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 znlgis/opengis-skills --skill lightcadgit clone --depth 1 https://github.com/znlgis/opengis-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/skills/znlgis/opengis-skills/lightcad)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/lightcad"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/lightcad/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/znlgis/opengis-skills/lightcad"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/lightcad.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 | $0.00085 | $0.03658 |
| Opus 5.5 | $0.00034 | $0.01463 |
| Sonnet 5.5 | $0.00017 | $0.00732 |
| Haiku 4.5 | $0.00009 | $0.00366 |
Grade A, and why
lightcad 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 11d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目地址： https://github.com/znlgis/lightcad1
所属平台： 飞扬集成设计平台（LightCAD，启道软件 Qidao Soft 开源）
许可证： CC-BY-SA-4.0（见仓库 LICENSE）
中文教程： https://znlgis.github.io/cad/LightCAD/（20 章，从架构到插件实战）
版本： 仓库暂无公开 Release/Tag，以 master 分支为准（截至2026-10）
概述
LightCAD（飞扬集成设计平台）是一套基于 .NET 8 / C# 开发的开源建筑工程设计软件，目标是把二维设计、三维设计、BIM 设计、智能设计与协同设计融合为一体，为建筑设计行业提供 BIM 正向设计支撑能力。项目采用严格的分层架构（MathLib → Core → RenderUtils → Drawing → Runtime → UI），既可作为完整 CAD 平台使用，也可作为二次开发底座。核心特性：
- 完整 2D/3D 能力：直线、圆弧、多段线、样条等二维图元；拉伸、旋转、放样、融合等参数化实体建模
- 多渲染后端：Three.js4Net（WebGL）与 OpenTK（OpenGL）
- DWG/DXF 兼容：通过 ODA SDK 与内置 netDxf 处理 AutoCAD 文件格式，另支持 SketchUp 导入
- 插件体系：基于 Weikio Plugin Framework 运行时加载；预置建筑（QdArch）、电气（QdElectric）、暖通（QdHvac）、结构（QdStruct）、给排水（QdWater）五大行业插件
- 视图构建：正交投影、截面视图、详图生成
环境准备
前置条件
| 项 | 要求 |
|---|---|
| 操作系统 | Windows 10（1909+）/ Windows 11 64 位 |
| 开发工具 | Visual Studio 2022（17.5.5+，.NET 桌面开发工作负载）或 dotnet CLI |
| SDK | .NET 8 SDK |
| 硬件 | 8GB 内存起（推荐 16GB+），支持 OpenGL 3.3 的显卡 |
获取源码与编译（命令行方式）
# 仓库体积较大（含 DLL 与资源），建议浅克隆
git clone --depth 1 https://github.com/znlgis/lightcad1.git
cd lightcad1
# 还原与编译
dotnet restore LightCAD1.sln
dotnet build LightCAD1.sln --configuration Debug
运行（VS 或 CLI）
# VS：用 Visual Studio 打开 LightCAD1.sln，将 LightCAD.WinForm 设为启动项目，按 F5
# CLI：
dotnet run --project src/LightCAD.WinForm
验证：稳定编译后启动主窗口即成功；插件调试采用 VS「附加到进程」绑定 lightcad 进程（参见 FY_Layout 插件示例的做法）。
解决方案结构（关键项目）
| 项目 | 职责 |
|---|---|
LightCAD.MathLib |
向量/矩阵、曲线数学、几何求交（Vector2/Vector3 等） |
LightCAD.Core |
核心数据模型：LcDocument、图元实体（LcElement）、ElementType、元素空间 |
LightCAD.RenderUtils |
Three.js4Net 桥接、资源与事件、三维控件 |
LightCAD.Drawing / LightCAD.Drawing.Actions |
视口、输入系统、捕捉、交互 Action（IDocumentEditor） |
LightCAD.Runtime |
应用运行时：ILcPlugin、PluginManager、命令框架（CommandClass/CommandMethod） |
LightCAD.Model / LightCAD.UI.WinForm / LightCAD.WinForm |
模型控件、UI 层与主程序入口 |
LightCAD.ImportAndExport |
DWG/DXF/SketchUp 导入导出 |
Plugins/ |
预编译行业插件（QdArch 等） |
netDxf、Libs/、ThirdParty/ |
DXF 库源码、本地 DLL（ThreeJs4Net/OpenTK）、第三方源码 |
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.
- 11d ago Changed · +10 lines · +1 tokens per session 0944e7764808
- 12d ago Changed · -12 lines · +41 tokens per session 94562d717712
- 1mo ago Changed 8a27717f9507
- 1mo ago Changed e97e1df3ff88
- 1mo ago Changed 1d04bf5ad3ba
- 1mo ago First seen · 252 lines · 43 tokens per session scan A 9202d870e129
lightcad is a skill published in the GitHub repository znlgis/opengis-skills (75 stars, last pushed 7d ago), licensed MIT. It adds 85 tokens to every session and 3,658 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 2026-08-30.
Other skills, from other repositories
furniture-fit
Assess whether furniture fits in a measured Pascal room or layout. Use this skill for sofa, table, bed, cabinet, appliance, staging, placement, collision, clearance, or rotated-footprint questions. Produce a tool-backed spatial report that distinguishes footprint fit from unsupported height, door-swing, assembly, and…
pascal-3d
Connect to Pascal and use its MCP tools to create, inspect, edit, validate, save, or hand off editable 3D building scenes. Use this skill whenever a user asks an agent to work in Pascal, make a room or building model, inspect a Pascal project, perform spatial edits, connect Pascal MCP, or return a verified Pascal…
semantic-kernel
Build AI-enabled .NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable. USE FOR: adding AI-driven prompts, plugins, or orchestration to a .NET app; reviewing kernel construction, service registration, or plugin usage; building…
codegen
Use for .NET code generation work with Roslyn, Microsoft.OpenApi, Razor templates, DTO/manager/controller generation, REST API generation, C# HttpClient generation, Angular/Axios TypeScript request clients, generated formatting, and deterministic output.
grasshopper-component
Complete guide for developing custom Grasshopper components in C# — GHComponent class, RegisterInputParams/OutputParams, SolveInstance, DataTree patterns, parameter types, error handling, and component packaging as .gha. Use this skill whenever creating or debugging a Grasshopper component: "grasshopper component c#"…
rhinocommon-geometry
Deep reference for Rhino.Geometry namespace — all geometry types, operations, and patterns in RhinoCommon. Use this skill whenever working with Rhino geometry in C# or Python: Point3d, Vector3d, Curve, Surface, Brep, Mesh, NURBS, intersections, boolean operations, transforms, planes, bounding boxes. Triggers on…