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/firasmj/figma-mcp-write-bridge/copilot-instructionsgit clone --depth 1 https://github.com/firasmj/Figma-MCP-Write-BridgeWrote 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/firasmj/figma-mcp-write-bridge/copilot-instructions)<a href="https://agentmods.dev/instructions/firasmj/figma-mcp-write-bridge/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/firasmj/figma-mcp-write-bridge/copilot-instructions.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 5.1 | $0.01063 | $0.01063 |
| Opus 5 | $0.00531 | $0.00531 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
Figma-MCP-Write-Bridge copilot-instructions.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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Coding Agent Instructions for figma-mcp-write-bridge
Purpose: Provide a local Model Context Protocol (MCP) server that exposes write/manipulation tools for a running Figma document via a lightweight plugin bridge (WebSocket + stdio). Use these instructions to quickly understand architecture, patterns, and safe extension points.
Big Picture Flow
- Host process runs
npm startwhich executestsx server.ts(seepackage.json). server.tsboots:- A WebSocket server on
ws://127.0.0.1:3055waiting for the Figma plugin UI (plugin/ui.html). - An MCP server (
McpServer) over stdio so AI clients (e.g. VS Code extension) can invoke tools.
- A WebSocket server on
- The Figma plugin (
plugin.js) loads a hidden UI (ui.html) solely to accessWebSocketAPIs. - Tool invocation path: MCP client ->
server.tstool handler ->sendToPlugin()-> WS to UI ->parent.postMessageinto plugin ->figma.ui.onmessage->handleAction()-> action implementation -> result bubbled back reversing the chain.
Core Files & Responsibilities
server.ts: Defines WebSocket bridge, pending request correlation (id + timeout), and registers MCP tools forwarding to plugin actions.plugin/plugin.js: Mapsactionstrings to concrete Figma API operations (frame, text, rectangle, grouping, positioning, page clearing). Handles error wrapping & result formatting.plugin/ui.html: Minimal resilient auto-reconnecting WS client; shuttles messages between bridge and Figma plugin viapostMessage.plugin/manifest.json: Declares plugin metadata & enables network access (required for WS localhost communication).tsconfig.json: Non‑strict TypeScript (strict:false) with modern ES2022 + bundler module resolution.
Message & Tool Pattern
Request envelope from server to plugin: { id, action, args }.
Reply envelope from plugin back: { replyTo, result, error? }.
server.ts maintains a Map of pending promises keyed by id; 15s timeout triggers rejection.
Each MCP tool uses registerTool(name, zodSchema, description, action) pattern; results are JSON‑stringified into MCP textual & structured content.
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.
- 5d ago First seen · 67 lines · 1,063 tokens per session scan A a1121ec44576
Figma-MCP-Write-Bridge copilot-instructions.md is an instructions file published in the GitHub repository firasmj/Figma-MCP-Write-Bridge (6 stars, last pushed 7mo ago), licensed MIT. It adds 1,063 tokens to every session, about $0.0053 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
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.
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.
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).