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 agentmods add skills/lex669/lumericalfdtd-skill/lumericalfdtd-modelingnpx skills add Lex669/LumericalFDTD-skill --skill lumericalfdtd-modelinggit clone --depth 1 https://github.com/Lex669/LumericalFDTD-skillWrote 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/lex669/lumericalfdtd-skill/lumericalfdtd-modeling)<a href="https://agentmods.dev/skills/lex669/lumericalfdtd-skill/lumericalfdtd-modeling"><img src="https://agentmods.dev/badge/skills/lex669/lumericalfdtd-skill/lumericalfdtd-modeling.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.01370 |
| Opus 5 | $0.00056 | $0.00685 |
| Sonnet 5 | $0.00022 | $0.00274 |
| Haiku 4.5 | $0.00011 | $0.00137 |
Grade A, and why
LumericalFDTD-modeling 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 6d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FDTD 结构建模器
职责范围
本 skill 仅负责结构建模阶段：构建几何、设置材料、配置光源和监视器、定义网格覆盖。输出纯建模脚本（不含 fdtd.run()），供后续仿真 skill 使用。
不负责：运行仿真（→ LumericalFDTD-simulation）、数据分析（→ LumericalFDTD-analysis）、端到端全流程（→ LumericalFDTD）。
工作流
1. 理解需求
确认以下信息后开始编写脚本。若用户未明确提供，主动询问：
| 类别 | 需确认的参数 |
|---|---|
| 器件结构 | 几何形状、尺寸、（x/y/z span / radius / thickness）、排列方式（单孔/阵列/周期） |
| 材料 | 衬底材料、金属层材料、蚀刻区域 |
| 光源 | 波长范围（start/stop）、偏振方向、入射方向、光束类型（平面波/高斯/偶极子） |
| 监视器 | 类型（功率/场分布/折射率）、位置、覆盖范围 |
| 仿真域 | x/y/z span、边界条件、网格精度 |
2. 构建脚本
按以下结构生成 *_model.py：
# 1. 导入
import sys; sys.path.append("{API_PATH}")
import lumapi; import numpy as np
import matplotlib; matplotlib.use('Agg'); import matplotlib.pyplot as plt
# 2. 参数定义（集中管理）
wavelength = 100e-6
x_span = 200e-6; y_span = 200e-6; z_span = 100e-6
# ... 结构参数 ...
# 3. 仿真会话 — 仅构建，不运行
with lumapi.FDTD(hide=True) as fdtd:
# 3a. 仿真区域
fdtd.addfdtd()
# ...
# 3b. 材料 / 衬底
# ...
# 3c. 几何结构（从底到顶）
# ...
# 3d. 网格覆盖（可选，精细结构才加）
# ...
# 3e. 光源
# ...
# 3f. 监视器
# ...
# 3g. 保存模型（不运行）
fdtd.save(os.path.join(fsp_dir, "model.fsp"))
3. 输出
*_model.py— 建模脚本（纯结构构建）- 可选：
.fsp模型文件（供手动打开检查）
参考文档
根据构建需要读取：
| 参考文件 | 何时读取 |
|---|---|
../LumericalFDTD/references/building-blocks.md |
需要几何结构、光源、监视器、网格覆盖的详细 API 用法 |
../LumericalFDTD/references/diffraction.md |
涉及孔衍射结构时 |
关键约束（与主 skill 一致）
| 约束 | 说明 |
|---|---|
2025 R2 必须显式 addfdtd() |
lumapi.FDTD() 后立即调用 fdtd.addfdtd()，否则所有 set 报错 |
严禁 fdtd.newproject() |
重置项目会销毁 'FDTD' 求解器 |
set() vs setnamed() 区别 |
set() 对当前选中对象操作；add*() 会改变当前选中。不确定时用 setnamed() |
不用 addmaterial 创建已有材料 |
addmaterial() 参数是基类型（'Dielectric'），不是材料实例名。内置材料直接用 set('material', '全名') |
| 材料全名不可简写 | "PEC (Perfect Electrical Conductor)" 不是 "PEC" |
addmaterial('(n=1.47)') 不支持 |
这是 .lsf 语法，Python API 不接受。用内置材料或 addmaterial('Dielectric') + set('index', 1.47) |
多边形函数名是 addpoly |
不是 addpolygon |
addcone 不存在 |
用多层 addcircle 堆叠替代 |
多边形不支持 mesh order |
省略该 set 语句 |
| 多边形顶点用 N×2 NumPy 数组 | set("vertices", np.array(...))，Python list of tuples 报 Unsupported data type |
严禁 fdtd.set("dimension", "2D") |
用 quasi-2D 方案：3D + y_span=0.2um + Periodic BC |
2D 监视器无 far field filter |
仅用 frequency points 做频域采样 |
2D 监视器无 record field in time |
addprofile 改用 frequency points |
| raw string 不能以反斜杠结尾 | 用 "C:\\path\\" 双反斜杠 |
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.
- 6d ago First seen · 106 lines · 111 tokens per session scan A 5aca0269d1fe
LumericalFDTD-modeling is a skill published in the GitHub repository Lex669/LumericalFDTD-skill (23 stars, last pushed 16d ago), licensed MIT. It adds 111 tokens to every session and 1,370 once invoked, about $0.0006 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
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
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for 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
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…