tldraw-mcp: Instructions file for Codex

AGENTS.md

tldraw-mcp AGENTS.md is an instructions file for Codex, OpenCode from dpunj/tldraw-mcp. It costs 336 tokens per session, scanned A, original, MIT.

A project guide for an AI coding agent working with a tldraw drawing canvas, an interactive tool for making diagrams. It documents commands, the code structure, and the messages exchanged between the server and canvas.

In plain words
What is it for?
Use it when changing the MCP server, the tldraw widget, or their WebSocket communication. It also explains commands for creating, updating, deleting, connecting, and inspecting shapes.
Why use it?
It gives the agent and developers a shared reference for running, building, checking, and understanding the project.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is dpunj/tldraw-mcp's own configuration. It tells Codex and OpenCode how to work on tldraw-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 tldraw-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dpunj/tldraw-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/dpunj/tldraw-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dpunj/tldraw-mcp

Made for: Codex, OpenCode.

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 tldraw-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dpunj/tldraw-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/dpunj/tldraw-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dpunj/tldraw-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dpunj/tldraw-mcp/agents-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 tldraw-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dpunj/tldraw-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dpunj/tldraw-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 336 This file is loaded in full into every session.
When invoked 336 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 $0.00336 $0.00336
Opus 5.5 $0.00134 $0.00134
Sonnet 5.5 $0.00067 $0.00067
Haiku 4.5 $0.00034 $0.00034

Measured 2mo ago against content hash e22781b7eb8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tldraw-mcp AGENTS.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 2mo 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.

AGENTS.md · 48 lines

What it actually says

Agent Instructions

Commands

Command Description
bun run dev Run MCP server (stdio)
bun run build Build MCP server
bun run check TypeScript check

Widget

cd widget
bun run dev    # Starts vite (port 3000) + WS server (port 4000)

Architecture

src/
├── index.ts     # MCP server entry point (tools)
├── bridge.ts    # WebSocket client to widget
└── schema.ts    # Zod schemas for tldraw types

widget/
├── src/App.tsx        # tldraw canvas + WS handler
└── src/ws-server.ts   # WebSocket relay server

Protocol

MCP server ↔ Widget communication via WebSocket JSON messages:

// Commands (MCP → Widget)
{ type: "create", shape: {...}, requestId: "1" }
{ type: "update", id: "...", props: {...}, requestId: "2" }
{ type: "delete", ids: [...], requestId: "3" }
{ type: "connect", from: "...", to: "...", requestId: "4" }
{ type: "snapshot", requestId: "5" }
{ type: "clear", requestId: "6" }

// Responses (Widget → MCP)
{ id: "shape:xxx", requestId: "1" }
{ shapes: [...], bounds: {...}, requestId: "5" }
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. 2mo ago First seen · 48 lines · 336 tokens per session scan A e22781b7eb8c

Subscribe to this mod's changes

tldraw-mcp AGENTS.md is an instructions file published in the GitHub repository dpunj/tldraw-mcp (2 stars, last pushed 9mo ago), licensed MIT. It adds 336 tokens to every session, about $0.0013 per session on Opus 5.5. 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.

Related

tldraw-mcp AGENTS.md compared with instructions from other repositories

tldraw-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tldraw-mcp AGENTS.mddpunj/tldraw-mcpInstructions file29mo agoMITA336Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode