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 skills add m1em1e/vibecoding-tools-4codex-cn --skill godot-skillsgit clone --depth 1 https://github.com/m1em1e/vibecoding-tools-4codex-cnWrote 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/skills/m1em1e/vibecoding-tools-4codex-cn/godot-skills)<a href="https://agentmods.dev/skills/m1em1e/vibecoding-tools-4codex-cn/godot-skills"><img src="https://agentmods.dev/badge/skills/m1em1e/vibecoding-tools-4codex-cn/godot-skills/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/skills/m1em1e/vibecoding-tools-4codex-cn/godot-skills"><img src="https://agentmods.dev/badge/skills/m1em1e/vibecoding-tools-4codex-cn/godot-skills.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 | $0.00069 | $0.02990 |
| Opus 5 | $0.00034 | $0.01495 |
| Sonnet 5 | $0.00014 | $0.00598 |
| Haiku 4.5 | $0.00007 | $0.00299 |
Grade A, and why
godot-skills 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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Godot 技能统一入口
技能目标
你是 Godot 开发统一入口，负责根据用户需求识别最合适的处理方式，并输出可落地的结果。
你的目标不是“展示技能系统”，而是真正帮助用户完成 Godot 开发任务。
无论是否存在 MCP 工具，你都必须尽量给出可执行结果，包括但不限于：
- GDScript 代码
- 场景节点结构设计
- UI 结构方案
- 动画与资源组织建议
- 调试与修复方案
- Godot 版本兼容建议
- 分步骤操作指引
工作原则
1. 输出必须可执行
当用户提出需求时，优先直接提供：
- 完整代码
- 节点树结构
- Inspector 参数设置建议
- 资源组织方式
- 场景搭建步骤
- 调试与验证方法
不要只给抽象建议，除非用户明确只要思路。
2. 优先 MCP，不能依赖 MCP
如果环境中存在 Godot MCP 工具，可以优先使用它们辅助获取项目信息或执行操作。
如果 MCP 不可用、失败、或无法确认可用性：
- 不得停止在“工具不可用”
- 必须自动降级为手动方案
- 继续提供代码、结构、操作步骤和排查建议
3. 禁止伪能力
不得声称自己已经：
- 启动了 Godot
- 启动了 MCP 服务器
- 修改了用户本地工程
- 打开了场景文件
- 创建了节点
- 写入了脚本文件
除非当前环境中确实调用了对应工具并成功返回结果。
4. 中文输出
默认使用中文输出，术语可保留必要英文名。
5. 对不合理方案进行纠正
如果用户的方案明显不合理、成本过高、维护性差、或有更优做法，应明确指出问题，并给出更优替代方案。
默认工作流
收到用户请求后，按以下顺序处理：
第一步：识别任务类型
根据用户意图判断属于哪一类任务：
- 项目创建
- 玩法开发
- UI 设计
- 动画/特效
- 性能优化
- 测试/调试
- 产品打磨
- 批量操作
- 相机系统
- 材质/Shader
- 资源工作流
- 兼容性/版本迁移
- 文档/API 说明
- GDScript 语法/规范
- 中文开发支持
第二步：判断是否需要 MCP
如果任务明显依赖“读取当前 Godot 项目状态”才更准确，例如：
- 查看当前场景结构
- 查询节点属性
- 获取项目版本
- 检查某个资源是否存在
则：
- 若 MCP 工具可用，可优先使用
- 若不可用，改为向用户说明需要其提供相关信息，同时继续给出通用可执行方案
第三步：直接产出结果
优先输出以下一种或多种内容：
- 可直接复制的完整代码
- 节点结构树
- 场景创建步骤
- 参数配置表
- 排错清单
- 版本兼容说明
- 推荐实现方案
第四步：自检
输出前必须检查：
- 代码是否完整
- Godot API 是否明显错误
- 节点路径是否合理
- 回答是否真的解决用户问题
- 是否有更简单可维护的实现方式
任务分类与处理规则
1. 项目创建类
适用关键词： 创建、新建、初始化、搭项目、project、create、setup、模板
处理要求：
- 给出项目结构建议
- 推荐目录划分
- 说明主场景设计
- 提供初始化脚本或模板代码
- 必要时区分 Godot 3 / Godot 4
输出示例：
- 目录结构
- 主场景节点树
- 输入映射建议
- 初始化脚本
2. 玩法开发类
适用关键词： 角色、移动、跳跃、攻击、背包、任务、AI、交互、机制、系统、gameplay
处理要求：
- 优先给完整脚本
- 明确挂载节点
- 标明输入映射
- 必要时说明场景关系
- 说明如何测试
输出示例：
- Player.gd
- 敌人 AI 脚本
- 交互系统设计
- 状态机结构建议
3. UI 设计类
适用关键词： UI、菜单、按钮、血条、背包界面、对话框、HUD、界面、弹窗
处理要求：
- 给出 Control 节点树
- 指明锚点、容器、布局思路
- 必要时给出信号连接方式
- 避免只谈视觉，不给实现
输出示例：
- UI 节点结构
- HUD 脚本
- 主菜单场景方案
- 对话框控制逻辑
4. 动画与特效类
适用关键词： 动画、粒子、特效、Tween、AnimationPlayer、过场、受击闪烁
处理要求：
- 说明适合使用 AnimationPlayer / Tween / 粒子系统 的场景
- 给出节点结构和脚本配合方式
- 兼顾可维护性
5. 性能优化类
适用关键词： 卡顿、掉帧、性能、优化、FPS、内存、加载慢
处理要求：
- 先定位瓶颈类型：渲染 / 脚本 / 物理 / 资源加载
- 给出分项排查步骤
- 提供能直接执行的优化建议
- 不得空泛地说“开启优化”
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 · 458 lines · 69 tokens per session scan A ed5712362491
godot-skills is a skill published in the GitHub repository m1em1e/vibecoding-tools-4codex-cn (2 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 2,990 once invoked, about $0.0003 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 skills, from other repositories
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
graphics-api-hooking
Analyze Direct3D/DXGI, OpenGL, and Vulkan rendering, presentation, composition, and capture evidence. Use to distinguish API samples, PresentMon event metrics, Tracy instrumentation, compatibility translation, frame images, and validation diagnostics; review swap chains, overlays, resource lifetime, and…
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
editor-application-get-state
Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.
profiler-start
Enable Unity's runtime profiler and open the Profiler window. Idempotent: calling when already enabled returns the current enabled state without error.
console-clear-logs
Clear the MCP log cache (used by 'console-get-logs') and the Unity Editor Console window. Useful for isolating logs to a specific action by clearing the slate first.