Borrowing it
Nothing to install: this file belongs to e-brokenc0de/claude-design-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/e-brokenc0de/claude-design-mcp/main/.claude/skills/claude-design/SKILL.mdgit clone --depth 1 https://github.com/e-brokenc0de/claude-design-mcpWrote 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/e-brokenc0de/claude-design-mcp/claude-design)<a href="https://agentmods.dev/skills/e-brokenc0de/claude-design-mcp/claude-design"><img src="https://agentmods.dev/badge/skills/e-brokenc0de/claude-design-mcp/claude-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/e-brokenc0de/claude-design-mcp/claude-design"><img src="https://agentmods.dev/badge/skills/e-brokenc0de/claude-design-mcp/claude-design.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 | $0.00141 | $0.02367 |
| Opus 5 | $0.00071 | $0.01184 |
| Sonnet 5 | $0.00028 | $0.00473 |
| Haiku 4.5 | $0.00014 | $0.00237 |
Grade A, and why
claude-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 11d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Design (via MCP)
The claude-design MCP server automates claude.ai/design — which has no public API —
by attaching to a real Chrome over CDP and calling its internal RPC. It exposes clean
tools (prefix mcp__claude-design__*) so you can build and pull design systems straight
into a repo instead of clicking through the web app.
Before anything: the session must be authenticated
Every tool drives a logged-in Chrome. If a tool returns NOT_AUTHED (or anything
mentions login), the CDP Chrome isn't signed into claude.ai. Tell the user to run, once:
cd <claude-design-mcp repo> && pnpm run chrome:cdp
…then log into claude.ai in the window that opens. The session persists, so this is a one-time step per machine (or after logout). Don't try to work around auth failures — surface this instruction.
Generation is asynchronous (a full design system takes ~5 min; small projects are
faster). Never block waiting — start it, then either poll get_status, or watch in the
background and get auto-woken when it finishes (see below).
Waiting for generation (background + auto-wake)
After generate, iterate, or send_message, don't sit and re-poll every few seconds —
that burns turns. Two options:
-
Quick manual check: call
get_status({ projectId })→generating|ready. Good for a one-off "is it done yet?". -
Background watch with automatic wake-up (preferred for long runs): run the watcher as a background command. The harness sends a completion notification the moment it exits, so you're woken exactly when generation settles — no polling in between:
cd <claude-design-mcp repo> && \ pnpm run watch:status -- --project <projectId>Run it with the agent's background execution (e.g. Bash
run_in_background: true). It connects over CDP, watches the project's files until a change is seen and then nothing changes for ~40s, prints{"status":"ready", ...}and exits 0 (exits 2 with{"status":"timeout"}if it never settles). Kick it off right after the generate/send_message call. Flags:--timeout,--quiet,--interval(ms).
What ships with it
3 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.
- 11d ago First seen · 206 lines · 141 tokens per session scan A ea89b22898d6
claude-design is a skill published in the GitHub repository e-brokenc0de/claude-design-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 141 tokens to every session and 2,367 once invoked, about $0.0007 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
anydesign
Analyze images, websites, and Figma files to extract their design and generate a design.md with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest…
spectr
Turn a screen recording (.mp4 / .mov / .m4v) into a production-ready DESIGN.md — 10 sections, exact hex codes, exact font weights, exact spacing, every screen folded in. Produces the Spectr gallery spec format. Use when the user has dropped a screen recording in chat and wants to clone or document the app.
extract-design
Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…