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.
git 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/commands/k-13robot/hfss_mcp/hfss-model)<a href="https://agentmods.dev/commands/k-13robot/hfss_mcp/hfss-model"><img src="https://agentmods.dev/badge/commands/k-13robot/hfss_mcp/hfss-model/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/commands/k-13robot/hfss_mcp/hfss-model"><img src="https://agentmods.dev/badge/commands/k-13robot/hfss_mcp/hfss-model.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 | $0.00000 | $0.00800 |
| Opus 5.5 | $0.00000 | $0.00320 |
| Sonnet 5.5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
hfss-model 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.
What it actually says
HFSS 建模:把天线建出来并求解
读 ~/.claude/skills/hfss-design/SKILL.md —— 常驻约定(坐标层叠、sheet 规则、故障判定、卡住了怎么办),
然后按它的路由表判断这次属于哪种,去读对应的流程卡:
- 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 - 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-stackupskill ⚠️ 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-searchskill ⚠️ 先查本地库,别一上来就联网
一个任务读 3~4 份是正常的。拿不准读哪张就先读路由表本身。
⚠️ 任务性质中途变了就回路由表重查,别抱着一张卡走到黑。
最常见的转变:建完发现指标差得远 → 该转 /hfss-tune。
上面这份分支列表由
make_commands.py从SKILL.md的路由表生成,别手改 —— 改路由表后重跑脚本即可。
用户的要求:
$ARGUMENTS
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 ce6f80428a86
- 2d ago First seen · 42 lines · 0 tokens per session scan A dc6234a0ea61
hfss-model is a command published in the GitHub repository K-13ROBOT/HFSS_MCP (8 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 800 tokens. 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 2026-10-25.
Other commands, from other repositories
ruview-app
Run a RuView sensing application — presence, vitals, pose, sleep, environment mapping, MAT, point cloud, or a novel RF app.
rvcsi-nexmon
Nexmon CSI helpers — inspect a nexmoncsi .pcap, decode a Broadcom chanspec, or list the known Nexmon chips / Raspberry-Pi models.
kshana-fit-imu
Fit hybrid and fusion sensor parameters from a stationary IMU log via the kshana-mcp server.
hyperbolic-space
Install (if needed) and run the hyperbolic-space cog on the paired seed.
cross-validate-sensors
Byzantine-fault detection for the emissions network: cross-check each sensor against an independent reference and flag the ones that are lying before any of their data is trusted.
checklist
Generate a custom checklist for the current feature based on user requirements.