Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/danielvm-git/bigpowersnpx agentmods add skills/danielvm-git/bigpowers/extract-designWrote 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/danielvm-git/bigpowers/extract-design)<a href="https://agentmods.dev/skills/danielvm-git/bigpowers/extract-design"><img src="https://agentmods.dev/badge/skills/danielvm-git/bigpowers/extract-design/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/danielvm-git/bigpowers/extract-design"><img src="https://agentmods.dev/badge/skills/danielvm-git/bigpowers/extract-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Prompt Injection · line 11 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 3 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium MCP Rug Pull · line 13 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]
- medium MCP Rug Pull · line 40 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 | $0.00069 | $0.01640 |
| Opus 5.5 | $0.00028 | $0.00656 |
| Sonnet 5.5 | $0.00014 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
extract-design 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract DESIGN.md from HTML
HARD GATE — Do NOT write DESIGN.md without Puppeteer dual-pass extraction. Tokens from static HTML (Cheerio, regex, string scanning) are invalid — they miss cascade, custom properties, and Tailwind resolution.
HARD GATE — Do NOT claim certainty where evidence is thin. Low-confidence color roles, component classifications, and prose assertions MUST be flagged with
<!-- AGENT NOTE: uncertain — validate during grill-me. Evidence: [what was observed] -->.HARD GATE — Do NOT ship DESIGN.md without running
npx @google/design.md lint. Unvalidated output is unverified output. If lint is unavailable (offline), flag prominently in terminal and in DESIGN.md prose.
Quick Start
# First run — extract from HTML prototype
node extract-design/scripts/extract.js --source ./prototype.html
# From a published URL
node extract-design/scripts/extract.js --source https://my-prototype.example.com
# With a custom name
node extract-design/scripts/extract.js --source ./proto.html --name "My Design System"
# Update — re-extract from new HTML, diff against existing
node extract-design/scripts/extract.js --source ./proto-v2.html
# Lint-only — validate existing DESIGN.md without re-extraction
node extract-design/scripts/extract.js --lint-only
Flow
- Launch Puppeteer — dual-pass (light + dark) with retry + timeout. CI flags:
--headless=new --no-sandbox --disable-gpu --disable-dbus --use-gl=angle --use-angle=swiftshader. - Collect styles —
page.evaluate()collects computed styles from every element. Returns raw JSON to Node.js. Browser = sensor; Node = brain. - Classify tokens — modular pipeline: colors (Material 3 roles), typography (scale detection), spacing (tolerance GCD), rounded (clustering), components (visual signature + pseudo-state variants).
- Generate prose — AI heuristics produce all 8 DESIGN.md sections. Overview and Do's/Don'ts flagged with agent notes.
- Write + validate — serialize to
specs/tech-architecture/DESIGN_LATEST.md, runnpx @google/design.md lint, report to terminal. - Handoff — writes
handoff.next_skill: grill-metospecs/state.yamlwith uncertain decisions context.
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 · 133 lines · 69 tokens per session scan A 469d6ad55a5e
extract-design is a skill published in the GitHub repository danielvm-git/bigpowers (275 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,640 once invoked, about $0.0003 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 skills, from other repositories
ui-designer/interaction-specification
A guide to specifying how an interface responds to user actions, including loading screens, empty results, feedback, animation, keyboard use, and screen readers.
ui-designer/component-specification
A specification for reusable interface components such as buttons, inputs, and cards. It defines their variations, sizes, and states, including hover, focus, disabled, loading, and error states.
pm/user-research
A user research guide for describing target users and mapping the steps, thoughts, feelings, and problems they experience while completing a task.
ui-designer/design-variants
A UI design method that creates two or three meaningfully different interface options, then compares their advantages and disadvantages.
code-quality-principles
Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.
design-md-convention
Convention DESIGN.md pour design systems AI-friendly. Use when setting up a new project UI, documenting design tokens, or generating UI consistent with a design system.