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 wangbin3162/agents-skills --skill design-extractgit clone --depth 1 https://github.com/wangbin3162/agents-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/wangbin3162/agents-skills/design-extract)<a href="https://agentmods.dev/skills/wangbin3162/agents-skills/design-extract"><img src="https://agentmods.dev/badge/skills/wangbin3162/agents-skills/design-extract/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/wangbin3162/agents-skills/design-extract"><img src="https://agentmods.dev/badge/skills/wangbin3162/agents-skills/design-extract.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 | $0.00162 | $0.04592 |
| Opus 5 | $0.00081 | $0.02296 |
| Sonnet 5 | $0.00032 | $0.00918 |
| Haiku 4.5 | $0.00016 | $0.00459 |
Grade A, and why
design-extract 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Extract
You are about to extract a website's design language into a single structured DESIGN.md — a design-system reference document that another AI (or human) can use to reproduce the site's visual identity. The output is not a clone of the page; it is a token-level specification of the design system: colors, typography, layout, elevation, shapes, components, responsive behavior, and the editorial voice that makes the brand recognizable.
The reference standard for the output is the Claude.com design document: a warm, editorial, token-referenced spec where every value is a {token.name} reference and every component is documented to the pixel.
Interactive Input
If $ARGUMENTS is empty or incomplete, ask the user interactively. Do NOT proceed without the required information. Ask questions one at a time — don't overwhelm with a long form.
Step 1: Input Source
If no URL and no screenshots were provided, ask:
Q: 用什么作为设计提取的来源？
- Option A: 输入 URL（推荐）— "提供目标网址，例如 https://example.com，我会打开并采集"
- Option B: 仅截图 — "我没有 URL，只有本地截图（需多模态分析）"
- Option C: URL + 截图 — "我有 URL，同时补充几张截图（交互态/移动端/特定页面）"
If the user chooses B (screenshots only), note that extraction relies entirely on visual inference — no computed CSS. Skip to Step 2 (screenshots).
Validate URL format. If invalid, ask again.
Step 2: Screenshots (only if B or C)
Q: 截图文件路径？
- 请提供 1-N 张截图路径（建议 ≥2 张，覆盖首屏 + 内容区 + footer）
- Option A: 输入路径（多个用空格分隔）
- Option B: 我还没截图 — "帮我从 URL 自动截"（仅 C 模式可用，转 URL 自动截图流程）
Verify each path exists. If not, ask again.
Step 3: Output Directory Name
If --dir was not provided, suggest a default derived from the hostname (URL mode) or the first screenshot's name (screenshot mode) and ask:
Q: 输出目录叫什么名字？
- 显示建议名称（如
example-com），让用户确认或自定义- 用户可直接回车确认默认值，或输入新名称
If the directory already exists, ask whether to overwrite or pick a new name.
Step 4: Output Language
Q: DESIGN.md 用什么语言？
- Option A: 跟随你的提问语言（推荐）— 中文提问→中文输出，英文提问→英文输出
- Option B: 英文 — 对标 Claude.com 标准，便于喂给 AI 编程工具
- Option C: 中文 — 章节说明用中文，token 名键仍用英文
What ships with it
2 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.
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 · 289 lines · 162 tokens per session scan A fb36fdf3b9b9
design-extract is a skill published in the GitHub repository wangbin3162/agents-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 162 tokens to every session and 4,592 once invoked, about $0.0008 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 2026-08-31.
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.