tapeout-precheck

tapeout-precheck is a skill for Claude Code from Midstall/claude-for-hardware. It costs 59 tokens per session (1,224 once invoked), scanned A, original, Apache-2.0.

A checklist for verifying chip layouts before sending them to a factory. It covers DRC, which checks whether the layout follows manufacturing rules, and LVS, which checks that it matches the circuit design.

In plain words
What is it for?
Use it when preparing GDS layout files for an MPW shuttle or full-mask submission, running final DRC/LVS checks, or reviewing metal layers, standard-cell rules, density, fill, and submission metadata.
Why use it?
It helps catch layout and connectivity mistakes before an expensive, hard-to-reverse manufacturing run. It also discourages ignoring verification failures just to meet a deadline.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-for-hardware plugin — 14 skills, 3 commands, 3 agents, 1 hook shipped together

Good fit Use it when preparing GDS layout files for an MPW shuttle or full-mask submission, running final DRC/LVS checks, or reviewing metal layers, standard-cell rules, density, fill, and submission metadata.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/midstall/claude-for-hardware/tapeout-precheck
Install

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.

Any agent
npx skills add Midstall/claude-for-hardware --skill tapeout-precheck
Clone the repo
git clone --depth 1 https://github.com/Midstall/claude-for-hardware

Made for: Claude Code.

Or install claude-for-hardware, the plugin that ships this one along with the rest of its 14 skills, 3 commands, 3 agents, 1 hook.

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.

agentmods badge for tapeout-precheck

README.md
[![agentmods](https://agentmods.dev/badge/skills/midstall/claude-for-hardware/tapeout-precheck/github.svg)](https://agentmods.dev/skills/midstall/claude-for-hardware/tapeout-precheck)
Your own site
<a href="https://agentmods.dev/skills/midstall/claude-for-hardware/tapeout-precheck"><img src="https://agentmods.dev/badge/skills/midstall/claude-for-hardware/tapeout-precheck/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.

agentmods 80×15 button for tapeout-precheck

Your own site · 80×15
<a href="https://agentmods.dev/skills/midstall/claude-for-hardware/tapeout-precheck"><img src="https://agentmods.dev/badge/skills/midstall/claude-for-hardware/tapeout-precheck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,224 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01224
Opus 5 $0.00030 $0.00612
Sonnet 5 $0.00012 $0.00245
Haiku 4.5 $0.00006 $0.00122

Measured 10d ago against content hash 0f70ba4ba088, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tapeout-precheck 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 10d 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.

skills/tapeout-precheck/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tapeout Precheck

Overview

Tapeout is irreversible and expensive. The precheck is the last gate where a tool, not a person, confirms the layout obeys the foundry rules and matches the schematic. The job is to pass that gate honestly, because the alternative is paying for a respin to learn what the checker already knew.

Core principle: A physical-verification failure is the design telling you it's wrong. Fix the design, never the checker. Every disabled rule is a defect you chose to ship.

When to Use

  • Preparing a GDS for an MPW shuttle or full-mask submission
  • Running DRC (design rule check) or LVS (layout vs schematic) signoff
  • Packaging the submission (GDS, top-cell name, layer map, fill, metadata)
  • Tempted to wave, downgrade, or disable a DRC/LVS violation to make a deadline

The Signoff Gate, In Order

  1. DRC clean. Geometry obeys the foundry rules (spacing, width, density, antenna, latchup). Zero unwaived violations.
  2. LVS clean. The extracted layout netlist matches the schematic/source netlist exactly: same devices, same connectivity, no shorts, no opens, no unintended merges.
  3. Density / fill. Metal density windows satisfied, fill added without creating new violations.
  4. Submission package. Correct top-cell name, layer mapping, and the foundry's required metadata and file format. A perfect GDS rejected for a wrong top-cell name is a wasted shuttle slot.

A precheck step may be a no-op for a given flow (some shuttles run DRC on their side), but treat it as a real gate: know which checks run where, and don't assume "no errors printed" means "checked."

Never Flatten Or Merge Std-Cell Metal

This is the rule that quietly destroys a chip:

Do not flatten standard cells and then merge their metal layers across cell boundaries. The std cells were verified as discrete cells with defined pins. Flatten-and-merge can short nets that the cell library kept apart and break the device-to-net correspondence LVS relies on. The result is an LVS mismatch at best, a silently shorted net at worst. Keep cells as instances; route between their pins. Let the router own inter-cell metal, not a flattening pass.

Read the full file on GitHub · 71 lines

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.

  1. 10d ago First seen · 71 lines · 59 tokens per session scan A 0f70ba4ba088

Subscribe to this mod's changes

tapeout-precheck is a skill published in the GitHub repository Midstall/claude-for-hardware (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,224 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.

Related

Other skills, from other repositories

lab-hardware-cad

Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…

K-Dense-AI/scientific-agent-skills · 106 tokens

opentrons-integration

Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow…

K-Dense-AI/scientific-agent-skills · 79 tokens

pylabrobot

Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.

K-Dense-AI/scientific-agent-skills · 49 tokens

embedded-systems

Use when developing firmware for microcontrollers, implementing RTOS applications, or optimizing power consumption. Invoke for STM32, ESP32, FreeRTOS, bare-metal, power optimization, real-time systems, configure peripherals, write interrupt handlers, implement DMA transfers, debug timing issues.

Jeffallan/claude-skills · 59 tokens

offensive-wifi

Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…

SnailSploit/Claude-Red · 183 tokens

offensive-lorawan-sub-ghz

LoRaWAN and sub-GHz (433 / 868 / 915 MHz) attack methodology — LoRaWAN ABP/OTAA join attack, network/session key reuse, frame counter replay, downlink injection on TTN/Helium-style networks, sub-GHz protocol replay (KeeLoq garage doors, fixed-code remotes, TPMS spoofing, smart plug telemetry), HackRF / RTL-SDR /…

SnailSploit/Claude-Red · 163 tokens