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 jagit 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/ja)<a href="https://agentmods.dev/skills/k-telux/opticalmodeler/ja"><img src="https://agentmods.dev/badge/skills/k-telux/opticalmodeler/ja/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/k-telux/opticalmodeler/ja"><img src="https://agentmods.dev/badge/skills/k-telux/opticalmodeler/ja.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 | $0.00106 | $0.02699 |
| Opus 5.5 | $0.00042 | $0.01080 |
| Sonnet 5.5 | $0.00021 | $0.00540 |
| Haiku 4.5 | $0.00011 | $0.00270 |
Grade A, and why
thorlabs-blender-optical-path-ja 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 18d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpticalModeler 2.0 — Thorlabs Blender Optical Path
測定要件または 2D 光路図を、説明可能で独立監査可能な Blender 光学テーブルへ変換します。
2.0 の操作と納品境界
英語版を技術的な正本とします。写真・固定端点・限定移動・port/shutter state では再構築と改訂、材質・照明・画像再利用・UI/返信ではpresentation と納品、公開ではprivacyを読みます。6 つの英語対話と中国語対話は依頼、確認、拒否/修正、検査、最終成果物までを示す教育用編集であり、逐語 transcript や新 blind test ではありません。
- 新設計、写真/図の再構築、限定修正、presentation copy、read-only audit を区別します。新測定は空のシーン/新 topology から開始します。明示的に保持する再構築 baseline は新 revision で read-only 再利用できます。限定修正は既存 lineage、入力 lock、実 pending gate を維持します。
- Installed/user-confirmed identity、メーカー candidate、proposed part、geometry source、図面/モデル/実験室寸法、physical qualification は別軸です。実 holder は未知 optic prescription を証明しません。
- 完全な protected set、rigid 相対ベクトル、固定上段 pose、鏡数/順序、水平区間、編集自由度を事前に固定します。「Compact」は再設計許可ではありません。意図一致を幾何診断と別に確認します。
- 実 working-face 中心/法線を使い、他 node の足/ねじを含む whole family と changed-to-fixed/changed-to-changed を検査します。屋根下配置は全 device/support footprint と実 plate projection を比較します。Source plate 範囲、穴位相、slot/polygon index、広い bearing、盲孔底を検査し、null を zero gap、finite contact を retention/preload/load qualification にしません。
- 未確認内部は functional black box です。実外部開口と正確な selector を使い、2 exit を同時分光と仮定しません。各 state で evaluated transform/visibility を更新し、CLOSED axis は明示 closure で停止します。Proposed label を画像/説明で維持します。
- Presentation は別 copy です。保存後に全関連 mesh/topology、属性/normal、modifier、semantic、slot、visibility、state を比較します。実 shader users を調べ、必要時だけ対象 object/slot を独立化し sensor/optic を保護します。実画素/branch と decode 寸法/bit depth を確認します。Frame 内投影は非遮蔽の証明ではありません。
- 再利用画像は元 producer と完全な dependency bridge を残し、新 render receipt に偽装しません。Relight/recolor の影響画像は新規描画します。
- 既存写真/証拠を先に使い、必要な問いのみします。ユーザーが review candidate を先に望む場合、editable model、実 full-path views、guide、測定 checklist を未知項目付きで完成します。
READY_FOR_USER_REVIEWは physical PASS ではありません。 - 並行許可でも共有 writer は一人です。通常 feedback は checkpoint/idle にまとめ、進行中 render を繰り返し中断しません。明示 resource stop で再開状態を保存し、納品後の任意修正を止めます。
- 公開は機能 alias を使い、重要 SKU、実座標/動作値、private photos/scenes、メール/session、対応表を Git に含めません。既公開 independent example の出所は保持します。Private term policy は repository 外に置き、scanner と visual/container review を実施します。
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.
- 18d ago Changed · +19 lines 76384a5855ea
- 1mo ago Changed · +4 lines · +6 tokens per session 1107db9931a5
- 1mo ago First seen · 37 lines · 100 tokens per session scan A 7fa121d0556b
thorlabs-blender-optical-path-ja is a skill published in the GitHub repository k-telux/OpticalModeler (137 stars, last pushed 18d ago), licensed MIT. It adds 106 tokens to every session and 2,699 once invoked, about $0.0004 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
blender-data-geometry
Create bounded native meshes, editable poly curves and built-in-font text from explicit data. Use for GIS contours, scientific interchange, native typography and procedural authoring before raw scripting.
FigFox-Gen-skill
Use when turning a scientific Methodology, with an optional reference image, into one evidence-grounded, human-editable final PNG figure.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…