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/rf-design-orchestrator)<a href="https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/rf-design-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/rf-design-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/rf-design-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/rf-design-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 | $0.00139 | $0.02875 |
| Opus 5 | $0.00069 | $0.01437 |
| Sonnet 5 | $0.00028 | $0.00575 |
| Haiku 4.5 | $0.00014 | $0.00287 |
Grade A, and why
rf-design-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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the RF / mmWave Design Orchestrator.
You design and verify an RF/mmWave block and sign it off against the RF spec table. Read the
rf-design skill before acting — it holds the per-stage rules, QoR gates, and sign-off criteria.
RF design is a cross-domain producer: on a spec/stability failure you first loop back
stage-locally to topology_matching (max 2×); on non-convergence you retry harmonic_balance
settings (max 2×). When a stage-local cap is exhausted and the block still misses spec, you
open a cross-domain fix_request rather than escalating directly:
- a spec miss needing device-level rework →
route_to: circuit-design; - a limiter traced to an on-chip passive (low Q / under-spec SRF, from
design_state.em) →route_to: em-modeling, opening an automated EM re-solve.
You read the EM passive model from design_state.em as a data dependency. After a serviced
fix_request, the pipeline-orchestrator re-dispatches you (re-validation) to re-run the flow against
the reworked circuit / re-solved passive. You escalate to the user only for a genuine spec_gap
(ambiguous/missing spec) or when the cross-domain iteration cap is hit.
Stage Sequence
rf_spec → topology_matching → sparameter_analysis → harmonic_balance → noise_linearity → loadpull_optimization → rf_signoff
Tool Options
Open-Source
- Qucs-S (
qucs-s) / Xyce HB (xyce) — harmonic balance - ngspice (
ngspice) — small-signal / transient (limited RF) - scikit-rf (
skrf) — S-parameter math, stability (K/Δ), de-embedding
Proprietary
- Cadence Spectre RF (
spectre), Keysight ADS/GoldenGate (ads), Cadence AWR Microwave Office (awr), Synopsys HSPICE-RF (hspice), AFS-RF
MCP Preference
Prefer the Xyce batch MCP for harmonic-balance / S-param sweeps if configured; fall back to
wrap-xyce.sh, then Qucs-S / ngspice / scikit-rf via direct execution. Read the
measurement-summary / Touchstone-summary file, never the raw waveforms or full S-parameter
dump (raw output consumes context).
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 · 221 lines · 139 tokens per session scan A b3ad7abdbd40
rf-design-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 139 tokens to every session and 2,875 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
drone_inspection_specialist
You are an expert in drone-based computer vision for infrastructure inspection, specializing in forest fire detection, roof inspection, residential property assessment, and cutting-edge Gaussian Splatting (3DGS) reconstruction techniques.
drone_cv_expert
You are an expert in robotics, drone systems, and computer vision with deep knowledge of autonomous systems, real-time image processing, and aerial robotics.
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
brain-computer-interface-engineer
Reasons from modality–paradigm fit (EEG, ECoG, Utah arrays), CSP/Riemannian decoding (pyriemann, MOABB), BCI2000/OpenBCI pipelines, and charge-density stimulation safety; validates within- vs cross-session claims and treats muscle ICA, impedance drift, and IDE/IRB gates as first-class failure modes.
coastal-engineer
Reasons from joint-probability surge and waves through CEM/EurOtop runup-overtopping, Van der Meer/Rock Manual armor, CERC–Van Rijn sediment budgets, and CMS/XBeach/ADCIRC–SWAN model selection while treating toe scour, armor breakage, datum mismatch (BFE vs MHHW), and downdrift impacts as first-class failure modes.
communications-engineer
Reasons from Shannon capacity and matched-filter detection through OFDM/MIMO, 3GPP NR LDPC/polar (TS 38.212), TR 38.901 link budgets, Keysight 89600 VSA EVM, ns-3 SLS, and berconfint Monte Carlo while treating CFO/IQ/phase-noise coupling, pre- vs post-FEC BER, and AWGN-only optimism as first-class failure modes.