Working in isolated worktree directories for parallel work - work normally, tests isolated, orchestrator handles cleanup
/plugin marketplace add bryonjacob/aug/plugin install aug-dev@augThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Git worktrees create isolated working directories on separate branches. Enables parallel work without conflicts.
Why you're in a worktree:
git rev-parse --git-dir
# .git → main repo
# ../path/.git/worktrees/name → worktree
git branch # Shows your feature branch
Everything works normally!
What's different:
# Delegated to worktree
cd ../worktree-42
# Verify
git branch # feature-branch-42
git status # Clean
# Work normally
# Edit files
git add .
git commit -m "feat: implement"
just check-all
git push -u origin HEAD
# Create PR
gh pr create --draft
| Aspect | Main Repo | Worktree |
|---|---|---|
| Location | Original path | Separate directory |
| Tests | May conflict | Fully isolated |
| Files | Shared | Independent |
| Git history | Shared | Shared |
Don't manually delete!
Orchestrator handles cleanup after merge. Just return to main:
cd ../main-repo
git checkout main
git pull
# Create (usually orchestrator does this)
git worktree add ../worktree-42 -b feature-42
# List
git worktree list
# Remove (orchestrator does this)
git worktree remove ../worktree-42
"Branch already checked out" - Switch branch in other worktree first
Changes not showing - Check pwd and git branch
Tests failing - Verify with git pull
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.