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/fidelity)<a href="https://agentmods.dev/commands/manavarya09/design-extract/fidelity"><img src="https://agentmods.dev/badge/commands/manavarya09/design-extract/fidelity/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/fidelity"><img src="https://agentmods.dev/badge/commands/manavarya09/design-extract/fidelity.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 | $0.00040 | $0.00466 |
| Opus 5.5 | $0.00016 | $0.00186 |
| Sonnet 5.5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
fidelity 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.
What it actually says
Run designlang fidelity to score a clone against the site it was cloned from. Unlike tools that just hand you code and claim "pixel-perfect", this measures it: a full-page pixel-diff for visuals and a motion-fidelity comparison (durations, easings, springs, keyframe kinds, scroll-linked motion, choreography/stagger) — blended into one score with a ranked plan of what to fix next.
npx designlang fidelity $ARGUMENTS
If no $ARGUMENTS were supplied, ask the user for the original URL and the
clone URL (often a local dev server like http://localhost:3000).
After the run, surface the overall score + grade, the visual/motion split, and the top correction directives. Outputs land in the output dir:
| File | What it is |
|---|---|
fidelity.md |
headline score, motion breakdown table, ranked correction plan |
fidelity.json |
the full machine-readable report |
fidelity-card.svg |
a shareable score card (88% · B · stripe.com) |
fidelity-diff.png |
the visual loss heatmap |
Useful flags via $ARGUMENTS:
| Flag | Effect |
|---|---|
--clone <url> |
the clone to score (required) |
--min <score> |
exit non-zero if overall fidelity is below this (CI gate) |
--motion-runtime |
capture real runtime motion + choreography on both sides |
This is the self-correcting clone loop: measure → read the correction plan →
rebuild → re-run until the score crosses your threshold. Pair with /extract
and /verify.
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.
- 1mo ago First seen · 43 lines · 40 tokens per session scan A e7850910618b
fidelity is a command published in the GitHub repository Manavarya09/design-extract (4,257 stars, last pushed 10d ago), licensed MIT. It adds 40 tokens to every session and 466 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.
print-audit
Audit a print layout for bleed, safe zone, color mode, font embedding, and page break rules. Optionally audits brand consistency when brand context is provided.