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 agentmods add instructions/grab/talktofigmadesktop/agents-mdgit clone --depth 1 https://github.com/grab/TalkToFigmaDesktopWrote 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/grab/talktofigmadesktop/agents-md)<a href="https://agentmods.dev/instructions/grab/talktofigmadesktop/agents-md"><img src="https://agentmods.dev/badge/instructions/grab/talktofigmadesktop/agents-md.svg" alt="Measured on agentmods" 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 | $0.02879 | $0.02879 |
| Opus 5 | $0.01439 | $0.01439 |
| Sonnet 5 | $0.00576 | $0.00576 |
| Haiku 4.5 | $0.00288 | $0.00288 |
Grade C, and why
TalkToFigmaDesktop AGENTS.md scanned grade C 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Clear Vite cache: `rm -rf .vite` Copies of this mod
1 near-identical copy found in the catalogue:
- TalkToFigmaDesktop CLAUDE.md — 97% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Project Overview
TalkToFigma Desktop is an Electron-based desktop application that bridges Figma with AI tools (Cursor, Codex, VS Code) using the Model Context Protocol (MCP). It enables AI assistants to read and manipulate Figma designs through a structured protocol.
Current Version: 2.0.0 Bundle ID: com.grabtaxi.klever Architecture: Electron + React + TypeScript
Migration History
This project was migrated from Kotlin Compose Desktop to Electron in January 2026 (v2.0.0). The Electron version maintains feature parity while adding cross-platform support (macOS, Windows, Linux) and better developer experience with modern JavaScript tooling.
Development Commands
Start Development Server
npm start
# Launches Electron app with hot reload
# Main process: src/main.ts
# Renderer process: src/renderer.tsx
Build & Package
npm run package # Package for current platform
npm run make # Create distributable installers
Linting
npm run lint # Run ESLint on TypeScript files
Building Individual Components
The project uses Vite with multiple entry points configured in forge.config.ts:
- Main process:
src/main.ts→vite.main.config.ts - Preload script:
src/preload.ts→vite.preload.config.ts - Renderer: React app →
vite.renderer.config.ts - MCP stdio server:
src/main/server/mcp-stdio-server.ts→vite.stdio.config.ts
Architecture
High-Level Overview
MCP Clients (Cursor, Codex, etc.)
│ spawn independent process per client
▼
stdio MCP Servers (one per client)
│ WebSocket connection (ws://127.0.0.1:3055)
▼
WebSocket Server (Electron App - Port 3055)
│ Channel-based routing
▼
Figma Plugin
Core Architectural Concepts
1. Multi-Process Architecture
- Each MCP client (Cursor, Codex) spawns its own independent stdio server process
- stdio servers are NOT managed by the Electron app - they're spawned by the MCP clients themselves
- All stdio servers connect to the same WebSocket server (port 3055) in the Electron app
- This allows multiple AI tools to work with Figma simultaneously
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.
- 4d ago First seen · 303 lines · 2,879 tokens per session scan C 0c46bc95fa26
TalkToFigmaDesktop AGENTS.md is an instructions file published in the GitHub repository grab/TalkToFigmaDesktop (51 stars, last pushed 4mo ago), licensed MIT. It adds 2,879 tokens to every session, about $0.0144 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.