# collab-ai

> collab-ai — makarski-collab-ai. Use this tool when you need to facilitate local messaging between AI coding agents, such as Codex and Claude Code, to streamline collaborative coding processes. It solves problems of agent communication and integration by connecting them through a reliable broker and server infrastructure. The collab-ai tool accepts code-related inputs and outputs through Unix sockets and a SQLite database, ideal for use cases involving version control with git.

Canonical page: https://skillsregistry.net/skills/makarski-collab-ai  
JSON: https://api.skillsregistry.net/v1/skills/makarski-collab-ai

## Description

Local messaging for AI coding agents. Connect Codex and Claude Code through an MCP server, Unix sockets, and a SQLite-backed broker.

## Trust

- **Trust score (0–1):** 0.82
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/makarski/collab-ai)

## 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": "makarski-collab-ai"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/makarski-collab-ai` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/makarski-collab-ai/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