What is analog-hardmacro-gen?

A packaging step that turns a verified analog circuit block into files that digital chip-design tools can place and connect. It produces layout, timing, and simulation descriptions for that block.

Use it after post-layout simulation when an analog block must be integrated into a digital chip. It prepares the block for tools such as OpenROAD.

It removes the manual work of making an analog block understandable to digital place-and-route tools. It also checks that the required files and pin names agree and that timing is not left at zero.

analog-hardmacro-gen — Skill for Claude Code by vibeic

Install

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.

Clone the repo

git clone --depth 1 https://github.com/vibeic/vibe-ic

agentmods

npx agentmods add skills/vibeic/vibe-ic/analog-hardmacro-gen

Made for: Claude Code.

Or install vibe-ic, the plugin that ships this one along with the rest of its 70 skills, 8 commands, 8 agents, 2 hooks, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vibeic/vibe-ic/analog-hardmacro-gen/github.svg)](https://agentmods.dev/skills/vibeic/vibe-ic/analog-hardmacro-gen)

Your own site

<a href="https://agentmods.dev/skills/vibeic/vibe-ic/analog-hardmacro-gen"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/analog-hardmacro-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vibeic/vibe-ic/analog-hardmacro-gen"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/analog-hardmacro-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,126 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00069	$0.02126
Opus 5	$0.00034	$0.01063
Sonnet 5	$0.00014	$0.00425
Haiku 4.5	$0.00007	$0.00213

Measured 7d ago against content hash c39bb7987758, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

analog-hardmacro-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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/test_compliance.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

vibe-ic-marketplace/plugins/vibe-ic/skills/analog-hardmacro-gen/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analog Hardmacro Gen

Takes a verified analog block (SPICE corner sweep passed, optionally hardware-verified) and produces the four deliverables that digital PnR (OpenROAD) needs to integrate it alongside standard cells.

When to use

Step A7 of the analog track
After analog-extraction-resim confirms post-layout specs are acceptable
When the user says "package this analog block for digital integration"

Inputs

analog/<block>/corner_results.json — worst-case timing from SPICE
analog/<block>/layout.mag — Magic layout (or generate via eda_analog_layout)
analog/<block>/spec.json — port definitions
PDK (gf180 or sky130)

Four deliverables

Deliverable PRESENCE + non-degeneracy is enforced deterministically: programs/analog_hardmacro_check.py (all 4 files exist; LEF has MACRO/PIN, LIB has cell, V has module) and programs/analog_liberty_nonzero_delay_check.py (the "no zero-delay Liberty" rule — area-only / all-zero .lib => FAIL; a propagation arc slower than the design's declared SDC/L8 clock period => FAIL). Cross-file pin-name equality is enforced by programs/analog_hardmacro_pinname_consistency_check.py.

1. GDS (`hardmacro/<block>/<block>.gds`)

NOT YOUR JOB — a program does this. programs/analog_hardmacro_gds_emit.py streams phase3/analog/<block>/layout.mag out to phase3/analog/hardmacro/<block>/<block>.gds with Magic, against the technology the layout's own tech line names. analog_one_shot_runner invokes it at A8_hardmacro_gen, before the A8 checks. It is deliberately NOT wired into A8's flow gate: flow_compliance_check is the acceptance auditor, and an auditor that writes a declared required_output into the project it audits certifies its own output. Do not hand-author a .gds.
Its TCL is magic_port_extract_emit.build_gds_write_tcl — the same fixed load / select top cell / gds write template the extraction path uses. Between v0.1.114 and 2026-07 that emitter had no caller at all, which is why A8 declared a layout no run produced.
Honest contract: rc=2 when no container/Magic/magicrc for that technology is reachable, rc=1 when Magic runs and the result carries no geometry (the hollow file is deleted, never left where a presence check would count it), and a deterministic-stub layout.mag is skipped so the PASS_WITH_STUB tier is untouched.
If the block has no layout.mag yet, run eda_analog_layout (A5) first — the producer names that as its skip reason rather than inventing geometry.

Read the full file on GitHub · 160 lines

Files

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.

Changes

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.

7d ago Changed · +14 lines c39bb7987758
11d ago First seen · 146 lines · 69 tokens per session scan A a960494ea017

Subscribe to this mod's changes

analog-hardmacro-gen is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 2,126 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.

Hardware and IoT ai-agents asic claude eda ic-design mcp

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…

Arcadia-1/analog-agents · 291 tokens

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.

Arcadia-1/analog-agents · 41 tokens

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.

Arcadia-1/analog-agents · 38 tokens

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…

Arcadia-1/analog-agents · 94 tokens

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"…

Arcadia-1/analog-agents · 92 tokens

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.

Arcadia-1/analog-agents · 49 tokens