Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Claude Code Harness

A curated harness for Claude Code: 13 specialized agents, 16 skills, and a six-beat AGENTS.md workflow that takes a task from an isolated worktree to an evidence-backed pull request.

Compatibility: Not stated.

Grade C

One Medium finding. Read the report 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_UNDECLARED

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

    Runs shell commands that the manifest or description does not mention.

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 100 result = subprocess.run(

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

    Concern

    requests shell access. No manifest field names shell or command execution.

    PERMISSION_SHELL_UNDECLARED

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 100

    result = subprocess.run(

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 113

    result = subprocess.run(

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 164

    result = subprocess.run([tool], text=True, capture_output=True, check=False, timeout=5)

    Show more

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 475

    def spawn_detached(command: list[str], log_file: Any, env: dict[str, str]) -> subprocess.Popen[bytes]:

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 487

    return subprocess.Popen(command, **kwargs)

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 549

    result = subprocess.run(

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 659

    def stop_child_gracefully(child: subprocess.Popen[bytes], grace_seconds: float) -> None:

    .claude/skills/evidence-driven-testing/scripts/evidence.py, line 705

    child = subprocess.Popen(command, stdout=log_file, **kwargs)

  • Install and update

    Pass

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

  • Network

    Pass

    No network call found.

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_UNCONFIRMED

    .claude/skills/new-feature/SKILL.md, line 25

    - Keep the harness-assigned branch name. Make sure `.claude/worktrees/` is gitignored (this collection's `.gitignore` already does that). Put gitignored files that a worktree needs

  • Agent instructions

    Pass

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

  • Obfuscation

    Pass

    No encoded or minified payload found.

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Get the full report on this tool, £49

Note

Hygiene check of commit c3ada5e3b6ab. requests shell access. No manifest field names shell or command execution. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: c3ada5e3b6abdbcb606c5f274e0fad2d1e79e95f

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