Skip to main content
ClaudeWave
Skill282 repo starsupdated 3mo ago

worktree-lifecycle

The worktree-lifecycle skill manages the complete lifecycle of git worktrees for isolated feature development, including creation, setup, and cleanup with safety checks and error recovery. Use this skill when starting new features requiring isolated workspaces, executing risky experimental changes, coordinating parallel work across multiple agents, or following implementation plans that need clean environments while preserving existing work.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/MadAppGang/claude-code /tmp/worktree-lifecycle && cp -r /tmp/worktree-lifecycle/plugins/dev/skills/discipline/worktree-lifecycle ~/.claude/skills/worktree-lifecycle
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Worktree Lifecycle

**Purpose:** Manage git worktrees for isolated feature work with safety checks, multi-stack setup, and clean lifecycle management.

## When to Use

This skill applies whenever you:
- Start a new feature that requires isolated workspace
- Execute risky or experimental changes
- Need to keep current work untouched while testing alternatives
- Coordinate parallel agent work (each agent in separate worktree)
- Follow an implementation plan requiring clean environment
- Preserve long-running feature work across sessions

**Trigger keywords:** experiment, prototype, risky, breaking, parallel, isolate, worktree, workspace

## Red Flags (Anti-Patterns)

- [ ] Creating worktree without checking if branch already exists
- [ ] Creating worktree without checking if directory path is available
- [ ] Forgetting to add worktree directory to .gitignore
- [ ] Manually deleting worktree with `rm -rf` (use `git worktree remove`)
- [ ] Removing worktree with uncommitted changes without user confirmation
- [ ] Using same branch in multiple worktrees simultaneously
- [ ] Working in worktree after returning to main directory (stale CWD)
- [ ] Not storing original CWD before entering worktree
- [ ] Skipping dependency installation in new worktree
- [ ] Not running baseline tests before starting work

## 6-Phase Lifecycle

### Phase 1: Pre-flight Checks

**Purpose:** Verify all prerequisites before creating anything.

**Required checks** (all must pass):

```bash
# 1. Verify git repository
git rev-parse --git-dir &>/dev/null
if [ $? -ne 0 ]; then
  ERROR: "Not a git repository"
  RECOVERY: Abort with clear error message
fi

# 2. Detect detached HEAD state
if ! git symbolic-ref HEAD &>/dev/null; then
  WARNING: "Currently in detached HEAD state"
  RECOVERY: Ask user if they want to create branch from current commit
fi

# 3. Check if branch already in a worktree
if git worktree list | grep -q "$BRANCH"; then
  ERROR: "Branch $BRANCH already checked out in a worktree"
  RECOVERY: Ask user - reuse existing, rename branch, or cancel
fi

# 4. Check if branch exists (but not in worktree)
if git branch --list "$BRANCH" | grep -q .; then
  WARNING: "Branch $BRANCH already exists"
  RECOVERY: Ask user - use existing branch or create new with different name
fi

# 5. Check if target path is available
# IMPORTANT: Create directory first before checking (git check-ignore needs path to exist)
mkdir -p "$WORKTREE_DIR"
if [ -d "$WORKTREE_PATH" ]; then
  ERROR: "Directory $WORKTREE_PATH already exists"
  RECOVERY: Ask user - choose different path or remove existing
fi
```

**Error Recovery Table:**

| Error | Detection | Recovery |
|-------|-----------|----------|
| Not a git repo | `git rev-parse --git-dir` fails | Abort with clear error |
| Detached HEAD | `git symbolic-ref HEAD` fails | Ask: create branch from commit? |
| Branch in worktree | `git worktree list \| grep $BRANCH` succeeds | Ask: reuse, rename, or cancel |
| Branch exists | `git branch --list $BRANCH` returns result | Ask: use existing or rename |
| Path exists | Directory already present | Ask: choose different path or remove |
| Parent not writable | Cannot create parent directory | Abort with permission error |

### Phase 2: Directory Selection

**Priority order** (cascading, first match wins):

1. **Check for existing `.worktrees/` directory** → use it (no prompt)
2. **Check for existing `worktrees/` directory** → use it (no prompt)
3. **Check CLAUDE.md for worktree preference** → follow it (no prompt)
4. **Ask user** (only if no default found)

**For orchestrator integration**: Pass `WORKTREE_DIR=".worktrees"` to skip this phase entirely.

**Example detection**:
```bash
if [ -d ".worktrees" ]; then
  WORKTREE_DIR=".worktrees"
elif [ -d "worktrees" ]; then
  WORKTREE_DIR="worktrees"
elif grep -q "worktree.*directory" CLAUDE.md 2>/dev/null; then
  WORKTREE_DIR=$(grep "worktree.*directory" CLAUDE.md | extract_path)
else
  # Ask user via AskUserQuestion
  # Options: .worktrees/, worktrees/, custom
fi
```

### Phase 3: Creation

**Steps** (must be executed in order):

```bash
# 1. Verify .gitignore safety
# IMPORTANT: Directory must exist before git check-ignore
mkdir -p "$WORKTREE_DIR"

if ! git check-ignore -q "$WORKTREE_DIR" 2>/dev/null; then
  echo "$WORKTREE_DIR/" >> .gitignore
  git add .gitignore
  git commit -m "chore: add $WORKTREE_DIR to .gitignore"
fi

# 2. Store original CWD (critical for Phase 6 cleanup)
ORIGINAL_CWD=$(pwd)

# 3. Create worktree
git worktree add "$WORKTREE_PATH" -b "$BRANCH"

# 4. Verify creation succeeded
if [ ! -d "$WORKTREE_PATH" ]; then
  ERROR: "Worktree creation failed"
  RECOVERY: Clean up any partial state, report error
  exit 1
fi

# 5. Change to worktree directory
cd "$WORKTREE_PATH"

# 6. Initialize submodules (if any)
if [ -f .gitmodules ]; then
  git submodule update --init --recursive
fi

# 7. Write statusline worktree marker (persists across compaction)
if [ -n "$SESSION_ID" ]; then
  cat > "$HOME/.claude/.statusline-worktree-${SESSION_ID}" <<MARKER_EOF
{
  "worktree_path": "$WORKTREE_PATH",
  "branch": "$BRANCH",
  "worktree_name": "$(basename "$WORKTREE_PATH")"
}
MARKER_EOF
fi
```

**Error handling**: If `git worktree add` fails, clean up any partial state and report the error to user.

### Phase 4: Setup

**Multi-stack detection**:

```bash
# Detect all present stacks
STACKS=()
[ -f package.json ] && STACKS+=("nodejs")
[ -f Cargo.toml ] && STACKS+=("rust")
[ -f go.mod ] && STACKS+=("golang")
[ -f pyproject.toml ] || [ -f requirements.txt ] && STACKS+=("python")
[ -f Gemfile ] && STACKS+=("ruby")

# Run setup for each detected stack
for stack in "${STACKS[@]}"; do
  echo "Setting up $stack..."
  case "$stack" in
    nodejs)
      if [ -f bun.lockb ]; then
        bun install
      elif [ -f pnpm-lock.yaml ]; then
        pnpm install
      elif [ -f yarn.lock ]; then
        yarn install
      else
        npm install
      fi
      ;;
    rust)
      cargo build
      ;;
    golang)
      go m