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/sitegit 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/site)<a href="https://agentmods.dev/commands/manavarya09/design-extract/site"><img src="https://agentmods.dev/badge/commands/manavarya09/design-extract/site.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 | $0.00025 | $0.00453 |
| Opus 5 | $0.00013 | $0.00227 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
site 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.
What it actually says
Run designlang site against the user-provided URL. Instead of reading one page, it crawls the site's canonical pages (home, pricing, docs, blog, about, product…), extracts each, and synthesizes a single de-duplicated design system weighted by how broadly each token is used.
npx designlang site $ARGUMENTS
If no $ARGUMENTS were supplied, ask the user which site to analyze.
Default output goes to ./design-extract-output/. When it finishes, read the
generated files and present a tight summary:
*-site-consistency.md— the consistency grade (A–F · score), the per-category breakdown, and the off-system outlier tokens (introduced by a single page) that are candidates to consolidate.*-site-coverage.md— which tokens are 🟢 site-wide, 🟡 section, or 🔴 page-local, and which pages use each.*-site-system.json— the canonical unified tokens.
The standard pack (DTCG tokens, Tailwind, shadcn theme, CSS variables,
*-design-language.md) is also emitted — but from the whole-site canonical
system, not just the homepage.
Useful flags via $ARGUMENTS:
| Flag | Effect |
|---|---|
--max-pages <n> |
crawl up to N pages including the homepage (default 6) |
--out <dir> |
output directory |
--name <prefix> |
output filename prefix |
Then offer follow-ups:
/grade <url>— single-page Design Report Card + SVG badge/studio— open the live token editor over the latest extraction/pack <url>— bundle every output into one design-system directory
Full reference: https://github.com/Manavarya09/design-extract#full-cli-reference
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 · 46 lines · 25 tokens per session scan A 65774d08b332
site is a command published in the GitHub repository Manavarya09/design-extract (4,048 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 453 once invoked, about $0.0001 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
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.
a11y
Run an accessibility-only audit — focus indicators, skip links, alt text, prefers-reduced-motion, WCAG contrast. Scoped variant of /ui-ux-suite:audit.
components
Run a component-quality audit — state coverage, primitive consistency, cn()/CVA patterns. Scoped variant of /ui-ux-suite:audit.
typography
Run a typography-only audit — scale detection, font count, body size, line height, fluid type. Scoped variant of /ui-ux-suite:audit.
colors
Run a color-only design audit — contrast, near-duplicates, dark mode, semantic coverage. Scoped variant of /ui-ux-suite:audit.
figma-component-library
Generate a complete component library in Figma from a design system config — atoms, molecules, and organisms with all variants, auto layout, and component properties.