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 HappyLifeOk/cocos-mcp-gateway --skill cocos-mcp-controlgit clone --depth 1 https://github.com/HappyLifeOk/cocos-mcp-gatewayWrote 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/happylifeok/cocos-mcp-gateway/cocos-mcp-control)<a href="https://agentmods.dev/skills/happylifeok/cocos-mcp-gateway/cocos-mcp-control"><img src="https://agentmods.dev/badge/skills/happylifeok/cocos-mcp-gateway/cocos-mcp-control/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/happylifeok/cocos-mcp-gateway/cocos-mcp-control"><img src="https://agentmods.dev/badge/skills/happylifeok/cocos-mcp-gateway/cocos-mcp-control.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 | $0.00060 | $0.00750 |
| Opus 5 | $0.00030 | $0.00375 |
| Sonnet 5 | $0.00012 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
cocos-mcp-control 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 12d 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.
What it actually says
Cocos MCP 控制
绑定当前项目
- 从当前工作目录向上寻找同时包含
assets/、settings/和package.json的项目根。 - 调用
gateway_list_editors，用规范化后的绝对projectPath精确匹配当前项目。不要只凭工具前缀或项目名猜实例。 - 匹配后使用该实例的
<shortName>__*工具。多个项目同时打开时只操作当前项目。 - 没有匹配实例时，读取项目
package.json的creator.version，调用editor_spawn，显式传绝对projectPath和版本，再等待就绪。 gateway_list_editors只应返回transport=editor-bridge、gatewayApiVersion>=2、bridgeApiVersion=1的实例；旧项目/mcp不受支持。- Cocos Creator 3.8.x 项目缺少
extensions/cc-3-8-x-mcp时：若用户要求接入项目，运行cocos-mcp-connect <项目绝对路径>；若当前任务未授权安装扩展，则停止并说明缺失。非 3.8.x 项目不得安装此扩展。
选择入口
.prefab、.anim的结构化查询与修改：优先使用全局prefab_query、prefab_edit、prefab_batch；路径必须为绝对路径。- 场景运行态、AssetDB、预览和编辑器状态：使用当前项目带前缀的 MCP 工具。
- 项目扩展的
/bridge是 Gateway 私有协议；不要直接调用、不要把它注册成 MCP Server，也不要输出注册记录里的 token。 - 浏览器中的真实交互：先用 MCP 获取预览 URL，再交给可用的浏览器工具。
- 纯文本源码和文档：使用普通文件工具，不走 Prefab CLI。
修改 Prefab 前先查询节点树或字段；批量修改先 dry-run；任一操作失败时不要绕过 CLI 直接改 JSON。
修改后的闭环
- 单个资源修改后调用当前项目的
asset_reimport。 - 多资源或依赖不确定时调用
asset_refresh，再调用preview_refresh_and_reload。 - 尊重项目自己的预览刷新守卫、服务端和测试账号约定。
- 运行项目要求的类型检查或定向验证，并区分静态验证与真实预览验证。
安全边界
- 重启或关闭编辑器前先确认目标
projectPath；工具报告存在活跃调试连接时，不传force绕过。 editor_spawn、editor_restart、editor_wait_ready在编辑器未注册时必须显式传绝对项目路径。- 工具行为、文档与实际不一致时报告插件问题，不在业务项目添加临时 workaround。
- 详细工具分工和失败排查见 references/operations.md。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 40 lines · 60 tokens per session scan A 2740728be541
cocos-mcp-control is a skill published in the GitHub repository HappyLifeOk/cocos-mcp-gateway (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 60 tokens to every session and 750 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
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.