tapeout-check

tapeout-check is a command for Claude Code from Midstall/claude-for-hardware. It costs 12 tokens per session (287 once invoked), scanned A, original, Apache-2.0.

A pre-submission check for an integrated-circuit design before tapeout, the point when a chip design is sent for manufacturing, or an MPW shuttle, a shared prototype run.

In plain words
What is it for?
Checking design-rule violations, confirming layout-versus-schematic matches, verifying density and fill, reviewing submission metadata and file formats, and giving a ready or not-ready verdict.
Why use it?
It catches signoff and packaging problems before submission and requires failures to be fixed instead of hidden or casually waived.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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

Good fit Checking design-rule violations, confirming layout-versus-schematic matches, verifying density and fill, reviewing submission metadata and file formats, and giving a ready or not-ready verdict.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/midstall/claude-for-hardware/tapeout-check
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.

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-check

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/midstall/claude-for-hardware/tapeout-check"><img src="https://agentmods.dev/badge/commands/midstall/claude-for-hardware/tapeout-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 287 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 $0.00012 $0.00287
Opus 5 $0.00006 $0.00143
Sonnet 5 $0.00002 $0.00057
Haiku 4.5 $0.00001 $0.00029

Measured 9d ago against content hash 08e87bc49df6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tapeout-check 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.

commands/tapeout-check.md · 18 lines

What it actually says

The user is preparing a design for tapeout or an MPW shuttle. Context: $ARGUMENTS

Invoke the tapeout-precheck skill (and silicon-grade-discipline for the failures-should-fail stance). Then walk the signoff gate honestly, in order:

  1. DRC: read the actual report and confirm zero unwaived violations. Do not infer clean from an absent error message or a run that skipped the rule deck.
  2. LVS: confirm the extracted netlist matches the source exactly, no shorts, opens, or unintended merges.
  3. Density and fill satisfied without introducing new violations.
  4. Submission package: top-cell name, layer map, metadata, and file format correct for this foundry or shuttle.

Enforce the hard rules: a failing check means fix the design, never disable the checker; never flatten and merge std-cell metal across cell boundaries; a legitimate waiver is foundry-granted in writing, not a flag flipped to hit a date.

If the user is asking whether they can suppress or wave a violation, the answer is to fix the design unless they have a written foundry waiver. Give a clear ready / not-ready verdict with blocking items and their design-side fixes.

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. 9d ago First seen · 18 lines · 12 tokens per session scan A 08e87bc49df6

Subscribe to this mod's changes

tapeout-check is a command published in the GitHub repository Midstall/claude-for-hardware (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 287 once invoked, about $0.0001 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.