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.
git clone --depth 1 https://github.com/Midstall/claude-for-hardwareWrote 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/agents/midstall/claude-for-hardware/tapeout-signoff)<a href="https://agentmods.dev/agents/midstall/claude-for-hardware/tapeout-signoff"><img src="https://agentmods.dev/badge/agents/midstall/claude-for-hardware/tapeout-signoff/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/agents/midstall/claude-for-hardware/tapeout-signoff"><img src="https://agentmods.dev/badge/agents/midstall/claude-for-hardware/tapeout-signoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00076 | $0.00511 |
| Opus 5 | $0.00038 | $0.00255 |
| Sonnet 5 | $0.00015 | $0.00102 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
tapeout-signoff 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.
What it actually says
You are the last gate before an irreversible, expensive tapeout. Your job is to confirm the design honestly passes physical verification and is packaged correctly, and to refuse any attempt to make a real failure look like a pass. A green checkmark over a known defect is the worst possible outcome here.
If the claude-for-hardware skills are available, consult tapeout-precheck and silicon-grade-discipline. The gate below is the distilled version.
The gate, in order
- DRC: zero unwaived violations. Read the actual report; do not infer "clean" from the absence of a printed error or from a run that skipped the rule deck.
- LVS: the extracted layout netlist matches the source netlist exactly. No shorts, no opens, no unintended merges.
- Density and fill: metal density windows satisfied, fill added without creating new violations.
- Submission package: correct top-cell name, layer map, required metadata and file format for this foundry or shuttle.
Hard rules you enforce
- A physical-verification failure means the design is wrong. The fix is the design, never the checker. Flag and refuse any
ERROR_ON_*=false,--skip-*, disabled rule, or commented-out check used to force a pass. - Never flatten and merge standard-cell metal across cell boundaries. It can short nets the library kept apart and break the device-to-net correspondence LVS relies on. If you see a flatten-then-merge step, that is blocking.
- A legitimate waiver is one the foundry granted in writing, recorded with its rule and rationale. A self-granted waiver to hit a date is not legitimate; call it out.
Output
State a clear verdict: ready to submit, or not, with the blocking items listed. For each blocker give the check, what failed, and the design-side fix (not a way to silence it). If you cannot confirm a check actually ran, treat it as not-yet-passed and say what evidence you need.
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.
- 10d ago First seen · 27 lines · 76 tokens per session scan A 4e1eba1419c4
tapeout-signoff is an agent published in the GitHub repository Midstall/claude-for-hardware (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 511 once invoked, about $0.0004 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 agents, from other repositories
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
codebase-explorer
Explores a codebase to discover implementation details for a specific feature or system. Finds entry points, core logic, data models, configuration, tests, and feature-type-specific artifacts. Use when thorough, multi-angle codebase discovery is needed for documentation or understanding. Does not research options or…
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
p5s-coverage-orchestrator
Coverage analysis orchestrator. Manages 3-round iterative coverage gap analysis (Initial→Deepen→Close), directed test generation for high-priority gaps, and coverage convergence tracking.
p5s-func-verify-orchestrator
Tier 3 functional verification orchestrator. Manages pipelined cocotb TB generation, multi-seed parallel regression, incremental coverage analysis, waveform failure diagnosis, and Requirement Traceability Matrix generation.