UnitySkills is a REST API-based automation engine that lets AI coding agents control Unity Editor projects, including scenes and other editor operations. It is for developers using Unity with supported coding agents and IDEs. The catalogue skills and commands provide the agent workflows used to operate Unity projects through the engine.
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 agentmods add commands/besty0728/unity-skills/metacheckgit clone --depth 1 https://github.com/Besty0728/Unity-SkillsWrote 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/commands/besty0728/unity-skills/metacheck)<a href="https://agentmods.dev/commands/besty0728/unity-skills/metacheck"><img src="https://agentmods.dev/badge/commands/besty0728/unity-skills/metacheck.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02257 |
| Opus 5 | $0.00000 | $0.01128 |
| Sonnet 5 | $0.00000 | $0.00451 |
| Haiku 4.5 | $0.00000 | $0.00226 |
Grade A, and why
metacheck 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 5d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Check — .meta GUID 健康度审计
你是 UnitySkills 项目的 .meta 文件 GUID 审计助手。扫描整个仓库的 .meta 文件，检测使用了"伪随机 GUID"的资源——这类 GUID 因为字符模式可识别，极易与第三方包碰撞，导致 Unity 资源 ownership 争夺、类型缺失、CS0103 等编译错误。同时对照"已知第三方包 GUID 黑名单"，抓出 fork/衍生场景下与上游逐字节相同的确定性冲突。
背景：为什么要做这件事
Unity 用 32 位十六进制 GUID 唯一标识每一个资源。真随机 GUID（uuid4）碰撞概率约 $2^{-128}$。但人手写或简单算法生成的"伪 GUID"（如 a1b2c3d4e5f6...、0123456789abcdef...）会因为同样的"看似合理的造法"在多个独立项目里同时出现，进而碰撞。
历史教训（v1.8.x）：ValidationSkills.cs.meta 因为 GUID d4e5f6a7b8c9d0e1f2a3b4c5d6e7f8a9 与某些第三方包（如 com.posthog.unity 的 WebGLExceptionIntegration.cs）碰撞，导致用户项目里 ValidationSkills.cs 被 Unity 排除导入，BatchSkills.cs / PerceptionSkills.cs 出现 CS0103: The name 'ValidationSkills' does not exist in the current context。
另一类碰撞（v2.0.x，issue #41）：fork/衍生项目若连同上游 .meta 一起复制，会出现与上游逐字节相同的 GUID。这种 GUID 本身格式规范、也不命中下文任何伪随机启发式（例如 a2f7ae0675bf4fb478a0a1df7a3f6c64），步骤 2 的启发式审计无法发现，只能靠步骤 2b 的"已知第三方包 GUID 黑名单"对照。本项目曾因 package.json.meta 沿用上游 com.coplaydev.unity-mcp 的 GUID，导致两包同装时 Unity 报 6 条 missing script 警告。
步骤 1：扫描所有 .meta 收集 GUID
遍历仓库根目录下所有 .meta 文件（排除 .git、Library、Temp、obj、Logs），提取每个文件的 guid: 字段。
步骤 2：用启发式判定伪 GUID
一个 32 位 hex 字符串若同时满足"格式正确"且任一下列特征，判为可疑：
- 连续 hex 递增：包含长度 ≥ 4 的连续 hex 递增子串，如
0123、1234、2345、3456、4567、5678、6789、789a、89ab、9abc、abcd、bcde、cdef - 交错递增：包含形如
字母-数字-字母-数字-字母-数字-字母-数字且字母递增、数字递增的 8 字符段（例a1b2c3d4、b2c3d4e5、c0d1e2f3） - 同字符重复：包含
aaaa、0000、ffff等连续 4 个以上相同字符 - 字面 abcdef：包含子串
abcdef（hex 字面表） - 长度异常：不是恰好 32 位 hex
步骤 2b：已知第三方包 GUID 黑名单对照
启发式只能抓"可猜测的伪 GUID"，抓不了"与上游/第三方包逐字节相同"的确定性冲突。因此维护一份已知冲突 GUID 表，把本仓库所有 GUID 与之对照，命中即标记为"🔴 已知冲突 GUID"。
已知冲突 GUID 黑名单
| GUID | 来源 | 备注 |
|---|---|---|
a2f7ae0675bf4fb478a0a1df7a3f6c64 |
com.coplaydev.unity-mcp 的 package.json.meta（本项目 fork 上游） |
issue #41：两包同装触发 6 条 missing script 警告；已在 issue #41 修复中替换为本仓库独立 GUID 4a81947acf6349c4b37a44f35a71d7e8 |
如何扩充黑名单
fork/衍生项目应把上游仓库所有 .meta 的 GUID 纳入此表。一次性收集：
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.
- 5d ago First seen · 122 lines · 0 tokens per session scan A b3711d7d7c98
metacheck is a command published in the GitHub repository Besty0728/Unity-Skills (1,707 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,257 tokens. 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 commands, from other repositories
tokenless-stats
Show Tokenless compression statistics.
sim
Run the EmbodiedGen simulation rendering workflow with sim-cli.
combat-design
Design or revise combat rules, variables, readability, and tuning direction.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
skyrun
Toggle the SKYRUN game pane in your terminal (free-play).
good
Write good creative & smart copy [GOOD].