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 hamzaPixl/pixl-ai --skill design-extractiongit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote 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/hamzapixl/pixl-ai/design-extraction)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/design-extraction"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/design-extraction/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/hamzapixl/pixl-ai/design-extraction"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/design-extraction.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 | $0.00042 | $0.01919 |
| Opus 5.5 | $0.00017 | $0.00768 |
| Sonnet 5.5 | $0.00008 | $0.00384 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade A, and why
design-extraction 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Extracts design tokens and layout structure from three input types and outputs a design-spec.json:
- Figma URL (
figma.com/design/...orfigma.com/file/...) — reads the design via Figma API - Live website URL (any other URL) — captures and analyzes via
agent-browserCLI followingreferences/frontend/url-design-extraction.md - Screenshot / image file — visual analysis of a provided image
Output: Always a design-spec.json conforming to references/frontend/design-spec-schema.md.
Two modes after extraction:
- Implement mode — design source only → extract →
design-spec.json→ build new site via/websiteMode B (spec-fed) or Mode C (replicate) - Redesign mode — design source + existing project path → extract →
design-spec.json→ apply to existing site via/website-themethen/website-layout
Prerequisites
- For Figma URLs: Figma API access must be configured
- For live website URLs:
agent-browserCLI must be available (npm install -g agent-browser) - For Mode C replication:
npx firecrawlrecommended for content scraping (optional — falls back to DOM extraction) - For redesign mode: target project must already exist
URL Type Detection
Detect the input type and route accordingly:
- Figma URL (
figma.com/design/...orfigma.com/file/...) → Step 1 (Figma extraction) - Live website URL (any other URL) → Step 2 (URL extraction)
- Screenshot / image file (local path ending in
.png,.jpg,.webp) → Step 3 (Visual extraction)
Step 1: Extract from Figma
1.1 Parse the Figma URL
Extract the file key and node ID from the URL:
- File key: the segment after
/design/or/file/ - Node ID: from
node-id=query parameter (optional — if absent, use the root)
1.2 Read the Figma File
Use the Figma API tools to inspect the design:
- Get file metadata — file name, pages, top-level frames
- Get the target node (or root frame) — inspect its children to understand the page structure
- Extract styles and variables:
- Colors (fills, strokes) →
theme.colors - Typography (font families, sizes, weights, line heights) →
typography - Spacing (padding, gaps, auto-layout settings) →
layout - Border radius →
theme.border_radius - Effects (shadows, blurs) →
theme.shadows
- Colors (fills, strokes) →
- Extract layout structure:
- Top-level sections in order →
pages[].sections - Component patterns — cards, grids, splits
- Navigation and footer patterns →
components.navbar,variants.footer - Hero variant →
variants.hero
- Top-level sections in order →
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 · 181 lines · 42 tokens per session scan A 1b5232b73bc0
design-extraction is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 1,919 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.