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 k-telux/OpticalModeler --skill zh-cngit clone --depth 1 https://github.com/k-telux/OpticalModelerWrote 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/k-telux/opticalmodeler/zh-cn)<a href="https://agentmods.dev/skills/k-telux/opticalmodeler/zh-cn"><img src="https://agentmods.dev/badge/skills/k-telux/opticalmodeler/zh-cn.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.01419 |
| Opus 5 | $0.00045 | $0.00709 |
| Sonnet 5 | $0.00018 | $0.00284 |
| Haiku 4.5 | $0.00009 | $0.00142 |
Grade A, and why
thorlabs-blender-optical-path-zh 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 3d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thorlabs Blender 光路
把测量需求或二维示意图转换成可解释、可独立审计的 Blender 光学平台。
英文版是技术权威源。涉及几何时读取 ../../skills/thorlabs-blender-optical-path/references/physical-gates.md；验收前读取 evidence-contract.md；修订旧场景时读取 history-derived-rules.md；完整案例见 project-case-study.md；整机运行前读取 end-to-end-workflow.md；多轮规模/发布资格测试读取 multi-run-qualification.md。
权威与版本
- 系统约束优先；随后是用户最新文字或标注截图、项目 active rules、本 skill，最后才是旧产物和旧 PASS。
- 冻结已提交或验收的包；在活动 revision 中集中处理相关纠正，不覆盖冻结证据，不为每张预览发布新版本。
- 整机保持一个 run ID、writer、revision、生成器/Blend 谱系和 workflow 账本；副 agent 默认只读，禁止拼接独立写入模块冒充整机完成。
- 把每个截图问题转换为对象族、世界坐标几何、数值门槛和必需证据。
- 无法证明时使用
UNVERIFIED或BLOCKED。文件存在、CAD 导入、进程成功、AABB 接触和自报文本都不是证据。
核心流程
先区分新测量设计、原图重建、既有场景修正与纯渲染。用户要求“参考旧示例的精度生成另一种光路”时，旧示例只作画质比较，需从空场景建立新拓扑、生成器与资产映射。optics-only 包含光学探测器和机械支撑，排除电路及电气/数据信号可视化。详细要求见新设计与渲染。
- 用
scripts/workflow_ledger.py初始化一个整机 run spec、状态账本和 append-only 事件哈希链。 - 建立
schematic node -> 实验角色 -> 真实资产 -> 光/光纤/电端口 -> 支撑路径。 - 列出全部分支、器件、光束高度、孔径和探测终点。
- 只从 manifest 锁定的厂家 URL 把官方 CAD 下载到私有缓存；原子落盘前复核 bytes 与 SHA-256，并记录型号、来源、尺度、bbox、局部光轴、法向、孔径、provenance 和再分发边界。替代件必须明示；没有明确授权时禁止公开厂家几何。
- 把 source lock 与其全部哈希文件当作一个原子输入包；几何前运行 producer-to-consumer artifact preflight，确认 source bytes、CAD canonical/型号别名 key、官方图纸和 runtime 均位于下一脚本实际消费的路径。查找前先按强类型 exact-set 合同验证结构化 authority 输入；missing、duplicate、extra、legacy、malformed 或身份不一致必须生成可持久化的结构化
BLOCKED，不得异常退出或静默折叠重复项。 - 发布脚本必须重算同一语义锁且 difference paths 为零。多状态系统的每条 edge 必须有精确
active_states或哈希化确定型展开，每个 state 都要有明确 ray template。 - 先解光心、镜面、分束面、反射和分支连续性。设计坐标与保存后重开的真实 mesh/port 测量必须分开；常量零误差和命中同名器件族不足以证明孔径及首碰撞。
- 再从真实桌孔向上按 post-first 构建紧固件、夹具、holder、post、mount 和器件。
- 修共享根因，在同一运行内先验一个代表件再传播；保存后重开并逐件复核。
- 先做明亮的机械/轴向/剖切审计图，再做 beauty render。
- README/GATE 计数必须来自机器证据；随后在同一账本完成重开、整机 ray/BVH、OpenCV、GLB 回导、二进制/PNG 元数据脱敏、manifest、hash 和全 active-rule 合规矩阵。
光束、柔性光纤和电缆必须是不同对象族，仅生成请求范围内的类别。孔径必须真实开放。删除重复 surrogate 和无角色 placeholder。低成本诊断预览可用于检查器件精度、可见光路与构图，但必须注明尚未闭合的物理证据；最终发表级渲染在物理门通过后完成。保留材质槽与多边形索引语义，逐器件近景和逐分支检查；全图清晰度、边缘密度、颜色像素数不能单独证明建模精度或光束连续。实际 2K 图不能满足 4K 交付要求。
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.
- 3d ago Changed · +4 lines · -8 tokens per session 47c294592d65
- 8d ago First seen · 37 lines · 98 tokens per session scan A f910d825798d
thorlabs-blender-optical-path-zh is a skill published in the GitHub repository k-telux/OpticalModeler (215 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 1,419 once invoked, about $0.0005 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
FigFox-Gen-skill
Use when turning a scientific Methodology, with an optional reference image, into one evidence-grounded, human-editable final PNG figure.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
figure
Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly). Includes a TikZ template library covering quantum circuits (quantikz), Feynman diagrams (tikz-feynman), circuits (circuitikz), molecules (chemfig), 2D/3D plots (pgfplots), energy-level diagrams, phase-space trajectories…