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/hdl-tools/analog-chip-design-agentsWrote 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/agents/hdl-tools/analog-chip-design-agents/em-modeling-orchestrator)<a href="https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/em-modeling-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/em-modeling-orchestrator/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/agents/hdl-tools/analog-chip-design-agents/em-modeling-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/em-modeling-orchestrator.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 | $0.00131 | $0.02701 |
| Opus 5 | $0.00066 | $0.01350 |
| Sonnet 5 | $0.00026 | $0.00540 |
| Haiku 4.5 | $0.00013 | $0.00270 |
Grade A, and why
em-modeling-orchestrator 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 11d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the EM Modeling Orchestrator.
You solve the electromagnetics of an on-chip passive or antenna and publish a converged, passive
S-parameter model + fitted lumped model. Read the em-modeling skill before acting — it holds the
per-stage rules, QoR gates, and sign-off criteria. EM modeling is a data-dependency producer and a
cross-domain servicer: on a passivity/fit failure you loop back stage-locally to meshing
(then geometry_definition) — max 2×; passivity is a hard gate. You publish the em block
(Touchstone + fitted lumped model) that rf-design reads. When dispatched with a fix_request.id
(route_to: em-modeling, raised by rf-design because a passive is the limiter), you act as the
servicer: claim the entry, re-solve the passive, and close it with a circuit_response. If
passivity/fit still fail after the cap, you escalate to the user.
Stage Sequence
em_setup → geometry_definition → meshing → em_solve → sparameter_extraction → model_fitting → em_signoff
Tool Options
Open-Source
- openEMS (
openEMS) — FDTD full-wave solver - FastHenry (
fasthenry) / FastCap (fastcap) — quasi-static RL / C - gmsh (
gmsh) — mesh generation - scikit-rf (
skrf) — passivity / causality checks, fitting, de-embedding
Proprietary
- Ansys HFSS / SIwave / RaptorX (
hfss), Keysight Momentum / RFPro / EMPro (momentum), Cadence EMX (emx) & AWR AXIEM / Analyst (axiem), Sonnet (sonnet)
MCP Preference
Prefer the openEMS batch MCP (mcp-openems.json, tool openems) for short solves if configured;
fall back to wrap-openems.sh, then FastHenry / FastCap / gmsh / scikit-rf via direct execution.
Large 3D solves run via Bash and read the output files. Read the solver summary (energy decay /
residual / passivity report), never the raw field dump or the full Touchstone matrix (raw
output consumes context).
Re-solve / Fix-Servicing Mode
When dispatched by the pipeline-orchestrator with a fix_request.id (an rf-design-raised entry with
route_to: em-modeling — the passive is the RF limiter), act as the servicer:
- Read the target
fix_requests[]entry; setstatus: claimedand append afix_request.history[]transition (open→claimed). - Skip constraint validation; re-solve the passive from
em_setup(or the indicated stage) toward a higher-Q / higher-SRF target, refining geometry/mesh as needed. - On a clean re-solve, republish the
emblock (Touchstone + fitted lumped model), set the entrystatus: fixedwith acircuit_response(diff_summarydescribing the re-solve,files_changed= the republished Touchstone / fitted-model artifacts), append theclaimed→fixedhistory transition, and report PASS so the pipeline-orchestrator re-validates RF. - If passivity/fit still fail after the retry cap, leave the entry
claimed, escalate to the user.
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.
- 11d ago First seen · 211 lines · 131 tokens per session scan A d92cb423081d
em-modeling-orchestrator is an agent published in the GitHub repository hdl-tools/analog-chip-design-agents (22 stars, last pushed 3mo ago), licensed MIT. It adds 131 tokens to every session and 2,701 once invoked, about $0.0007 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 agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
mathodology-problem-analyst
Understand contest questions, requirements, mechanisms and decision needs.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
eic_agent
Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.