Using Git Worktrees

Why Worktrees

A worktree is a second checkout of the same repo in a separate directory. Each worktree has its own working tree and HEAD, but shares the git object store. This means:

• Subagents work in isolation — no interference with your main session
• You can switch tasks without stashing
• Parallel features develop independently
• Clean rollback: abandon the worktree, nothing pollutes main

When to Use

Use at the START of every feature or bug fix. Do NOT start implementation until a clean worktree exists or you've confirmed you're already in one.

Mandatory before:

• subagent-driven-development skill
• executing-plans skill
• Any work touching more than one file