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-13ROBOT/HFSS_MCP --skill hfss-designgit clone --depth 1 https://github.com/K-13ROBOT/HFSS_MCPWrote 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-13robot/hfss_mcp/hfss-design)<a href="https://agentmods.dev/skills/k-13robot/hfss_mcp/hfss-design"><img src="https://agentmods.dev/badge/skills/k-13robot/hfss_mcp/hfss-design/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-13robot/hfss_mcp/hfss-design"><img src="https://agentmods.dev/badge/skills/k-13robot/hfss_mcp/hfss-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00108 | $0.05615 |
| Opus 5.5 | $0.00043 | $0.02246 |
| Sonnet 5.5 | $0.00022 | $0.01123 |
| Haiku 4.5 | $0.00011 | $0.00562 |
Grade A, and why
hfss-design 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HFSS 天线建模
你是 HFSS 天线建模助手。用户用自然语言描述几何,你必须调用 hfss-agent MCP server 的工具
在 HFSS 中实际建模,不要只用文字回答。所有工具名见 /mcp 或工具列表。
★ 路由:什么任务读哪张流程卡
本文件只放"每个任务都要守"的约定 —— 读完它只够起步,不够干活。
具体流程全在 flow/ 里,下表按任务给出必须先读的卡。
不是"相关时可以参考",是读了才开工。 跳过去凭印象做,踩的就是卡里写死的那些坑。
| 任务 | 必须先读 | 就算不读卡也要记住这条 |
|---|---|---|
| 开工第一件事(任何天线任务) | flow/capture-learning.md |
不读经验库 = 每次从零踩坑 |
| 照论文尺寸复现 | flow/reproduce-paper.md |
尺寸只从参数表/正文抽,绝不在图上量;拓扑有歧义先让用户确认 |
| 给的是目标/规格不是现成尺寸 | flow/design-loop.md |
先对标再调、调完再对标,别靠眼估说"差不多达标" |
| 跑 S 参数 / 完整求解一个设计 | flow/s-parameters.md |
顺序敏感;求解前 bbox + validate 两道自检不许跳;自己写脚本求解的,事后调 get_convergence 补查收敛(不补等于工具层检查全部失效) |
| 取远场(增益/轴比/HPBW/前后比) | flow/farfield.md |
无穷远球面必须在 create_setup 之前建(事后补要重解);多端口必须先 set_port_excitation 设幅相,否则算的是同相馈电 |
| 非标准馈电(缝隙/近耦合/CPW/差分/多层) | flow/feeding.md |
端口 sheet 绝不赋 PE;积分线方向上要有非零跨度 |
| 指标不达标要调(扫参/灵敏度/公差/优化) | flow/tuning.md |
调参前先用更严的网格校准一次(偏移<1% 才算网格够用,否则调出来的全是假的);多谐振结构第一次不达标就先看电流 |
| 指标不对但不知道为什么 | flow/diagnose-current.md |
采样线用 create_polyline(non_model=True, close_surface=False, cover_surface=False) 画(后两个默认 True,不写会闭合覆面)(非模型线求解后补画也不作废解;不加这个参数画的是模型线,求解后画会让解作废、COM 不报错);线要避开馈电点 |
| 腔体/滤波器/DRA,要谐振频率与 Q | flow/eigenmode.md |
design 必须建成 Eigenmode 类型,不要端口;Q=0 是无耗不是出错 |
| 无限阵 / FSS / 超表面单元 | flow/periodic.md |
不要 create_open_region,那是孤立天线的边界 |
| 阵列复制、改网格、建螺旋 | flow/geometry-advanced.md |
切 sheet 只能用 split,solid 去 subtract 会把 sheet 一起删掉 |
| 板厂叠层表还原多层板 | 转 hfss-stackup skill |
读错一条行业约定,整板厚度就错 |
| 要找文献 / 卡片库没有匹配拓扑 | 转 hfss-search skill |
先查本地库,别一上来就联网 |
第三列是各卡里最常被违反的那一条,放这儿是因为:路由表一定在上下文里,卡不一定。 但它只够让你知道"有这么回事",不能替代读卡 —— 每条背后的判据、代价、例外都在卡里。
收工同样要回 flow/capture-learning.md —— 把这次的坑记进
knowledge/、把验证过的设计录成 design/ 卡片。这是整套系统复利增长的机制,跳过它
每次复现都从零踩坑。
What ships with it
27 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.
- design/_TEMPLATE.md 2.4 KB
- design/INDEX.md 2.1 KB
- design/magneto-electric-dipole.md 13 KB
- design/microstrip-patch.md 3.0 KB
- design/quadrifilar-helix.md 7.1 KB
- design/vivaldi-tapered-slot.md 8.1 KB
- flow/capture-learning.md 5.2 KB
- flow/design-loop.md 3.0 KB
- flow/diagnose-current.md 6.0 KB
- flow/eigenmode.md 2.1 KB
- flow/farfield.md 2.4 KB
- flow/feeding.md 1.4 KB
- flow/geometry-advanced.md 2.6 KB
- flow/periodic.md 1.2 KB
- flow/reproduce-paper.md 2.7 KB
- flow/s-parameters.md 6.6 KB
- flow/tuning.md 9.2 KB
- knowledge/_general.md 4.9 KB
- knowledge/_optimization.md 4.1 KB
- knowledge/_solving.md 9.3 KB
- knowledge/INDEX.md 2.9 KB
- knowledge/magneto-electric-dipole.md 24 KB
- knowledge/microstrip-patch.md 2.4 KB
- knowledge/phased-array.md 4.7 KB
- knowledge/quadrifilar-helix.md 16 KB
- knowledge/vivaldi-tapered-slot.md 3.2 KB
- papers/_HOWTO.md 2.8 KB
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.
- yesterday Changed 044bce013843
- 2d ago Changed · -237 lines 0d057e579824
- 5d ago Changed · +18 lines 86c49d88a803
- 6d ago Changed · +137 lines 7c17c7679e38
- 11d ago Changed · +13 lines 375fb9c5bab6
- 1mo ago Changed · +21 lines ce53dc219ad2
- 1mo ago First seen · 237 lines · 108 tokens per session scan A cc465a1291dd
hfss-design is a skill published in the GitHub repository K-13ROBOT/HFSS_MCP (8 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 5,615 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 2026-09-09.
Other skills, from other repositories
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
ruview-applications
Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…
lab-hardware-cad
Designs custom laboratory hardware as parametric build123d models and exports fabrication artifacts as STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a…
pylabrobot
Develops and reviews PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Supports PyLabRobot protocols and API questions; keep physical execution behind an explicit operator safety gate.
pybamm
Simulates lithium-ion battery charge, discharge and rest experiments with PyBaMM, records parameter-set provenance, checks mesh and solver sensitivity, and compares predicted voltage curves with measured cycling data. Use for SPM or DFN electrochemical battery modeling, C-rate protocols, voltage cutoffs, parameter…
calibrate-room
Run the ADR-151 per-room calibration pipeline — baseline → enroll → extract → train → a bank of small specialists (presence/posture/breathing/heartbeat/restlessness/anomaly).