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/dnagit 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/dna)<a href="https://agentmods.dev/commands/manavarya09/design-extract/dna"><img src="https://agentmods.dev/badge/commands/manavarya09/design-extract/dna.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 | $0.00019 | $0.00435 |
| Opus 5 | $0.00010 | $0.00217 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
dna 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
/dna
Extract a site's design language and locate it in designlang's measured design space: a 30-feature vector covering colour, type, space, shape and motion.
Unlike /grade, which returns an absolute letter, /dna is comparative — every
number is a rank against a corpus of real design systems.
Usage
designlang dna <url>
designlang dna <url> --corpus ./my-corpus.json
Build your own reference frame — your products, your competitors, whatever you want to be measured against:
designlang dna-corpus acme.com acme.com/pricing competitor.com
What you get
*-dna.json— the vector, the raw measurements behind it, neighbours, percentiles*-dna.md— a readable report: where it sits per axis, its nearest design systems, and the features that make it look the way it does
Reading the output
- Distance is the mean absolute difference across the features both designs
have —
0.14means the average feature is 14% of its range apart. - Percentiles are ranks within the corpus, not judgements. A design far from the middle is unusual, which may be exactly the intent.
- Coverage tells you how much of the vector was measurable. A comparison built from a third of the features is a weaker claim, and the report says so.
Instructions
- Run
designlang dna <url>for the URL the user names. - Read the emitted
*-dna.md. - Summarise: the nearest systems and what separates them, the axes where the design is an outlier, and — if the user is trying to hit a target look — which axes to move and in which direction.
- If no corpus exists yet, say so and offer to build one with
dna-corpus.
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 · 50 lines · 19 tokens per session scan A 8de09a21aedf
dna is a command published in the GitHub repository Manavarya09/design-extract (4,048 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 435 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
full-diagnostic
Comprehensive design system health sweep.
describe-component
Generate an AI-optimised component description.
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.