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/mihai-codes/tldraw-mcp-server/agents-mdgit clone --depth 1 https://github.com/Mihai-Codes/tldraw-mcp-serverWrote 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/mihai-codes/tldraw-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/mihai-codes/tldraw-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/mihai-codes/tldraw-mcp-server/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 | $0.03719 | $0.03719 |
| Opus 5 | $0.01860 | $0.01860 |
| Sonnet 5 | $0.00744 | $0.00744 |
| Haiku 4.5 | $0.00372 | $0.00372 |
Grade A, and why
tldraw-mcp-server 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 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — tldraw MCP Server
Guidance for AI agents (AdaL, Claude Code, Codex CLI, etc.) working in this repository.
What This Project Is
An MCP (Model Context Protocol) server that gives AI agents programmatic control over a live tldraw infinite canvas. Two processes run together:
- Canvas Server (
src/canvas-server.ts) — Express HTTP + WebSocket server on port 3000. Owns the in-memory element store and broadcasts mutations to connected browsers. - MCP Server (
src/index.ts) — Stdio MCP server. Validates tool calls with Zod and proxies them to the canvas server via HTTP REST. - Frontend (
frontend/src/App.tsx) — React + tldraw app. Connects to canvas server via WebSocket, applies all mutations to the tldraw editor in real time.
Repository Layout
tldraw-mcp-server/
├── src/
│ ├── index.ts # MCP server entry point — 27 tools, Zod schemas
│ ├── canvas-server.ts # Express + WebSocket canvas server — REST CRUD + snapshot
│ ├── types.ts # Shared types: CanvasElement, WSMessage, ApiResponse, generateId
│ ├── layout/
│ │ ├── engine.ts # Main layout engine entry point
│ │ ├── dagre.ts # Hierarchical layout using @dagrejs/dagre
│ │ ├── force.ts # Force-directed layout using d3-force
│ │ ├── grid.ts # Grid layout algorithm
│ │ ├── graph.ts # Graph building helpers for layout algorithms
│ │ └── types.ts # Layout types and interfaces
│ └── export/
│ ├── svg.ts # SVG generation from elements
│ └── pdf.ts # PDF export using Playwright or pdf-lib fallback
├── frontend/
│ ├── src/
│ │ ├── App.tsx # React component — WS sync, tldraw shape mapping
│ │ └── main.tsx # React entry point
│ ├── index.html
│ ├── vite.config.ts # Dev proxy /api → :3000, build → dist/public
│ ├── tsconfig.json
│ └── package.json
├── dist/ # Compiled backend (tsc output) — gitignored
│ └── public/ # Compiled frontend (vite build output) — gitignored
├── .mcp.json # Project-level MCP config for AdaL CLI / Claude Code
├── package.json # Root — backend deps + build scripts
└── tsconfig.json # Backend TS config
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 · 309 lines · 3,719 tokens per session scan A 07e975e585d4
tldraw-mcp-server AGENTS.md is an instructions file published in the GitHub repository Mihai-Codes/tldraw-mcp-server (1 stars, last pushed 3mo ago), licensed MIT. It adds 3,719 tokens to every session, about $0.0186 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
agent-skills GEMINI.md
Gemini CLI instructions for mongodb/agent-skills, covering mongodb gemini extension and configuration.
agent-skills AGENTS.md
AGENTS.md instructions for tech-leads-club/agent-skills, covering agents.md, workflow orchestration, 1. plan mode default, 2. subagent strategy and 3. verification before done.
robrain AGENTS.md
Instructions for adelinamart/robrain, covering robrain — context management (oss self-hosted), session start (mandatory, first thing in every new chat), after every response (mandatory) and session end (last thing).
fast-mcp-telegram CLAUDE.md
Claude Code instructions for leshchenko1979/fast-mcp-telegram, covering fast-mcp-telegram, session corrections and 2026-05-27.
compare-mcp CLAUDE.md
Claude Code instructions for Cristophereasygoing927/compare-mcp, covering compare-mcp, architecture, running and key decisions.
xlsx-for-ai CLAUDE.md
Instructions for senoff/xlsx-for-ai, covering xlsx-for-ai — agent loading guide, always-load, load on relevance, review gate (mandatory unless explicitly skipped) and repo posture.