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/luban-dev/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/luban-dev)<a href="https://agentmods.dev/skills/amanidawn/dgame/luban-dev"><img src="https://agentmods.dev/badge/skills/amanidawn/dgame/luban-dev/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/luban-dev"><img src="https://agentmods.dev/badge/skills/amanidawn/dgame/luban-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00243 | $0.03578 |
| Opus 5.5 | $0.00097 | $0.01431 |
| Sonnet 5.5 | $0.00049 | $0.00716 |
| Haiku 4.5 | $0.00024 | $0.00358 |
Grade A, and why
luban-dev 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 1mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DGame Luban 配置开发
核心约定
现有 Excel 表结构保护
-
修改已有业务表字段前，先按逻辑字段名压缩并删除字段区间内、字段末尾的空列，再追加字段。
-
DGame 普通表通常包含
##var、##type、##group和##注释标记行，但这不是固定行号规则。修改前必须读取当前 Sheet 的全部标记行；多行##var/##type、纵表和额外注释行必须按原顺序保留，字段工具应复用现有注释行。 -
追加/删除字段后必须检查
field list的列号连续、validate --all通过，再执行导表。 -
源头：
GameConfig/Datas/、GameConfig/Defines/、GameConfig/CustomTemplate/，不要手改生成产物。 -
默认生成：客户端
cs-bin代码 +bin/json数据，优先走 LazyLoad。 -
默认脚本：
GameConfig/GenerateTool_Binary/gen_bin_client_lazyload.bat。 -
代码输出：
GameUnity/Assets/Scripts/HotFix/GameProto/LubanConfig/。 -
桥接文件：
ConfigSystem.cs、ExternalTypeUtil.cs由模板复制到GameUnity/Assets/Scripts/HotFix/GameProto/。 -
数据输出：二进制到
GameUnity/Assets/BundleAssets/Configs/Binary/；Json 路径以GenerateTool_Binary/path_define.*当前配置为准。 -
命名空间/顶层模块：
GameProto；总表管理器：Tables。 -
业务访问：优先在
GameUnity/Assets/Scripts/HotFix/GameLogic/ConfigMgr/封装XxxConfigMgr，不要把TbXXX访问散落到业务层。
导出脚本
所有脚本位于 GameConfig/GenerateTool_Binary/，使用相对路径调用。
| 脚本 | 用途 | 说明 |
|---|---|---|
gen_bin_client_lazyload |
客户端（推荐，LazyLoad 模板） | AI 默认调用此脚本 |
gen_bin_client |
客户端（标准模板） | 非懒加载 |
gen_bin_server_lazyload |
服务端（LazyLoad 模板） | 需要服务端配置时使用 |
gen_bin_server |
服务端（标准模板） | 非懒加载 |
gen_bin_all_lazyload |
客户端 + 服务端（LazyLoad 模板） | 一键导出两端 |
gen_bin_all |
客户端 + 服务端（标准模板） | 一键导出两端，非懒加载 |
AI 调用导表命令
根据操作系统选择对应扩展名。默认只导客户端 LazyLoad：
Windows：
cmd /c "set AI_MODE=1 && GameConfig\GenerateTool_Binary\gen_bin_client_lazyload.bat"
macOS/Linux：
bash GameConfig/GenerateTool_Binary/gen_bin_client_lazyload.sh
Workflow 导表边界
跨配置或需要写入生产输出时，优先使用仓库 Workflow：
python .agents/scripts/workflow.py luban validate
python .agents/scripts/workflow.py luban test
python .agents/scripts/workflow.py luban preview --mode lazyload
python .agents/scripts/workflow.py approve --plan <preview.json> --by <实际确认人> --reason <实际确认记录> --high-risk
python .agents/scripts/workflow.py luban apply --plan <preview.json> --approval <approval.json>
What ships with it
14 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.
- agents/openai.yaml 253 B
- references/command-reference.md 5.0 KB
- references/data-sources.md 4.0 KB
- references/dgame-integration.md 7.2 KB
- references/dgame-table-rules.md 3.5 KB
- references/excel-format.md 4.5 KB
- references/luban-conf.md 6.1 KB
- references/operating-guide.md 25 KB
- references/runtime.md 3.6 KB
- references/schema.md 8.8 KB
- references/type-system.md 4.3 KB
- references/validators.md 5.6 KB
- scripts/luban_helper.py 220 KB runs code
- scripts/requirements.txt 16 B
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.
- 1mo ago Changed · +14 lines c66b55a1b505
- 1mo ago Changed · +6 lines e13d7385760e
- 1mo ago Changed · +12 lines 2326bc4e9d80
- 2mo ago First seen · 168 lines · 243 tokens per session scan A bf490d1eb436
luban-dev is a skill published in the GitHub repository AmaniDawn/DGame (177 stars, last pushed 3d ago), licensed MIT. It adds 243 tokens to every session and 3,578 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
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
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
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.