# crux

> crux — keradd-crux. Use this tool when you need to significantly reduce token usage in AI coding agents, such as Claude Code, Cursor, or Cline, to optimize performance and efficiency. The crux tool achieves 60-95% token reduction through its 11-layer compression runtime, utilizing a single Rust binary and SQLite database. Ideal for local-first development and git-based workflows, crux streamlines AI coding processes by minimizing token consumption.

Canonical page: https://skillsregistry.net/skills/keradd-crux  
JSON: https://api.skillsregistry.net/v1/skills/keradd-crux

## Description

Compression Runtime for Universal eXecution — a 60–95% token reducer for AI coding agents (Claude Code, Cursor, Cline, …). Single Rust binary, SQLite, 11 layers, local-first.

## Trust

- **Trust score (0–1):** 0.71
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/Keradd/crux)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "keradd-crux"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/keradd-crux` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/keradd-crux/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt