A verification procedure for building and testing the universal-netlist program through its command-line and MCP interfaces. MCP is a standard way for programs to expose tools to other programs.

Use it to build the binary, run CLI commands, exchange JSON-RPC messages with the MCP interface, and exercise supplied design fixtures.

It checks the actual built binary and captures results, errors, and exit codes rather than relying only on source-level tests.

How IntelligentElectron/universal-netlist configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to IntelligentElectron/universal-netlist. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/IntelligentElectron/universal-netlist/main/.claude/skills/verify/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/IntelligentElectron/universal-netlist

Made for: Claude Code.

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/intelligentelectron/universal-netlist/verify/github.svg)](https://agentmods.dev/skills/intelligentelectron/universal-netlist/verify)

Your own site

<a href="https://agentmods.dev/skills/intelligentelectron/universal-netlist/verify"><img src="https://agentmods.dev/badge/skills/intelligentelectron/universal-netlist/verify/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/intelligentelectron/universal-netlist/verify"><img src="https://agentmods.dev/badge/skills/intelligentelectron/universal-netlist/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 498 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.00498
Opus 5.5	$0.00008	$0.00199
Sonnet 5.5	$0.00004	$0.00100
Haiku 4.5	$0.00002	$0.00050

Measured yesterday against content hash 95e0d331caad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify scanned grade A with 1 finding 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 yesterday.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

A short Python driver with `subprocess.Popen` and one JSON object per line works.

.claude/skills/verify/SKILL.md · 45 lines

What it actually says

Verify universal-netlist

Build a binary to drive

V=$(mktemp -d)
scripts/build-binary.sh host $V/universal-netlist packaged
codesign --force -s - --entitlements entitlements.plist $V/universal-netlist   # macOS: unsigned exits 137
$V/universal-netlist --version

Build the packaged channel. A github-channel binary self-updates when it starts serving MCP, which would replace the build under test with a release. Bun should match .bun-version; the script does not check it.

Surfaces

CLI: $V/universal-netlist <tool> <design> --flag value. Capture stdout, stderr and the exit code (0 result, 1 error field, 2 usage error).
MCP: run the binary with no arguments and speak JSON-RPC over stdio: initialize, notifications/initialized, then tools/list / tools/call. A short Python driver with subprocess.Popen and one JSON object per line works.

Fixtures worth driving

test/fixtures (submodule; npm run setup). Designs with named variants:

kicad/kicad-qa-variants/variants.kicad_pro: Variant 1, Variant2 (DNS differs: J1 / R14)
cadence/LAUNCHXL-CC1310/.../Cadence/LAUNCHXL-CC1310.DSN: Standard
altium/solarcar-bms/bms_mainboard-1_1.PrjPcb: a variant named 0
altium/fmc-dio-32chlvdsa/FMC_DIO_32ch_lvds_a.PrjPcb: VHDCI only (space)

universal-netlist list_designs --path test/fixtures/<format> lists each design's variants.

Gotchas

search_components_by_* refuses a pattern that matches every part (.*); use narrower patterns to cross-check a whole design.
Old Universal Netlist files: git show main:test/golden/<format>/<name>.netlist.json.

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.

yesterday First seen · 45 lines · 21 tokens per session scan A 95e0d331caad

Subscribe to this mod's changes

verify is a skill published in the GitHub repository IntelligentElectron/universal-netlist (56 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 498 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.

Testing altium cadence eda kicad mcp netlist

boardrepo

Read and review real PCB projects on BoardRepo. Search published hardware designs, open a board's schematic connectivity, bill of materials and files, run KiCad's DRC and ERC, and check a design against a fabrication house's limits. Use whenever the user names a BoardRepo board or URL, asks to find a published board…

flintt-dev/boardrepo-plugin · 156 tokens

autodesign

Drive an autonomous spec-to-board PCB design with the eda-agent MCP server (Altium Designer or EasyEDA Pro). Apply when the user asks to design a board/schematic from a requirement, wants an end-to-end autonomous design run, or mentions the design harness, designnextaction, design sessions, or spec-to-board. Requires…

salitronic/eda-agent · 100 tokens

field-agent-loop

Closed-loop field-agent that drives plugin quality improvements by running phase1/phase2/phase3 on benchmark IC projects, DRILLING each systematic gap to a fully-converged all-layers-resolved state in its OWN sandbox worktree, then handing the gatekeeper ONE complete verified bundle (candidate.patch + per-layer…

vibeic/vibe-ic · 211 tokens

loop2converge

The closed convergence loop for ANY benchmark subject — open-benchmark Evaluation, benchmark IC (doc→GDS), or IP-cell (doc→LEF/GDS). RUN the canonical front door, CLASSIFY every FAIL as flow / gate / tool, CONVERGE it by fixing the layer that owns it, PROVE the fix in the plugin cache against the real artefacts BEFORE…

vibeic/vibe-ic · 237 tokens

phase1-coverage-loop

Closed-loop field-agent for Phase 1 coverage. Rotates through a benchmark IC folder (e.g. 2ndbanchmark/) running /vibe-ic-phase1 on each IC's README/prompt, measures input→L1-L27 token completeness with phase1inputvsgeneratedcompletenesscheck, and files chip-AGNOSTIC plugin backlog issues for systematic ingester gaps.…

vibeic/vibe-ic · 150 tokens

testbench-gen

Generate a PROFESSIONAL, high-coverage testbench for a design directly from its Phase-1 L-docs — the Phase-2 'Simulation' step (canonical flow Step 4). Use whenever a design needs functional verification: derive the interface (L1/L9), clock/reset (L8/L9), a reference model, a scoreboard, functional coverage, and…

vibeic/vibe-ic · 185 tokens

universal-netlist: Skill for Claude Code