Skill Cleaner
Audit agent skills: loaded roots, duplicate skills, unused skills, prompt-budget costs, compact descriptions.
Install
$ agentstack add skill-jesse-merhi-skills-skill-cleaner ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-jesse-merhi-skills-skill-cleaner) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Skill Cleaner
Use this when trimming skill prompt budget, finding duplicate skills, auditing enabled/disabled skill roots, or deciding which skills/plugins to remove.
Workflow
- Run the analyzer from this skill directory or repo root:
``bash npx --yes tsx@4.22.4 skills/skill-cleaner/scripts/skill-cleaner.ts --months 3 ``
- Use [commands.md](references/commands.md) for useful variants.
- Read the report in the order described by
[report-guide.md](references/report-guide.md).
- Before deleting or editing, apply the safety checks in
[cleanup-policy.md](references/cleanup-policy.md).
- Use [analyzer-notes.md](references/analyzer-notes.md) when interpreting
budget, root, duplicate, and usage heuristics.
Required Discipline
- Suggest first; edit only when the user asks.
- Verify the kept copy exists and is loaded before deleting duplicates.
- Preserve trigger nouns in descriptions: product, tool, action, object.
- Do not delete ignored/untracked skill dirs without naming the destination or
confirming they are disposable.
Context Pointers
- Use [commands.md](references/commands.md) for analyzer command variants.
- Use [report-guide.md](references/report-guide.md) for report reading order.
- Use [analyzer-notes.md](references/analyzer-notes.md) for how the script models
Codex skill budget and usage.
- Use [cleanup-policy.md](references/cleanup-policy.md) before applying cleanup.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jesse-merhi
- Source: jesse-merhi/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.