Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Schematic Review

仅审查硬件电路原理图的电气合理性和需求符合性,按error、warning、suggestion列出有证据的问题、详细修改步骤和复验条件,生成简短前言的审查报告。用于首审、冻结前检查、改版 diff 和历史意见闭环;支持完整网表审查及明确受限的 PDF 审查。不执行 PCB/Gerber、布局布线、SCH-PCB 核对或生产准出审查。

Compatibility: Not stated.

Grade B

Minor issues only, no Medium or High. Worth a quick look at the findings below before installing.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

PERMISSION_SHELL_DECLARED OBFUSCATION_FILE_OVER_READ_CAP

Why this grade

  • PERMISSION_SHELL_DECLARED Note

    Runs shell commands, and the manifest or description says so.

    evals/circuit_bench/mutation_check.py, line 55 proc = subprocess.run(command, capture_output=True, text=True, timeout=90,

  • OBFUSCATION_FILE_OVER_READ_CAP Note

    A file was over the read cap and was not fully read.

    evals/circuit_bench/baselines/2aeaee5/results.json, line 1 {

Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.

Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.

What was checked

Plain notes from the hygiene checks.

  • Permissions

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    evals/circuit_bench/mutation_check.py, line 55

    proc = subprocess.run(command, capture_output=True, text=True, timeout=90,

    evals/circuit_bench/run.py, line 190

    result = subprocess.run(command, capture_output=True, text=True, timeout=args.timeout,

    evals/circuit_bench/run.py, line 204

    revision = subprocess.run(['git', '-C', str(args.sut), 'rev-parse', 'HEAD'],

    Show more

    evals/circuit_bench/spice_check.py, line 52

    version = subprocess.run([binary, '--version'], capture_output=True, text=True, timeout=10)

    evals/circuit_bench/spice_check.py, line 67

    proc = subprocess.run([binary, '-n', '-b', str(path)], capture_output=True,

    evals/circuit_bench/optimizations/2026-09-14-linear-feedback/independent/check_oracle_ngspice.py, line 51

    run = subprocess.run(['/opt/homebrew/bin/ngspice', '-b', str(deck)], text=True,

    scripts/parse_kicad.py, line 81

    done = subprocess.run(command, capture_output=True, text=True)

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Pass

    No network call found.

  • Secrets

    Pass

    No read of a credential file or secret environment variable found.

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Note

    a file was over the read cap and was not fully read.

    OBFUSCATION_FILE_OVER_READ_CAP

    evals/circuit_bench/baselines/2aeaee5/results.json, line 1

    {

    evals/circuit_bench/optimizations/2026-09-14-linear-feedback/results.json, line 1

    {

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Note

Hygiene check of commit a484106f8210. requests shell access. The manifest names this permission. a file was over the read cap and was not fully read.

Date and source

Date checked:

View source

github.com

Commit graded: a484106f82106869d008e8ee75b351b3aeca49f2

This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.

Read how this letter is chosen