aiconnect-figma-mcp: Instructions file for Claude Code

CLAUDE.md

aiconnect-figma-mcp CLAUDE.md is an instructions file for Claude Code from guptaprakhariitr/aiconnect-figma-mcp. It costs 688 tokens per session, scanned A, original, MIT.

Development instructions for an MCP server and Figma plugin that let an AI agent read and edit a live Figma design file. The parts communicate through a local server and a WebSocket relay.

In plain words
What is it for?
Use it when installing, building, testing, debugging, or extending the project’s Figma editing tools, such as shapes, text, layouts, images, exports, and batch operations.
Why use it?
It gives contributors the project structure, setup commands, testing steps, and connection details needed to work on the integration.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is guptaprakhariitr/aiconnect-figma-mcp's own configuration. It tells Claude Code how to work on aiconnect-figma-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aiconnect-figma-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to guptaprakhariitr/aiconnect-figma-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.

Copy the file
curl -O https://raw.githubusercontent.com/guptaprakhariitr/aiconnect-figma-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/guptaprakhariitr/aiconnect-figma-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for aiconnect-figma-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/guptaprakhariitr/aiconnect-figma-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/guptaprakhariitr/aiconnect-figma-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/guptaprakhariitr/aiconnect-figma-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/guptaprakhariitr/aiconnect-figma-mcp/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.

agentmods 80×15 button for aiconnect-figma-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/guptaprakhariitr/aiconnect-figma-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/guptaprakhariitr/aiconnect-figma-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 688 This file is loaded in full into every session.
When invoked 688 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00688 $0.00688
Opus 5 $0.00344 $0.00344
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 11d ago against content hash bf7e6ecc80bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aiconnect-figma-mcp 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 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.

CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and other agents) working in this repository.

Project Overview

AIConnect — an MCP (Model Context Protocol) server + Figma plugin that let an AI agent read and edit a live Figma file. Three components communicate in a pipeline:

MCP client ←(stdio)→ MCP Server ←(WebSocket)→ WebSocket Relay ←(WebSocket)→ Figma Plugin

Build & Development Commands

bun install              # Install dependencies
bun run build            # Build MCP server (tsup → dist/)
bun run dev              # Build in watch mode
bun socket               # Start WebSocket relay server (port 3055)
bun run start            # Run built MCP server
bun run test             # Connection-free coverage test (tests/coverage.mjs)
bun run test:smoke <chan> # Live smoke test against the plugin (tests/smoke.mjs)
bun setup                # Install + write .mcp.json

Architecture

MCP Server (src/aiconnect_mcp/server.ts)

Implements the MCP protocol via @modelcontextprotocol/sdk. Exposes the tools (create shapes, text, layouts, fills/gradients/effects, images, export, batch_ops, etc.). Each request gets a UUID, tracked in a pendingRequests Map with timeout/promise callbacks, and resolves when the plugin responds.

WebSocket Relay (src/socket.ts)

Lightweight Bun WebSocket server on port 3055 (configurable via PORT). Routes messages between server and plugin using channel-based isolation; join enters a channel and messages broadcast only within it.

Figma Plugin (src/figma_plugin/)

Runs inside Figma. code.js is the main thread: a handleCommand dispatcher over the Plugin API (including batch_ops, which runs many commands in one round-trip with @ref placeholders). ui.html manages the WebSocket connection. manifest.json declares dynamic-page access and localhost-only network. The plugin is not bundledcode.js is the runtime artifact, so re-run the plugin in Figma after editing it.

Key Patterns

  • Colors: RGBA 0-1 floats. set_fill_color accepts both top-level {r,g,b,a} and {color:{…}}.
  • batch_ops: prefer it for multi-node builds; one round-trip instead of dozens of calls.
  • Logging: stderr only — stdout is reserved for MCP protocol messages.
  • Timeouts: 30s default per command (180s for batch_ops).
  • Reconnection: the plugin UI auto-reconnects to the relay after a short delay.
  • Zod validation: all tool params validated with Zod.
  • No telemetry: the plugin makes no external network calls.

Read the full file on GitHub · 63 lines

Changes

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.

  1. 11d ago First seen · 63 lines · 688 tokens per session scan A bf7e6ecc80bf

Subscribe to this mod's changes

aiconnect-figma-mcp CLAUDE.md is an instructions file published in the GitHub repository guptaprakhariitr/aiconnect-figma-mcp (15 stars, last pushed 2mo ago), licensed MIT. It adds 688 tokens to every session, about $0.0034 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 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens