by Abinesh-L · Claude Skill · ★ 82
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx claude-crusts analyze
npm install -g claude-crustsTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 82 |
| Forks | 23 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70/100 |
| Last Updated | 2026-10-25 |
| Created | 2026-04-01 |
| Platforms | claude-code, cli, node |
| Est. Tokens | ~22k |
CRUSTS — Context Window Analyzer for Claude Code See what's eating your tokens. CRUSTS breaks down your Claude Code context window into 6 categories, detects waste, and tells you exactly what to do about it.
Looking for a claude-crusts alternative? If you're comparing claude-crusts with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Sync MCP servers, Skills, Agents & Commands across Claude Code, Cursor, OpenCode, Codex. One config, all tools
Automatic context preservation for Claude Code. Never lose work to compaction again. 7 hooks, 187 semantic pat
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
Config-driven CLI tool that compresses command output before it reaches an LLM context
The Universal AI-Optimized Project Boilerplate. A Tiered Memory System (TMS) designed to maximize AI agent per
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: