Hand off your Claude Code setup between devices — sync ~/.claude/ across machines, driven by slash commands.
Why
If you use Claude Code on more than one machine — say a home Mac and a work Mac — moving hooks, skills, and agents between them is surprisingly painful. Copying hooks.json across doesn't work: absolute paths like /Users/your-home-name/… don't exist on the other machine, so every hook breaks. Skills, agents, and rules all end up getting moved by hand.
claude-handoff automates the whole thing. Per-machine paths are rewritten to portable tokens so configs resolve correctly wherever you pull them, a scanner catches secrets (API keys, tokens) before anything leaves your device, and a shared hub repository keeps every machine's configs and push history in one place.
It all runs inside Claude Code through slash commands — no terminal juggling, no flags to memorize.
One-time terminal step (npm publish pending — see Installation):
git clone https://github.com/im-ian/claude-handoff.git && cd claude-handoff
npm install && npm run build && npm link
Then back in Claude Code:
/handoff-init # asks you a few questions, creates a PRIVATE GitHub hub repo
/handoff-push # snapshot ~/.claude/ to the hub
On another machine — after the same install + /handoff-init:
/handoff-pull # pick the source device, preview diff, apply
Every slash command drives prompts through AskUserQuestion (device pickers, secret-scan policy, install confirmations) — no interactive CLI hangs, no flags to memorize.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
