Borrowing it
Nothing to install: this file belongs to whoistus/figma-mcp-poor. 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/whoistus/figma-mcp-poor/master/CLAUDE.mdgit clone --depth 1 https://github.com/whoistus/figma-mcp-poorWrote 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/whoistus/figma-mcp-poor/claude-md)<a href="https://agentmods.dev/instructions/whoistus/figma-mcp-poor/claude-md"><img src="https://agentmods.dev/badge/instructions/whoistus/figma-mcp-poor/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/whoistus/figma-mcp-poor/claude-md"><img src="https://agentmods.dev/badge/instructions/whoistus/figma-mcp-poor/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 | $0.01088 | $0.01088 |
| Opus 5 | $0.00544 | $0.00544 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
figma-mcp-poor CLAUDE.md 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 — 68 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.
What This Is
A Figma MCP (Model Context Protocol) bridge that lets AI assistants read design context from Figma without hitting REST API rate limits or blowing up context windows. It uses the Figma Plugin API (local, no network) instead of the REST API.
AI IDE <--MCP stdio--> MCP Server (Node.js :3055) <--WebSocket--> Figma Plugin (figma.* API)
Build Commands
# Install dependencies (npm workspaces)
npm install
# Build everything
npm run build
# Build individually
npm run build:server # tsc -> mcp-server/dist/
npm run build:plugin # esbuild via build.mjs -> figma-plugin/dist/
# Dev mode (MCP server with tsx)
npm run dev:server
# Watch mode (Figma plugin)
npm run watch -w figma-plugin
The MCP server is an ES module ("type": "module"). The Figma plugin is bundled with esbuild.
Architecture
Two workspaces in an npm workspaces monorepo:
mcp-server/ — Node.js MCP server
src/index.ts— Entry point: wires McpServer + StdioServerTransport + WebSocketBridgesrc/server.ts— Registers 9 MCP tools with zod schemas, handles formatting/truncation of responsessrc/websocket.ts— WebSocketBridge class: single-connection WS server on port 3055, request/response matched by UUIDsrc/formatter.ts— Transforms raw Figma data into CSS-like developer format (colors→hex/rgba, layout→flexbox, text→CSS font shorthand)src/truncator.ts— Token estimation (JSON length / 4) and smart truncation with configurable max (default 8000 tokens)src/types.ts— Re-exports from shared types
figma-plugin/ — Figma plugin (runs inside Figma)
src/main.ts— Plugin main thread: shows UI, routes WS messages to handlerssrc/ui.html— WebSocket client that relays messages between WS and plugin main threadsrc/serializer.ts— Depth-controlled node serialization (depth 0 = stub, depth N = full properties + children). Applies automatic depth bonus for COMPONENT_SET (+2) and INSTANCE (+1) so variant hierarchies (e.g. dropdowns) aren't flattened at default depth.src/base64.ts— Pure base64 encoder for the plugin main thread (nobtoaavailable). Screenshots are encoded here, not in the UI thread.src/handlers/— One handler per tool type (document, selection, node, styles, variables, components, context, screenshot, dev-summary)
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 · 68 lines · 1,088 tokens per session scan A 6edabe772c5c
figma-mcp-poor CLAUDE.md is an instructions file published in the GitHub repository whoistus/figma-mcp-poor (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,088 tokens to every session, about $0.0054 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 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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.