Using Git Worktrees

Overview

Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching.

Core principle: Systematic directory selection + safety verification = reliable isolation.

Announce at start: "I'm using the git-worktree skill to set up an isolated workspace."

When to Use

•Before executing implementation plans (/superspec:execute)
•When starting a new change that needs isolation
•When you need to work on multiple changes simultaneously

Directory Selection Process

Follow this priority order:

1. Check Existing Directories

bash

# Check in priority order
ls -d .worktrees 2>/dev/null     # Preferred (hidden)
ls -d worktrees 2>/dev/null      # Alternative

If found: Use that directory. If both exist, .worktrees wins.

2. Check Project Configuration

bash

grep -i "worktree.*director" CLAUDE.md 2>/dev/null
grep -i "worktree.*director" superspec/project.md 2>/dev/null

If preference specified: Use it without asking.

3. Ask User

If no directory exists and no preference:

code

No worktree directory found. Where should I create worktrees?

1. .worktrees/ (project-local, hidden) - Recommended
2. worktrees/ (project-local, visible)

Which would you prefer?

Safety Verification

For Project-Local Directories

MUST verify directory is ignored before creating worktree:

bash

# Check if directory is ignored
git check-ignore -q .worktrees 2>/dev/null || git check-ignore -q worktrees 2>/dev/null

If NOT ignored:

•Add to .gitignore
•Commit the change
•Proceed with worktree creation

Why critical: Prevents accidentally committing worktree contents to repository.

Creation Steps

1. Determine Change ID

Use the change ID from SuperSpec:

bash

change_id="add-2fa"  # From superspec/changes/[change-id]/

2. Create Worktree

bash

# Create worktree with new branch
git worktree add .worktrees/$change_id -b feature/$change_id

# Navigate to worktree
cd .worktrees/$change_id

3. Run Project Setup

Auto-detect and run appropriate setup:

bash

# Node.js
if [ -f package.json ]; then npm install; fi

# Rust
if [ -f Cargo.toml ]; then cargo build; fi

# Python
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
if [ -f pyproject.toml ]; then poetry install; fi

# Go
if [ -f go.mod ]; then go mod download; fi

4. Verify Clean Baseline

Run tests to ensure worktree starts clean:

bash

npm test / cargo test / pytest / go test ./...

If tests fail: Report failures, ask whether to proceed or investigate.

If tests pass: Report ready.

5. Report Location

code

Worktree ready at .worktrees/[change-id]
Branch: feature/[change-id]
Tests: Passing (N tests, 0 failures)

SuperSpec documents:
- Proposal: superspec/changes/[change-id]/proposal.md
- Design: superspec/changes/[change-id]/design.md
- Specs: superspec/changes/[change-id]/specs/

Ready to implement. Next: /superspec:execute

Quick Reference

Situation	Action
`.worktrees/` exists	Use it (verify ignored)
`worktrees/` exists	Use it (verify ignored)
Both exist	Use `.worktrees/`
Neither exists	Check config → Ask user
Directory not ignored	Add to .gitignore + commit
Tests fail during baseline	Report failures + ask

Common Mistakes

Skipping ignore verification

•Problem: Worktree contents get tracked, pollute git status
•Fix: Always use git check-ignore before creating project-local worktree

Proceeding with failing tests

•Problem: Can't distinguish new bugs from pre-existing issues
•Fix: Report failures, get explicit permission to proceed

Red Flags

Never:

•Create worktree without verifying it's ignored (project-local)
•Skip baseline test verification
•Proceed with failing tests without asking

Always:

•Follow directory priority: existing > config > ask
•Verify directory is ignored for project-local
•Auto-detect and run project setup
•Verify clean test baseline

Integration

Called by:

•plan-writing - After plan creation, before execution

Pairs with:

•finish-branch - Cleans up worktree after work complete
•subagent-development - Work happens in this worktree