Borrowing it
Nothing to install: this file belongs to hhhh124hhhh/godot-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.
curl -O https://raw.githubusercontent.com/hhhh124hhhh/godot-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/hhhh124hhhh/godot-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/hhhh124hhhh/godot-mcp/claude-md)<a href="https://agentmods.dev/instructions/hhhh124hhhh/godot-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hhhh124hhhh/godot-mcp/claude-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.
<a href="https://agentmods.dev/instructions/hhhh124hhhh/godot-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hhhh124hhhh/godot-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.07358 | $0.07358 |
| Opus 5 | $0.03679 | $0.03679 |
| Sonnet 5 | $0.01472 | $0.01472 |
| Haiku 4.5 | $0.00736 | $0.00736 |
Grade A, and why
godot-mcp CLAUDE.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 9d 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 — 954 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
本文件为 Claude Code (claude.ai/code) 在此代码库中工作时提供指导。
架构概览
这是一个 Godot 引擎 + Claude AI 集成项目,使用模型上下文协议 (MCP)。项目采用 客户端-服务器架构:
- Godot 插件 (客户端): 位于
addons/godot_mcp/- 作为 EditorPlugin 在 Godot 中运行 - MCP 服务器 (后端): 位于
server/- 使用 FastMCP 的 Node.js/TypeScript 服务器
通信流程
Claude ↔ MCP 服务器 (FastMCP) ↔ WebSocket ↔ Godot 插件
Godot 插件创建 WebSocket 服务器(默认端口 9080),接受来自 MCP 服务器的连接。所有命令都通过此 WebSocket 连接使用 JSON 消息格式传输。
构建和运行命令
MCP 服务器开发
- 安装依赖:
cd server && npm install - 服务器构建:
cd server && npm run build(将 TypeScript 编译到dist/) - 启动服务器:
cd server && npm run start - 开发模式:
cd server && npm run dev(使用 nodemon 自动重建) - 类型检查:
cd server && npx tsc --noEmit(仅类型检查,不输出文件)
Godot 项目
- 打开项目: 在 Godot Editor 中打开
project.godot - 插件位置:
addons/godot_mcp/ - 启用插件: 项目设置 → 插件 → 启用 "Godot MCP"
测试连接
- 启动 MCP 服务器:
cd server && npm run dev - 在 Godot Editor 中打开项目(插件自动启动)
- 检查 MCP 服务器日志,确认 WebSocket 连接到
ws://localhost:9080
核心组件
Godot 插件端 (addons/godot_mcp/)
mcp_server.gd: 主 EditorPlugin,创建 WebSocket 服务器command_handler.gd: 将 JSON 命令路由到相应的处理器commands/: 命令处理器(node_commands.gd, script_commands.gd, scene_commands.gd 等)ui/mcp_panel.gd: 编辑器 UI 面板,显示连接状态和日志
MCP 服务器端 (server/src/)
index.ts: FastMCP 服务器入口点,注册所有工具/资源utils/godot_connection.ts: WebSocket 连接管理,支持自动重连tools/: MCP 工具定义(node_tools.ts, script_tools.ts 等)resources/: MCP 资源提供器(scene_resources.ts, script_resources.ts 等)
开发模式
添加新命令
-
Godot 端: 在
addons/godot_mcp/commands/中创建新命令类- 继承基础命令模式
- 在
command_handler.gd中注册 - 遵循 snake_case 命名规范
-
MCP 服务器端: 在
server/src/tools/中创建工具- 使用 FastMCP 工具构建器模式
- 在
server/src/index.ts中注册 - 使用 Zod 进行参数验证
消息协议
命令格式 (MCP → Godot):
{
"type": "command_name",
"params": { /* 命令参数 */ },
"commandId": "unique_id"
}
响应格式 (Godot → MCP):
{
"status": "success|error",
"result": { /* 响应数据 */ },
"commandId": "matching_id"
}
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.
- 9d ago First seen · 954 lines · 7,358 tokens per session scan A 110fe10e8a94
godot-mcp CLAUDE.md is an instructions file published in the GitHub repository hhhh124hhhh/godot-mcp (42 stars, last pushed 9mo ago), licensed MIT. It adds 7,358 tokens to every session, about $0.0368 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
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.