# squeez

> squeez — claudioemmanuel-squeez. Use this tool when you need to compress tokens for AI CLI hosts, solving problems of excessive code length and improving efficiency with up to 95% bash compression. It accepts code inputs and produces compressed outputs, with features like signature-mode and cross-call deduplication. Ideal for use with git and AI-powered coding tools like Claude Code, Copilot CLI, and Codex CLI.

Canonical page: https://skillsregistry.net/skills/claudioemmanuel-squeez  
JSON: https://api.skillsregistry.net/v1/skills/claudioemmanuel-squeez

## Description

Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi, Hermes). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-27

## Source

- **Source listing:** [GitHub](https://github.com/claudioemmanuel/squeez)

## 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": "claudioemmanuel-squeez"
    }
  }
}
```

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