Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeic/vibe-icnpx agentmods add skills/vibeic/vibe-ic/analog-netlist-genWrote 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/vibeic/vibe-ic/analog-netlist-gen)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/analog-netlist-gen"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/analog-netlist-gen/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/vibeic/vibe-ic/analog-netlist-gen"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/analog-netlist-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.01672 |
| Opus 5 | $0.00032 | $0.00836 |
| Sonnet 5 | $0.00013 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
analog-netlist-gen 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analog Netlist Gen
Translates the sizing table (from analog-sizing) and topology (from analog-topology-select) into a valid, simulatable SPICE netlist with proper PDK model includes, body connections, and measurement statements.
When to use
- Step A3 of the analog track
- After
analog-sizinghas produced a device table with W/L/Id values - When the user wants to convert hand analysis into a SPICE deck
Inputs
analog/<block>/topology.md— fromanalog-topology-selectanalog/<block>/sizing.md— fromanalog-sizing(device table with W, L, gm/Id, Id)analog/<block>/spec.json— fromanalog-spec-extract(specs for .meas statements)- PDK: gf180 or sky130
GF180 device instantiation (CRITICAL)
From analog-sizing/PRACTICAL_NOTES.md — verified working:
* Model include — ORDER MATTERS
.include /foss/pdks/gf180mcuD/libs.tech/ngspice/design.ngspice
.lib /foss/pdks/gf180mcuD/libs.tech/ngspice/sm141064.ngspice typical
* NMOS: drain gate source body
XM1 drain gate source 0 nfet_03v3 W=20u L=2u
* PMOS: drain gate source body — BODY MUST BE VDD
XMP1 drain gate source VDD pfet_03v3 W=20u L=4u
Body connection rules (NMOS body → VSS/0, PMOS body → VDD — the #1 SPICE
simulation failure): enforced deterministically by programs/analog_netlist_pdk_check.py
(PMOS_BODY_TO_VSS / NMOS_BODY_TO_VDD). Model-include presence is also enforced
there (NO_MODEL_INCLUDE).
SKY130 device instantiation
.lib /foss/pdks/sky130A/libs.tech/ngspice/sky130.lib.spice tt
* NMOS: drain gate source body
XM1 drain gate source 0 sky130_fd_pr__nfet_01v8 W=1u L=0.15u
* PMOS: drain gate source body
XMP1 drain gate source VDD sky130_fd_pr__pfet_01v8 W=2u L=0.15u
Workflow
- Read topology schematic → identify all devices and their connections.
KEEP-JUDGMENT: resolving a free-form/ASCII topology description into the
device-to-net connectivity graph is comprehension, not parsing — only an LLM can
do this reliably. (Once the graph exists,
analog_netlist_connectivity_check.pyverifies it has no floating nodes / unused ports.) - Read sizing table → get W, L for each device
- Generate subcircuit definition:
.subckt <block_name> <port_list> * Device instantiations .ends - Generate testbench:
- Power supply:
Vdd VDD 0 DC 3.3(GF180) orDC 1.8(SKY130). The supply value must match the PDK + device flavor — enforced byprograms/analog_tb_supply_pdk_check.py(SUPPLY_PDK_MISMATCH/SUPPLY_DEVICE_MISMATCH/DEVICE_FLAVOR_PDK_MISMATCH). - Stimulus: DC sweep, AC source, transient pulse — choosing the stimulus class and load network requires understanding the block's function (KEEP-JUDGMENT).
- Load: resistive/capacitive per spec
- Power supply:
- Generate
.measstatements from spec.json — deterministic; do not hand-author. Runprograms/analog_meas_from_spec_gen.py <block>/spec.json --out meas.inc. It classifies each spec key into DC / AC / TRAN and emits the templated.measlines (FAILs honestly if spec.json is missing or has no measurable keys). - Add
.controlblock for ngspice batch mode
What ships with it
2 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.
- 11d ago First seen · 149 lines · 65 tokens per session scan A ea945bacff8c
analog-netlist-gen is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 1,672 once invoked, about $0.0003 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 skills, from other repositories
analog-netlist-crawl
Crawl and analyze post-layout parasitic netlists without running SPICE. Answers "what's the effective resistance from node A to node B across this massive R mesh?", "inside the VREFN mesh, which device pins are electrically farthest apart?", "which nets have the worst coupling?", "where does settling bottleneck?" — by…
spice
Run automatic SPICE simulations on subcircuits detected from KiCad schematic analysis — validates filter frequencies, divider ratios, opamp gains, LC resonance, and crystal load capacitance. Supports ngspice, LTspice, and Xyce (auto-detected). Generates testbenches, runs batch mode, produces structured pass/warn/fail…
analog-verify
Pre-simulation review and Spectre simulation verification for analog circuits. Reviews circuit netlist and testbench, runs simulation, produces margin report. Use after analog-design completes a netlist.
analog-design
Transistor-level circuit design for one analog sub-block. Produces Spectre netlist with hand-calculation rationale. Use when designing a specific circuit block after architecture is defined.
analog-pipeline
MANDATORY — MUST load this skill when the user mentions: OTA, ADC, PLL, comparator, bandgap, LDO, amplifier, opamp, or any analog/mixed-signal IC design task. Full analog design pipeline: spec -> architecture -> design -> verify -> deliver. Orchestrates analog-decompose, analog-behavioral, analog-design…
analog-audit
Audit analog circuit netlists for correctness, quality, and risks. Supports both pre-layout (schematic) and post-layout (extracted) netlists. Post-layout mode filters massive parasitic netlists before auditing. Works without EDA. TRIGGER on: "audit", "review netlist", "check this circuit", "design review"…