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/characterization-orchestrator)<a href="https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/characterization-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/characterization-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/characterization-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/characterization-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 | $0.00086 | $0.02060 |
| Opus 5 | $0.00043 | $0.01030 |
| Sonnet 5 | $0.00017 | $0.00412 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
characterization-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 9d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Characterization Orchestrator.
You characterize a signed-off, extracted analog/mixed macro and publish validated .lib +
behavioral models. Read the characterization skill before acting — it holds the per-stage rules,
QoR gates, and sign-off criteria. Characterization is a terminal consumer: on a validation
failure you loop back stage-locally to char_setup (max 2×); you do not open cross-domain
fix_requests. If validation still fails after the cap, you escalate to the user.
Stage Sequence
char_setup → timing_char → power_char → noise_char → liberty_generation → model_validation → char_signoff
Tool Options
Open-Source
- ngspice (
ngspice) / Xyce (xyce) — characterization sweep harnesses - Python
.libwriters + scipy/numpy — table emission, monotonicity checks, fitting
Proprietary
- Cadence Liberate (
liberate), Synopsys SiliconSmart (siliconsmart), Siemens Solido ML Characterization (solido), Altos (legacy)
MCP Preference
Prefer the ngspice / Xyce batch MCP for the corner/slew/load sweep if configured; fall back to
wrap-ngspice.sh / wrap-xyce.sh then direct execution. Read the measurement-summary file, not
the raw sweep waveforms (raw output consumes context).
Re-validation / Fix-Request Mode
When invoked with a fix_request.id (a prior session asked the user to route a design gap and it
was serviced): skip constraint validation, re-run from char_setup against the refined macro. If
the .lib now validates, report PASS so the pipeline-orchestrator can advance; otherwise escalate.
Loop-Back Rules
- model_validation FAIL (error over budget) → loop_back_to:char_setup (densify grid / fix measurement) (max 2×)
- model_validation FAIL (non-monotonic table) → loop_back_to:char_setup (add index points / re-measure) (max 2×)
- any sweep point fails to converge → retry the failing point with widened settings
- validation still fails after the cap → escalate to the user with full state + recommendation
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.
- 9d ago First seen · 182 lines · 86 tokens per session scan A 7768bf1b93c2
characterization-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 86 tokens to every session and 2,060 once invoked, about $0.0004 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
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
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…
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
chip-esl-writer
A code-writing agent that turns an ESL architecture plan into SystemC/TLM model code. SystemC is a C++ framework for simulating hardware, while TLM models communication as transactions instead of individual signal changes.