Godot-MCP-Native: Instructions file for Codex

AGENTS.md

Godot-MCP-Native AGENTS.md is an instructions file for Codex, OpenCode from yurineko73/Godot-MCP-Native. It costs 3,847 tokens per session, scanned A, original, MIT.

Project instructions for a Godot 4.6 editor plugin that provides a built-in MCP server, allowing AI assistants to read and modify Godot projects. MCP is a standard way for software tools to expose actions and data to AI assistants.

In plain words
What is it for?
Use them to operate the plugin through the gdmcp commands, locate its server entry point, and run the project's headless GUT tests.
Why use it?
They explain how to use the companion command-line tool, which Godot and PowerShell versions to check, and where Chinese text is allowed in code and documentation.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; names the TodoWrite tool; mentions Claude Code.

This is yurineko73/Godot-MCP-Native's own configuration. It tells Codex and OpenCode how to work on Godot-MCP-Native 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 Godot-MCP-Native configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yurineko73/Godot-MCP-Native. 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/yurineko73/Godot-MCP-Native/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/yurineko73/Godot-MCP-Native

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 Godot-MCP-Native AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yurineko73/godot-mcp-native/agents-md/github.svg)](https://agentmods.dev/instructions/yurineko73/godot-mcp-native/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yurineko73/godot-mcp-native/agents-md"><img src="https://agentmods.dev/badge/instructions/yurineko73/godot-mcp-native/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 Godot-MCP-Native AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yurineko73/godot-mcp-native/agents-md"><img src="https://agentmods.dev/badge/instructions/yurineko73/godot-mcp-native/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,847 This file is loaded in full into every session.
When invoked 3,847 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 $0.03847 $0.03847
Opus 5 $0.01924 $0.01924
Sonnet 5 $0.00769 $0.00769
Haiku 4.5 $0.00385 $0.00385

Measured 9d ago against content hash 541ac61e1e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Godot-MCP-Native 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 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.

AGENTS.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Godot MCP 项目指南

项目简介

一个 Godot 4.6 EditorPlugin(位于 addons/godot_mcp/),在 Godot 内部原生实现了 MCP(Model Context Protocol)服务器,无需 Node.js 依赖。提供 154 个工具(30 核心 + 124 补充),分为 6 大类,供 AI 助手读取和修改项目。

  • 插件入口addons/godot_mcp/mcp_server_native.gd(继承 EditorPlugin
  • 作者:yurineko73 | 版本:1.0.7
  • 许可证:MIT
  • 渲染器:GL Compatibility

gdmcp CLI Skill

When using the shell-oriented gdmcp companion for Godot editor operations, read skills/gdmcp/SKILL.md first. Use the high-level bounded commands before progressive discovery with tools search, tools schema, and tool-call.

PowerShell 7.x 路径

系统 PowerShell 版本可能变化,每次会话请验证确切的版本号:

& "C:\Program Files\WindowsApps\Microsoft.PowerShell_*_x64__8wekyb3d8bbwe\pwsh.exe"

(Get-Command pwsh).Source 解析路径。如果 WindowsApps 路径不可用,回退到系统默认 PowerShell。

代码语言政策

  • 任何代码文件中不得出现中文字符 — 注释、字符串、标识符全部使用英文。
  • 中文仅允许出现在:AGENTS.mdREADME.zh.mddocs/(翻译/计划文档)。

命令

运行 Godot 项目

在 Godot 编辑器(4.6.x,GL Compatibility 渲染器)中打开 project.godot

GUT 单元测试

& "F:\Godot\Godot_v4.6.1-stable_win64.exe" --headless --path "." -s addons/gut/gut_cmdln.gd -gdir=res://test/unit/ -ginclude_subdirs -gexit

配置:.gutconfig.json — dirs: res://test/unit/, log_level: 2, should_exit_on_finish: false

集成测试(Python)

cd test/integration
python test_runtime_probe_flow.py

Python 测试会启动 Godot 4.6.2(C:\SourceCode\Godot_v4.6.2-stable_mono_win64\...),通过 HTTP MCP(端口 9080)进行通信。

架构

addons/godot_mcp/
├── mcp_server_native.gd       # EditorPlugin 入口 — 注册插件、管理生命周期
├── native_mcp/                 # 核心服务器引擎
│   ├── mcp_server_core.gd      # 中枢:工具注册、JSON-RPC 分发、信号总线
│   ├── mcp_transport_base.gd   # 传输层抽象基类
│   ├── mcp_http_server.gd      # HTTP/SSE 传输(默认端口 9080)
│   ├── mcp_stdio_server.gd     # stdio 传输(供 Claude Desktop 等使用)
│   ├── mcp_types.gd            # JSON-RPC 和 MCP 协议常量、MCPTool 数据类
│   ├── mcp_tool_classifier.gd  # 工具分类映射:{core/supplementary, group}(CORE_MAX_COUNT=30)
│   ├── mcp_resource_manager.gd # 资源读取/列表/订阅
│   ├── mcp_debugger_bridge.gd  # Godot 调试器 ↔ MCP 桥梁(断点、栈帧、变量)
│   ├── mcp_auth_manager.gd     # HTTP Bearer Token 认证
│   ├── config_manager.gd       # 插件配置读写
│   ├── settings_manager.gd     # 编辑器设置持久化
│   ├── tool_state_manager.gd   # 每个工具的状态管理
│   └── translation_manager.gd  # 国际化支持
├── runtime/
│   └── mcp_runtime_probe.gd    # Autoload 单例,用于运行时检查(动画、音频、着色器、瓦片地图、输入)
├── tools/                      # 工具实现(每个分类一个文件)
│   ├── node_tools_native.gd    # 20 个工具 — 创建/删除/更新/复制/移动/重命名节点、信号、分组、锚点预设、批量操作、场景审计
│   ├── script_tools_native.gd  # 14 个工具 — 读取/写入/创建/附加/分析/验证/执行脚本、符号索引、搜索
│   ├── scene_tools_native.gd   # 8 个工具 — 创建/保存/打开/关闭场景、结构查看、列表
│   ├── editor_tools_native.gd  # 16 个工具 — 运行/停止、状态、截图、信号、导出、选择、查看器
│   ├── debug_tools_native.gd   # 70 个工具 — 日志、断点、栈帧/变量、性能分析器、运行时探针、动画/音频/着色器/瓦片地图运行时控制
│   └── project_tools_native.gd # 26 个工具 — 项目信息/设置、资源、输入映射、自动加载、全局类、测试运行器、诊断
├── ui/
│   ├── mcp_panel_native.gd     # 主停靠面板(VBoxContainer)— 启动/停止、传输配置、日志查看、工具管理
│   ├── mcp_tool_item.gd        # 单个工具开关 UI
│   └── mcp_tool_group_item.gd  # 工具组折叠/展开 UI
└── utils/
    ├── node_utils.gd           # 节点查找辅助函数
    ├── path_validator.gd       # 路径验证
    ├── resource_utils.gd       # 资源 I/O 工具
    ├── script_utils.gd         # 脚本工具
    └── vibe_coding_policy.gd   # Vibe Coding 模式守卫(allow_ui_focus / allow_window)

Read the full file on GitHub · 245 lines

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. 9d ago First seen · 245 lines · 3,847 tokens per session scan A 541ac61e1e75

Subscribe to this mod's changes

Godot-MCP-Native AGENTS.md is an instructions file published in the GitHub repository yurineko73/Godot-MCP-Native (767 stars, last pushed 1mo ago), licensed MIT. It adds 3,847 tokens to every session, about $0.0192 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens