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 | $0.07987 |
| Opus 5 | $0.00054 | $0.03993 |
| Sonnet 5 | $0.00022 | $0.01597 |
| Haiku 4.5 | $0.00011 | $0.00799 |
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 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 — 237 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。
0. 复现文献时:先解析结构图(建模前必做,治"建歪"的根)
论文几何靠图 + 参数表 + 正文三者共同确定。建歪的两大来源要分开治:尺寸数字错 vs 拓扑/连接错。
核心分工(最重要,违反必建歪):
- 所有尺寸数字 → 只从参数表 / 正文抽,绝不在图上"量"。复杂结构图引线密、3D 透视失真,在图上估尺寸必错;而精确值几乎总在 Table 或正文里(文字,可靠)。图上读出来的数和表里对不上,以表为准。
- 图 → 只用来判拓扑:谁连谁、谁压谁上、折叠往哪折、馈线走向、缝隙开在哪层、对称性。图不负责给数字,只负责给"结构怎么搭"。
流程:
- 定位:参数表(尺寸全在这)、结构图/俯视/侧视、截面图(看层叠 z 最关键)、正文里补充的尺寸(如"间距 1mm""gap 5.4mm")。
- 先确认图真进了模型:用
Read打开 PDF 对应页(会渲染成图)。如果你描述不出图里的具体视觉细节(线条走向、谁搭谁),说明图没真进来(可能只喂了文字层)→ 立刻让用户把那张结构图单独裁成高清图发你,或用文字描述拓扑,别硬猜。 - 数字:把参数表 + 正文里每个尺寸抄成变量(论文符号→变量名→值带单位;注意单位 mm/mil、注意 λ 值要换算成 mm)。一个都别从图上量。
- 拓扑(从图判):拓扑类型、层叠(几层/材料/谁上谁下/各层 z)、馈电方式与精确位置、各层对齐与对称面、折叠/拐角朝向。
- 拓扑有任何歧义就停下确认——复杂结构(折叠片、多层、3D 透视)你从图反推很容易错。先输出一张"结构理解表 + 层叠表"(每层/每个金属件:对象名 / 材料 / z 范围 / xy 范围 / 连到谁 + 馈电怎么接),用文字把你理解的结构讲清楚,让用户确认或纠正后再建。用户瞄一眼图就知道你哪折反了,比你自己反推可靠得多。
- 确认后才进 §3.5 坐标约定建模;建中拿不准(标注指向不清、符号对不上)→ 问用户,别猜着建。
越复杂的结构(折叠、多层、阵列、3D 馈电),越要把"读图"这步交给用户兜底:数字你从表抽、坐标你算、工具你调,但"结构长什么样"先让用户拍板。这是治这类建歪最稳的办法。
0.2 经验库:每类天线难点沉淀(开工先读、收工先记)
天线种类多、各有各的坑。本 skill 旁边有个 knowledge/ 目录(与本 SKILL.md 同级),按天线类型积累"难点 / 坑 / 解法"。目的是让每次复现都站在过往经验上,坑只踩一次——这是 AI 的自我学习机制,越往后 knowledge/ 越厚、复现越稳。
开工先读(解析结构 + 规划之前):
- 认出这次是哪类天线(贴片 / 磁电偶极 / 缝隙耦合 / 偶极单极 / 阵列 …)。
- 读
knowledge/INDEX.md找匹配条目 → 读对应knowledge/<type>.md和knowledge/_general.md,把里面已知的难点纳入这次的结构理解与规划。 - 没有匹配类型文件 = 这类第一次做,正常,照常进行,结束时新建该类型文件。
收工先记(复杂任务做完、或中途卡过壳/绕过坑之后):
- 把这次遇到的、非显然且跨任务可复用的难点,追加进对应
knowledge/<type>.md(没有该文件就新建,并在INDEX.md加一行指针)。 - 一条经验的格式(简洁,一条一个坑):
## <一句话标题> - 现象:踩坑时看到什么(报错/建歪/不收敛…) - 原因:为什么 - 解法:正确做法 / 怎么绕过 - 适用:(可选)什么条件下成立 - 追加前先扫一眼该文件有没有类似条目:有就补充/更新,别堆重复。
- 质量门槛——记"这类天线通用的,不记某一款的具体长相"(最重要):
- 判据:写下来的东西换一篇同类但结构不同的论文还用得上,才值得记。同一种天线结构千变万化,具体构造和尺寸是"数据"不是"经验"。
- ✅ 记:该类天线的物理本质/工作机理、通用建模陷阱、哪个设计自由度控什么(控谐振 / 控匹配 / 控带宽 / 控方向图)、馈电与层叠的套路性做法、收敛与匹配经验、文献符号易混点。
- ❌ 不记:某一款的具体结构与尺寸(L1=1.8、这篇的铜带怎么折…)、一次性手误、工具已知 bug(那进代码/CLAUDE.md)、某篇论文的具体数值(那是数据)。
What ships with it
9 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.
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 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 (5 stars, last pushed 4d ago), licensed MIT. It adds 108 tokens to every session and 7,987 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 2026-09-09.
Other skills, from other repositories
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
ruview-advanced-sensing
Advanced RuView capabilities — RuvSense multistatic sensing (attention-weighted fusion, geometric diversity, persistent field model), cross-viewpoint fusion across multiple nodes, RF tomography (ISTA L1 solver, voxel grids), longitudinal biomechanics drift, pre-movement intention signals, adversarial signal detection…
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
Design custom laboratory hardware as parametric build123d models and export fabrication-ready 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 research…
opentrons-integration
Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow…
pylabrobot
Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.