No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by khendzel · MCP Server · ★ 122
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is skills-janitor safe to install? View the security audit →
Skills Janitor Audit, track usage, and manage your AI coding skills - 7 focused skills, zero dependencies. Works with Claude Code and OpenAI Codex. A plugin that keeps your skills ecosystem clean, organized, and healthy. Automatically detects and scans skills from both Claude Code () and OpenAI Codex (). What's New in v1.1 Cross-platform - works with both Claude Code and OpenAI Codex Pre-install overlap check - check if a new skill duplicates existing ones before installing Context window token cost - see how many tokens each skill consumes and find unused waste Consolidated from 9 to 7 commands - fewer commands, same coverage Skills Install Plugin install (recommended): Or clone directly: bash git clone
| Stars | 122 |
| Forks | 19 |
| Language | Shell |
| Category | MCP Server |
| License | MIT |
| Quality Score | 72.7527323199039/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-30 |
| Created | 2026-03-23 |
| Platforms | claude-code, cli, codex, mcp |
| Est. Tokens | ~12k |
Looking for a skills-janitor alternative? If you're comparing skills-janitor with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Universal CLI for Agent Skills. Access 40,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitH
Claude Code Skills Marketplace: plugins, skills for ADR-driven development, DevOps automation, ClickHouse mana
Help your AI agent finish the job: solve the right problem, keep changes focused, and show what was verified.
Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP
🎯 The definitive collection of 50+ verified Awesome Claude Skills for Claude Code, Claude.ai, and API. Boost
🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity.
Explore other popular mcp server tools:
skills-janitor is Tinder for your Claude Code skills, subagents and MCP servers. Swipe away what wastes context, scan for prompt injection, get honest token costs. Fixes what it finds and actually deletes. Zero depende. It is categorized as a MCP Server with 122 GitHub stars.
skills-janitor is primarily written in Shell. It covers topics such as agent-skills, ai-agents, claude.
You can find installation instructions and usage details in the skills-janitor GitHub repository at github.com/khendzel/skills-janitor. The project has 122 stars and 19 forks, indicating an active community.
skills-janitor is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to skills-janitor on Agent Skills Hub include agent-skills-cli, cc-skills, claude-code-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: