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 skills add nathanonn/agent-skills --skill extract-design-systemgit clone --depth 1 https://github.com/nathanonn/agent-skillsWrote 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/skills/nathanonn/agent-skills/extract-design-system)<a href="https://agentmods.dev/skills/nathanonn/agent-skills/extract-design-system"><img src="https://agentmods.dev/badge/skills/nathanonn/agent-skills/extract-design-system/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/skills/nathanonn/agent-skills/extract-design-system"><img src="https://agentmods.dev/badge/skills/nathanonn/agent-skills/extract-design-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 179 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00178 | $0.02928 |
| Opus 5 | $0.00089 | $0.01464 |
| Sonnet 5 | $0.00036 | $0.00586 |
| Haiku 4.5 | $0.00018 | $0.00293 |
Grade A, and why
extract-design-system 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 9d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract a full design system bundle
Given a live URL, run the 9-stage pipeline and emit a bundle under
.design_systems/<domain>-YYYYMMDD/ (host dots→hyphens). The output bundle layout and the
AGENTS.md consumption template are specified in references/output-bundle-spec.md.
URL ─▶ 1 DISCOVER ─▶ 2 TOKENS ─▶ 3 COMPONENT SWEEP ─▶ 4 CLUSTER + CURATE
─▶ 5 DISTILL ─▶ 6 STATES ─▶ 7 SECTIONS ─▶ 8 SYNTHESIZE ─▶ 9 VALIDATE
Prerequisites
This skill drives three external tools — make sure each is available before running:
- playwright-cli on
PATH— the in-browser extraction, component sweep, and screenshots run through it. Install once withnpm install -g @playwright/cli@latestthenplaywright-cli install --skills(needs Node.js 18+). Check:which playwright-cli. - A reachable Firecrawl instance — used for page
discovery (
firecrawl map) and optional copy scraping. The hosted API or a self-hosted / local instance both work; if Firecrawl is unreachable the skill falls back to playwright link discovery (thinner page coverage). Confirm your instance responds before a run. npx(Node.js) — pulls the official@google/design.mdlinter on demand for the quality gate. If it's unavailable the skill writes the files anyway and notes "lint skipped".
If your agent sandboxes network or filesystem access, allow the outbound calls this skill makes (headless browsing, Firecrawl,
npx) before running.
file:// URLs are blocked by playwright-cli — serve local HTML with
python3 -m http.server <port> and kill the server by PID afterwards (a pkill -f pattern can
match your own shell).
Let SKILL = this skill's directory. Session name: S=dsys. Compose→run→slice pattern
for every in-page script:
playwright-cli -s=$S run-code "$(cat script.js)" | bash "$SKILL/scripts/slice-result.sh" > out.json
Two scripts are templates with a __-placeholder substituted per page
(distill.js → COMPONENTS, eval-selftest.js → FIXTURES). Compose with
tpl.replace('<placeholder>', JSON), then node --check the result. The placeholder
literal must appear exactly once in each template, in code — never add it to a comment
(this bug has now happened twice).
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/output-bundle-spec.md 5.8 KB
- scripts/build-fixtures.js 6.3 KB runs code
- scripts/build-snippets.js 7.4 KB runs code
- scripts/cluster.js 5.3 KB runs code
- scripts/distill.js 14 KB runs code
- scripts/eval-selftest.js 9.1 KB runs code
- scripts/export-dtcg.js 2.8 KB runs code
- scripts/extract-components.js 16 KB runs code
- scripts/extract-sections.js 11 KB runs code
- scripts/extract-tokens.js 7.3 KB runs code
- scripts/slice-result.sh 636 B runs code
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.
- 9d ago First seen · 218 lines · 178 tokens per session scan A 6203aa023bdb
extract-design-system is a skill published in the GitHub repository nathanonn/agent-skills (19 stars, last pushed 21d ago), licensed MIT. It adds 178 tokens to every session and 2,928 once invoked, about $0.0009 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 skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.