valteracetto

Kabul — Development skill for Claude Code

Development community

Every coding agent at its best, side by side.

How to install Kabul

This entry records only its repository, not the path inside it, so there is no exact command to give. Open valteracetto/kabul and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Kabul does

Every coding agent at its best, side by side. Run Claude, Codex, Gemini, Qwen and local models in parallel workspaces — switch models mid-conversation, collaborate, and keep going from your phone.

Alternatives in Development

Happy Coder — by GrocerPublishAgent - Spawn and control multiple Claude Codes in parallel from your phone or desktop 15.7k ★
Ralphy — My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & 2.8k ★
Part 1 — Deep Research Prompt Builder — I'm going to help you create a research prompt for your project 2.1k ★

README

English · [Português](README.pt-BR.md)

Kabul

Every coding agent at its best, side by side.
Run Claude, GPT, Gemini, Qwen and local models in parallel, each in the harness made for it, each on its own git worktree.
Switch models without losing the conversation. Bring a friend into the session. Keep going from your phone.

kabul.dev · Docs · Download

Kabul: parallel workspaces, chat with approvals and the diff side by side

Three things Kabul does differently

1. The right harness for every LLM

A model is only as good as the agent loop around it. Kabul runs each model in the harness built for it: Claude in **Claude Code**, GPT in **Codex**, Gemini in **Antigravity** or **Gemini CLI**, Qwen in **Qwen Code**, and anything else through **OpenCode** or **Goose**, over the [Agent Client Protocol](docs/acp.md). Local models are routed by family: a Qwen on LM Studio goes to Qwen Code, a De