
| 04 | Typography | Display + body families, weights, scale table, large specimen |
| 05 | Spacing | Base unit, scale length, visual rhythm bars |
| 06 | Shape | Border radii visualised, shadow elevation system |
| 07 | Iconography | Icon library detection + captured icons grid |
| 08 | Motion | Feel, durations (animated dots), easings, spring presence, scroll-linked flag |
| 09 | Components | Detected components with slots/variants/sizes |
| 10 | Voice & tone | Tone, pronoun posture, heading case, top CTA verbs, sample headings |
| 11 | Accessibility | WCAG score, failing pairs table, suggested replacements |
| 12 | Tokens | Drop-in code blocks (CSS vars, Tailwind config) + cross-ref to pack |
| 13 | How to use | Six rules of thumb for derivative work |
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.
- 6d ago First seen · 61 lines · 62 tokens per session scan A 92833bf17ba6
brand is a command published in the GitHub repository Manavarya09/design-extract (4,048 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 859 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 2026-08-30.
Other commands, from other repositories
full-diagnostic
Comprehensive design system health sweep.
docs-coverage
Audit whether your documentation surface keeps pace with your components.
governance-review
Quarterly governance review package.
release-check
Pre-release validation pipeline for a component.
component-audit
Audit your component library inventory.
describe-component
Generate an AI-optimised component description.