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 IvanYangYangXi/artclaw_bridge --skill artclaw-unity-contextgit clone --depth 1 https://github.com/IvanYangYangXi/artclaw_bridgeWrote 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/ivanyangyangxi/artclaw_bridge/artclaw-unity-context)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/artclaw-unity-context"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/artclaw-unity-context/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/ivanyangyangxi/artclaw_bridge/artclaw-unity-context"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/artclaw-unity-context.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 | $0.00135 | $0.01007 |
| Opus 5 | $0.00068 | $0.00504 |
| Sonnet 5 | $0.00027 | $0.00201 |
| Haiku 4.5 | $0.00014 | $0.00101 |
Grade A, and why
artclaw-unity-context 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ArtClaw Unity 上下文
UnityClawBridge 的入口 Skill。了解 Unity 环境的接入方式,并路由到正确的操作 Skill。
执行模型
AI → run_unity_python(code="<C# 代码>")
↓ MCP :8088
Python MCP Server
↓ HTTP POST :8089
C# CommandServer(Unity 后台线程接收)
↓ _commandQueue
EditorApplication.update(Unity 主线程)
↓ Roslyn/反射执行
Unity Editor API
↓ 结果写入 _results[id]
Python GET /result/{id}
↓
AI 收到 JSON 结果
核心规则:
- 所有 Unity API 必须通过
run_unity_python提交 C# 代码字符串 执行 - 代码在 Unity 主线程执行,完全支持
UnityEngine.*/UnityEditor.*命名空间 - 用
return Newtonsoft.Json.JsonConvert.SerializeObject(...)返回结构化数据 - 始终使用
Undo.RecordObject/Undo.RegisterCreatedObjectUndo支持撤销
Skill 路由表
| 任务 | 加载的 Skill |
|---|---|
| 获取场景信息、打开/保存场景、查找 GameObject | unity-scene-ops |
| 创建/删除/移动/复制 GameObject,设置 Transform | unity-gameobject-ops |
| 添加/移除/修改组件(Rigidbody、Light、Camera 等) | unity-component-ops |
| 导入/搜索/创建/删除资产,实例化 Prefab | unity-asset-ops |
| 撤销/重做、Play Mode、构建、菜单执行、控制台 | unity-editor-control |
环境检查
在执行操作前,先确认 Unity 已连接:
run_unity_python(code="""
return Newtonsoft.Json.JsonConvert.SerializeObject(new {
connected = true,
unityVersion = UnityEngine.Application.unityVersion,
projectName = UnityEngine.Application.productName,
dataPath = UnityEngine.Application.dataPath,
isPlaying = UnityEditor.EditorApplication.isPlaying,
isCompiling = UnityEditor.EditorApplication.isCompiling
});
""")
C# 代码格式要求
- 无需命名空间声明:
UnityEngine/UnityEditor已自动引入 - 返回 JSON 字符串:用
Newtonsoft.Json.JsonConvert.SerializeObject(...)或return "{...}" - 支持多行代码:用换行符分隔语句
- 变量在调用间共享(持久命名空间):可跨调用使用已定义的变量
// 最小示例 — 返回当前场景名
return UnityEngine.SceneManagement.SceneManager.GetActiveScene().name;
// 标准示例 — 返回 JSON
var scene = UnityEngine.SceneManagement.SceneManager.GetActiveScene();
return Newtonsoft.Json.JsonConvert.SerializeObject(new {
name = scene.name,
path = scene.path
});
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 · 115 lines · 135 tokens per session scan A f10a56ebc6c4
artclaw-unity-context is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 135 tokens to every session and 1,007 once invoked, about $0.0007 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 skills, from other repositories
usd-tools
Infrastructure skill — low-level OpenUSD scene inspection and validation: read layer stacks, traverse prims, validate USD schemas. Use when working directly with raw USD files (usda, usdc, usdz) or verifying USD compliance. Not for Maya-specific USD export — use maya-pipelineexportusd for that. Not for full DCC…
spatial-interchange
Plan deterministic coordinate-axis and unit conversions between DCCs, engines, and interchange formats from explicit right/up/forward axes and meters-per-unit values.
game-level-layout
Game level layout review helpers for editor contexts.
dcc-mcp-core
Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…
dcc-cua
A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…