Borrowing it
Nothing to install: this file belongs to AmaniDawn/DGame. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AmaniDawn/DGame/main/.agents/skills/unity-cli/SKILL.mdgit clone --depth 1 https://github.com/AmaniDawn/DGameWrote 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/amanidawn/dgame/unity-cli)<a href="https://agentmods.dev/skills/amanidawn/dgame/unity-cli"><img src="https://agentmods.dev/badge/skills/amanidawn/dgame/unity-cli/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/amanidawn/dgame/unity-cli"><img src="https://agentmods.dev/badge/skills/amanidawn/dgame/unity-cli.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 | $0.00064 | $0.01195 |
| Opus 5.5 | $0.00026 | $0.00478 |
| Sonnet 5.5 | $0.00013 | $0.00239 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
unity-cli 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 16d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DGame Unity CLI
执行入口
Unity CLI 原生命令通过客户端已加载的 MCP 工具或 unity command <name> 调用。MCP 工具已暴露时直接使用其描述与参数，先以 editor_status.projectPath 核对当前工程；不要求服务名为 unity-dgame，也不要求每次读取客户端配置或运行本地 CLI。任务需要 CLI 且项目副本缺失时，先运行 python .agents/scripts/workflow.py doctor 完成准备和验收，再继续调用。未暴露对应工具时，直接 CLI 固定 --project-path <GameUnity 绝对路径>；Player 使用明确的 --runtime-path。
直接 CLI 使用 GameUnity/Tools/unity.exe，缺失时按 版本配置 准备项目副本。无命令名的 unity command --project-path <绝对路径> 可发现当前注册命令。CLI 不是 Unity Editor 的同名程序。
MCP 工具由客户端配置的 unity mcp 服务提供，Pipeline 为原生命令提供描述和参数 Schema；技能不注册工具，Workflow 也不负责 MCP 发现。agents/openai.yaml 的自动调用策略用于技能选择，不设置工具优先级。普通原生命令不需要 Workflow 白名单、包装脚本或审批文件。
查询、验证、安装与 MCP 接入统一见 操作规程，按任务读取对应章节。组合验证、CI 和报告按需使用 项目 Workflow，Luban 生产导表使用 luban-dev。
| 操作 | 原生命令 / 对应 MCP 工具 |
|---|---|
| 工程与场景查询 | editor_status、list_open_scenes |
| 脚本编译 | test_status 确认无活动测试 → recompile → recompile_status |
| 测试 | list_tests → test_status 确认无活动测试 → run_tests → test_status |
不变量
- 只绑定当前 DGame 工程；导入、编译、测试与写入串行。新操作前核对唯一目标及状态，查询和轮询允许观察忙操作；直接 MCP/CLI 不经过 Workflow 工程锁。
- 源码用代码编辑工具修改，对象、序列化与资产用已注册命令；不通过文本写入、任意 eval、菜单或 Scene/Prefab YAML 绕过编辑和授权规则。
- 普通操作按用户任务及已有授权执行；先明确目标和影响范围，支持
dry_run时直接预览，不支持时读取目标并说明变更。删除、覆盖、依赖、设置、平台和真实构建按仓库授权边界处理，confirm不代替用户授权。 - 按命令真实实现核对副作用、
dry_run/confirm与 Undo 能力，执行后回读目标。超时先检查状态，禁止换入口自动重放写入。 - 编译或测试启动前查询
test_status；已有测试运行时等待，不依赖editor_status=ready判断测试空闲，不取消或覆盖已有测试。 - 异步命令检查触发响应，在调用方设定的总体期限内轮询终态；编译/测试默认每阶段 300 秒，超期报告 blocked/结果未知并保留现场，不自动取消或重放。测试先发现用例，按任务选择模式和筛选器，核对执行数与结果。零用例、全跳过、失败、取消或旧结果不能通过。
- 连接、命令或必需依赖缺失时报告具体 blocked 原因；任务需要项目 CLI 且副本缺失时先按安装验收流程准备，准备失败后再 blocked。不自动升级全局 CLI、启动 Editor、修改用户配置或借用其他工程。Pipeline 鉴权信息不得输出。
权威资料
按任务读取 GameUnity/Packages/com.unity.pipeline/Documentation~/：
| 场景 | 包内文档 |
|---|---|
| 连接、鉴权、Player | connectivity.md、runtime-setup.md |
| 路径、预览、Undo | safety-and-mutations.md、authoring-commands.md |
| 编译、测试、构建 | commands/build-and-compilation.md |
| 资源、对象、Prefab | commands/assets-and-files.md、commands/gameobjects-and-components.md、commands/prefabs.md |
| 截图、场景、设置 | commands/capture.md、commands/scenes.md、commands/project-settings.md |
| 新增项目命令 | creating-commands.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.
- 16d ago Changed 3fe6a17a42cb
- 18d ago Changed · -8 tokens per session af695cb6f13d
- 23d ago Changed · +6 lines 6a4a42e6e0d7
- 1mo ago First seen · 42 lines · 72 tokens per session scan A 9d8984531c14
unity-cli is a skill published in the GitHub repository AmaniDawn/DGame (177 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 1,195 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
regression-suite
Map test coverage to GDD critical paths, find fixed bugs lacking regression tests, flag drift from new features.
soak-test
Soak test protocol for extended play — what to observe and log for slow leaks, fatigue, late-appearing edge cases.
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
team-polish
Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
smoke-check
Critical-path smoke gate before QA hand-off — runs the automated suite. A failed check means the build is not QA-ready.