Claude Code, Skill
mentor
Self-improving orchestration and evaluation engine.
Compatibility: Not stated.
Grade B
Minor issues only, no Medium or High. Worth a quick look at the findings below before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
SECRETS_PATH_DOTENV PERMISSION_SHELL_DECLARED
Why this grade
- SECRETS_PATH_DOTENV Low
Mentions a .env file.
.gitignore, line 7
.env - PERMISSION_SHELL_DECLARED Note
Runs shell commands, and the manifest or description says so.
scripts/project_router.py, line 106
r = subprocess.run(["hermes", "-p", PROFILE, "kanban", "create", title, "--assignee", PROFILE,
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
scripts/project_router.py, line 106
r = subprocess.run(["hermes", "-p", PROFILE, "kanban", "create", title, "--assignee", PROFILE,
references/cron-mode-constraints.md, line 23
**Sandbox file discovery failure:** In the cron sandbox, Python's `subprocess.run(["find", ...])` and `os.walk()` silently return 0 results even when the filesystem is fully access
references/dual-path-journal-discovery.md, line 60
## Why Not os.walk or subprocess.run?
Show more
references/dual-path-journal-discovery.md, line 62
In cron-triggered `terminal()` heredocs, Python's `os.walk()` and `subprocess.run(["find", ...])` silently return 0 results even when the filesystem is fully accessible via shell t
references/gotchas-mentor.md, line 78
17. **`os.walk` on journals directory is unreliable at scale** - With 5000+ journal files across 100+ skill dirs, `os.walk` can silently produce wrong counts or hit timeouts. Use `
references/gotchas-mentor.md, line 297
54. **`os.environ.get()` in single-quoted Python heredocs returns 0/empty for unexported shell vars** - When the backup workflow writes evidence via `python3 << 'PYEOF'` and uses `
references/heartbeat-scan-technique.md, line 15
result = subprocess.run(
references/shell-write-pattern.md, line 49
total_3d = int(subprocess.check_output(['wc', '-l', '/tmp/mentor_files_3d.txt']).split()[0])
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_DOTENV
.gitignore, line 6
*.egg-info/
.gitignore, line 7
.env
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.
Note
Hygiene check of commit 9c9fabbb995e. requests shell access. The manifest names this permission. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 9c9fabbb995ee9108369908fd2be0fe56c802c69
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.