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/james2doyle/godot-docs-mcp/agents-mdgit clone --depth 1 https://github.com/james2doyle/godot-docs-mcpWrote 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/james2doyle/godot-docs-mcp/agents-md)<a href="https://agentmods.dev/instructions/james2doyle/godot-docs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/james2doyle/godot-docs-mcp/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 | $0.01813 | $0.01813 |
| Opus 5 | $0.00907 | $0.00907 |
| Sonnet 5 | $0.00363 | $0.00363 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
godot-docs-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 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- godot-docs-mcp AGENTS.md — 100% identical, 0 lines differ
- godot-docs-mcp AGENTS.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for godot-docs-mcp
This document provides coding guidelines and operational instructions for agents working on this codebase.
Project Overview
- Type: Cloudflare Workers MCP server (Model Context Protocol)
- Purpose: Provides AI agents with tools to search and retrieve Godot documentation
- Runtime: Cloudflare Workers (workerd) with Durable Objects
- Language: TypeScript (strict mode)
- Testing: Vitest with
@cloudflare/vitest-pool-workers
Architecture
src/
├── index.ts # Main entry point, MyMCP agent class, fetch handler
├── utils.ts # Search and docs retrieval logic
└── indexes/ # Search index JSON files (stable/, latest/, 4.6/, 4.5/, 4.4/, 4.3/)
tests/
└── *.test.ts # Vitest tests with Cloudflare Workers pool
MCP Server Configuration
The project uses Opencode MCP servers defined in opencode.json:
{
"mcp": {
"cloudflare-docs": {
"enabled": true,
"type": "remote",
"url": "https://docs.mcp.cloudflare.com/mcp"
},
"cloudflare-worker-bindings": {
"enabled": false,
"type": "remote",
"url": "https://bindings.mcp.cloudflare.com/mcp"
}
}
}
- cloudflare-docs: Enabled - provides tools to search Cloudflare documentation
- cloudflare-worker-bindings: Disabled by default - provides tools to query Worker bindings
Build, Lint, and Test Commands
# Install dependencies
npm install
# Development server (wrangler dev)
npm run dev
npm run dev:inspect # With Node inspector for debugging
# Deploy to Cloudflare Workers
npm run deploy
# Type checking
npm run type-check # tsc --noEmit
# Generate Cloudflare types
npm run cf-typegen # wrangler types
# Formatting (Biome)
npm run format # biome format --write
npm run lint:fix # biome lint --fix
# Testing
npm test # Run all tests (vitest)
npm test -- --run # Run tests once (not watch mode)
npm test -- --run -t "test name" # Run single test by name
npm test -- --run tests/search_docs.test.ts # Run single test file
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 · 251 lines · 1,813 tokens per session scan A 8807a3f7a3c3
godot-docs-mcp AGENTS.md is an instructions file published in the GitHub repository james2doyle/godot-docs-mcp (26 stars, last pushed 6mo ago), licensed MIT. It adds 1,813 tokens to every session, about $0.0091 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.
Other instructions, from other repositories
comedot AGENTS.md
AGENTS.md instructions for InvadingOctopus/comedot, covering agents.md, guidelines for the comedot project and repository, project overview, folder structure & module organization and subsystems.
everything-game-dev-code copilot-instructions.md
Copilot instructions for MRCalderon3D/everything-game-dev-code, covering github copilot repository instructions, repository intent, how to navigate the repository, working rules and repository maintenance.
codex-game-studio AGENTS.md
AGENTS.md instructions for merlinhu1/codex-game-studio, covering codex game studio template, project goal, engine, commands and context bootstrap.
yume CLAUDE.md
Instructions for kamwoh/yume, covering yume (夢) — json-driven game framework on godot, quick start, framework structure, how the engine works and tick rate is the engine's heartbeat (2026-05-16).
godot-docs-mcp CLAUDE.md
Claude Code instructions for mcintalmo/godot-docs-mcp, covering godot-docs-mcp — working notes, non-negotiables, layer map, conventions and adding a tool.
steam-mcp AGENTS.md
AGENTS.md instructions for sandraschi/steam-mcp, covering steam-mcp agent context, repo, ports, auth and ai / chat (webapp).