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.
git 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/pair)<a href="https://agentmods.dev/commands/manavarya09/design-extract/pair"><img src="https://agentmods.dev/badge/commands/manavarya09/design-extract/pair/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/commands/manavarya09/design-extract/pair"><img src="https://agentmods.dev/badge/commands/manavarya09/design-extract/pair.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 | $0.00060 | $0.00789 |
| Opus 5.5 | $0.00024 | $0.00316 |
| Sonnet 5.5 | $0.00012 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
pair 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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fuse the design DNA of two sites and emit an editorial pair card showing the crossover.
npx designlang pair $ARGUMENTS
If $ARGUMENTS doesn't contain at least two URLs, ask the user for the second one.
Both sites are extracted in parallel (~30s total). Outputs land in ./design-extract-output/:
*-x-*.pair.html— editorial pair card with cover, axis matrix, fused specimen*-x-*.pair.md— markdown summary (axis source table)*-x-*.pair.json— structured deltas (which axis came from where)*-x-*.pair.brand.html— full brand-guidelines book of the fused identity (only with--brand)
After the run completes:
- Read the markdown to summarise: which axis came from A, which from B
- Highlight the most distinctive crossover (the fused specimen quotes a real headline from whichever site contributed the voice)
- Offer to open the HTML pair card
Default axis split
| Axis | Default source | Why |
|---|---|---|
| Colour | A | Brand identity tends to lead with colour |
| Spacing | A | Spacing co-varies with the visual layout |
| Shape | A | Radii + shadows belong with the visual surface |
| Motion | A | Motion is part of the visual feel |
| Typography | B | The crossover moment — different voice |
| Voice | B | Tone, headings, CTA verbs from B |
| Components | B | Anatomy from B's library |
So the default is "Site A's visuals + Site B's words". Override any axis with --<axis>-from a|b.
Useful flags
| Flag | Effect |
|---|---|
--colors-from <a|b> |
Force colour source |
--typography-from <a|b> |
Force typography source |
--spacing-from <a|b> |
Force spacing source |
--shape-from <a|b> |
Force radii + shadows source |
--motion-from <a|b> |
Force motion source |
--voice-from <a|b> |
Force voice / tone / heading source |
--components-from <a|b> |
Force component anatomy source |
--brand |
Also emit a full brand-guidelines book of the fused identity |
--format html|md|json|all |
Pick output formats |
--open |
Open the HTML pair card |
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.
- 1mo ago First seen · 69 lines · 60 tokens per session scan A 092709fff668
pair is a command published in the GitHub repository Manavarya09/design-extract (4,257 stars, last pushed 11d ago), licensed MIT. It adds 60 tokens to every session and 789 once invoked, about $0.0002 per session on Opus 5.5. 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.
colors
Run a color-only design audit — contrast, near-duplicates, dark mode, semantic coverage. 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.
dashboard-layout
Design and build a complete dashboard layout — sidebar navigation, KPI cards, chart areas, data tables, filter bar, and responsive behavior. Outputs production-ready HTML/CSS.