Using Worktrees

Using 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.

Scope

This skill covers git worktree setup, lifecycle, and known limitations for rageatc-code-oss workflows. It does NOT cover process-level isolation (Docker sandboxes), CI/CD pipeline isolation, or worktree usage outside of chunk-based development.

When to Use

• Standard/Thorough workflows: Each implementation chunk gets its own worktree for isolation
• Parallel chunks (Thorough only): Multiple worktrees enable simultaneous work on chunks with non-overlapping file sets
• Quick workflow: Optional — branch-based isolation may suffice for single small changes

Approach: Orchestrator-Managed Worktrees

The orchestrator creates and manages worktrees manually using git worktree add, then points developer-agents to the worktree directory.

Why manual, not automated: Claude Code's isolation: "worktree" option creates a fresh worktree per agent spawn with an opaque branch name. The manual approach keeps the lifecycle with the orchestrator — setup (baseline tests, .gitignore checks) runs in the worktree before the agent launches, review iterations reuse the same worktree across developer invocations, and branches are named after chunks. The Feb 2026 bugs that originally forced this choice were re-verified fixed on 2026-07-04; see Known Limitations.

Orchestrator:
  1. git worktree add <path> -b <branch>
  2. Run setup in worktree
  3. Launch developer-agent pointed at worktree path
  4. After review + accept: merge branch, remove worktree

Directory Selection

Follow this priority order:

1. Check Existing Directories

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 CLAUDE.md

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

If preference specified: Use it.

3. Ask User

If no directory exists and no CLAUDE.md preference:

No worktree directory found. Where should I create worktrees?

Recommended: .worktrees/ (project-local, hidden)

Safety Verification

Verify Directory is Ignored

MUST verify before creating any project-local worktree:

git check-ignore -q .worktrees 2>/dev/null

If NOT ignored:

1. Add .worktrees/ to .gitignore
2. Commit the change
3. Proceed with worktree creation

Why critical: Prevents accidentally committing worktree contents to repository.

Worktree Lifecycle

1. Create Worktree

# Name branch after chunk for traceability
git worktree add .worktrees/chunk-003 -b chunk-003/recipe-service

2. Run Project Setup

Auto-detect and run appropriate setup:

# 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

3. Verify Clean Baseline

Run tests to ensure worktree starts clean:

# Use project-appropriate command
npm test

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

If tests pass: Worktree is ready for the developer-agent.

4. Assign to Developer

Orchestrator launches developer-agent with the worktree path as the working directory.

5. After Review + Accept

# Merge the chunk branch back to main
git checkout main
git merge chunk-003/recipe-service

# Clean up
git worktree remove .worktrees/chunk-003
git branch -d chunk-003/recipe-service

6. After Review + Reject (iteration cap reached)

# Discard the worktree — main is untouched
git worktree remove --force .worktrees/chunk-003
git branch -D chunk-003/recipe-service

Known Limitations

Claude Code's isolation: "worktree" option, re-verified empirically 2026-07-04 (original reports Feb 2026, GitHub #29110):

• Fixed — subagent permissions: isolated agents now run bash, tests, and git commit without permission failures. (Original bug: permissionMode: "bypassPermissions" was ineffective.)
• Fixed — silent data loss: auto-cleanup removes only unchanged worktrees; a worktree with committed or uncommitted changes survives the agent's exit.
• Fixed — background composition: a background agent with worktree isolation runs in its worktree, not the main repository.
• Still true — branch naming: isolation generates opaque branch names (worktree-agent-{hash}); manual creation names branches after chunks.

Automated isolation is now viable for one-shot parallel tasks. This skill keeps the manual approach for chunk builds because the review loop needs an orchestrator-controlled lifecycle: pre-launch setup, one worktree shared across developer iterations, and chunk-named branches.

When to Use Worktrees vs Branches

Red Flags

Never:

• Create worktree without verifying it's gitignored (project-local)
• Skip baseline test verification
• Use isolation: "worktree" with permissionMode: "bypassPermissions" (broken)
• Use isolation: "worktree" with background: true (ignored)
• Trust auto-cleanup — commit before exiting

Always:

• Follow directory priority: existing > CLAUDE.md > ask
• Name branches after chunks for traceability
• Verify clean test baseline before assigning to developer
• Merge to main only after review accepts