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 Abinesh-L · Claude Skill · ★ 83
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-crusts safe to install? View the security audit →
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. ╔════════════════════════════════════════════════════════════════╗ ║ CRUSTS Context Window Analysis ║ ║ Session: a1b2c3d4 | Model: claude-sonnet-4-6 ║ ║ Messages: 426 ║ ╠════════════════════════════════════════════════════════════════╣ ║ ║ ║ C Conversation 7,616 tkns (5.3%) █░░░░░░░░░░░░░░░░ ║ ║ R Retrieved 35,996 tkns (25.1%) ████░░░░░░░░░░░░░ ║ ║ U User Input 4,217 tkns (2.9%) █░░░░░░░░░░░░░░░░ ║ ║ S System 7,319 tkns (5.1%) █░░░░░░░░░░░░░░░░ ║ ║ T Tools 86,460 tkns (60.3%) ██████████░░░░░░░ ║ ║ S State/Memory 1,899 tkns (1.3%) █░░░░░░░░░░░░░░░░ ║ ║ ──────────────────────────────────────────────────────────────║ ║ TOTAL: 143,507 / 200,000 tokens (71.8%) ║ ║ FREE: 56,493 tokens ║ ║ ║ ║ WASTE DETECTED: ║ ║ "index.ts" read 9 times -- est. 9,897 tokens ║ ║ "types.ts" read 6 times -- est. 5,972 tokens ║ ║ .
| Stars | 83 |
| Forks | 23 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70.681672677711/100 |
| Last Updated | 2026-04-24 |
| Created | 2026-04-01 |
| Platforms | claude-code, cli, node |
| Est. Tokens | ~37k |
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.
Automatic context preservation for Claude Code. Never lose work to compaction again. 7 hooks, 187 semantic pat
Sync MCP servers, Skills, Agents & Commands across Claude Code, Cursor, OpenCode, Codex. One config, all tools
Config-driven CLI tool that compresses command output before it reaches an LLM context
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
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:
claude-crusts is Analyze your Claude Code context window, detect wasted tokens, and get pasteable fix commands. Zero API calls. It is categorized as a Claude Skill with 83 GitHub stars.
claude-crusts is primarily written in TypeScript. It covers topics such as claude-code, cli, context-engineering.
You can find installation instructions and usage details in the claude-crusts GitHub repository at github.com/Abinesh-L/claude-crusts. The project has 83 stars and 23 forks, indicating an active community.
claude-crusts is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to claude-crusts on Agent Skills Hub include c0ntextKeeper, vsync, tokf. 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: