Borrowing it
Nothing to install: this file belongs to tranhoangtu-it/mcp-figma. 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/tranhoangtu-it/mcp-figma/main/CLAUDE.mdgit clone --depth 1 https://github.com/tranhoangtu-it/mcp-figmaWrote 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/instructions/tranhoangtu-it/mcp-figma/claude-md)<a href="https://agentmods.dev/instructions/tranhoangtu-it/mcp-figma/claude-md"><img src="https://agentmods.dev/badge/instructions/tranhoangtu-it/mcp-figma/claude-md/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/instructions/tranhoangtu-it/mcp-figma/claude-md"><img src="https://agentmods.dev/badge/instructions/tranhoangtu-it/mcp-figma/claude-md.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 | $0.00585 | $0.00585 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
mcp-figma CLAUDE.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Never pass design data to `child_process.exec()` (CVE-2025-53967 pattern) How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MCP server bridging AI clients to Figma Desktop via Plugin API + WebSocket. Three components:
- MCP Server (
src/mcp-server/) — Exposes 25 design tools via stdio, connects to WS relay - WebSocket Server (
src/websocket/) — Relay with token auth, channel routing, heartbeat - Figma Plugin (
src/figma-plugin/) — Runs inside Figma Desktop, executes Plugin API calls
Build & Run
npm run build # Build with tsup
npm run ws # Start WebSocket relay server (shows session token)
npm run start # Start MCP server (needs MCP_FIGMA_TOKEN env)
npm run dev # Watch mode
npm run test # Run all tests
npm run test:ws # Run WebSocket tests only
Architecture
AI Client → MCP (stdio) → MCP Server → WebSocket (127.0.0.1:3055, token auth) → Figma Plugin → Figma Canvas
- MCP Server uses stdio transport (stdout = protocol, stderr = logging)
- WebSocket relay binds 127.0.0.1 only with per-session random token
- Figma Plugin is plain JS (code.js) running in WASM sandbox + HTML UI (ui.html) for WebSocket
Key Conventions
- Figma colors use 0-1 RGBA (not 0-255) — all color params are
z.number().min(0).max(1) - Plugin code.js is plain JavaScript — Figma sandbox doesn't support TypeScript, modules, or most browser APIs
- All logging to stderr — stdout is reserved for MCP stdio transport
- Message IDs use
crypto.randomUUID()— for request/response correlation over async WebSocket - Tools are organized in modular files under
src/mcp-server/tools/by function category - Shared schemas and constants live in
src/shared/
Testing
Tests use Node.js built-in test runner with tsx loader:
node --import tsx --test src/websocket/ws-server.test.ts
Figma Plugin cannot be unit tested outside Figma — integration testing requires Figma Desktop with plugin imported from manifest.
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 · 58 lines · 585 tokens per session scan A 444b010360f0
mcp-figma CLAUDE.md is an instructions file published in the GitHub repository tranhoangtu-it/mcp-figma (0 stars, last pushed 5mo ago), licensed MIT. It adds 585 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.