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-spec-extractWrote 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-spec-extract)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/analog-spec-extract"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/analog-spec-extract/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-spec-extract"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/analog-spec-extract.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 | $0.00055 | $0.01976 |
| Opus 5 | $0.00028 | $0.00988 |
| Sonnet 5 | $0.00011 | $0.00395 |
| Haiku 4.5 | $0.00006 | $0.00198 |
Grade A, and why
analog-spec-extract 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 12d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analog Spec Extract
Reads L1_DATASHEET.json (pin types, electrical specs) and L5_ADI_SPEC.json (analog-digital interface) to enumerate every analog block that needs transistor-level design, and produces a machine-readable spec.json for each.
⛔ HARD RULE — never silently emit empty block list (Wave 47, v0.120.1)
User directive (Wave 47): "EVERY ITEM IN DESIGN DOCUMENTS SHOULD BE IMPLEMENTED!!!! EVERY!!!"
The deterministic parts of this hard rule are now programs — run them, don't re-implement them in prose:
- 8-class analog keyword scan + L5-mapping — enforced by
programs/analog_content_detected_must_emit_l5_check.py(the chip-AGNOSTIC grep overinput_doc/*.txt+input/docs/*.txtfor oscillator / ldo / bandgap / por / pull / esd / charge_pump / trim, with per-hit negation awareness, lives there). For each detected class emit at least one minimalanalog_blocks[]entry:
then run the gate against{"name": "<descriptive>", "type": "<class>", "spec": "<one-line>", "evidence": "<file>:<line>", "implementation_status": "needs_design_work"}<project_dir>. - Forbidden
analog/A0_skip_decision.jsontop-level skip — enforced byprograms/analog_a0_skip_forbidden_check.py. Replace any skip withanalog/A0_implementation_status.json(per-block A1-A8 status) OR setL5.analog_blocks_detected=falsewhen the keyword scan PASSes empty.
A1 (this skill) PASS criterion is keyword-grep cleanliness, not human judgment that "the chip looks digital".
Residual LLM judgment (not a program): the keyword scan is a recall floor, not a complete detector — recognising a NON-keyword analog block (a custom sensor-readout front-end described only functionally, with no token in the 8-class list) is exactly where your judgment is needed. Catch what the grep misses and add it to analog_blocks[] anyway.
Spurious-block flip-side (cross-ref → analog-topology-select, #466B): the recall floor
also OVER-fires. A candidate emitted only because a product-name keyword in L1 matched a
class — with no spec ever bound (spec == null) — is presumed spurious and must be
confirmed against the L5 type enumeration (the "N analog blocks" count sentence and/or the
Block A/B table headers) before A2 spends any sizing compute. Drop it if L5 doesn't
enumerate that class; keep + spec-bind it if L5 does. A block's multiplicity (×N) must
come from the block's OWN enumeration row, never a sibling block's evidence paragraph. The
full sanity procedure + why_not_bucket_a rationale lives in analog-topology-select's
"spurious-block sanity check" capture; do not re-implement it here as a deny-list — whether
a name-only block is real requires reading L5, not a static rule.
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.
- 12d ago First seen · 147 lines · 55 tokens per session scan A 33fafbf6a0f6
analog-spec-extract is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,976 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…
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"…
analog-decompose
Architect Phase 1: decompose top-level analog spec into sub-block specs. Use when starting a new analog design to select architecture, allocate budgets, define sub-block specs, write testbenches, and create verification plans.