using-git-worktrees
obra/superpowers
Create isolated workspaces for feature work using native tools or git worktrees as fallback.
What is using-git-worktrees?
Ensures feature work happens in an isolated workspace by detecting existing isolation, preferring platform-native worktree tools, and falling back to git worktrees only when necessary. Use this before starting feature work or executing implementation plans that need separation from your current workspace.
- Detects if you're already in an isolated workspace to avoid nested worktrees
- Prefers native worktree tools (EnterWorktree, /worktree commands) over manual git operations
- Falls back to git worktree creation with automatic directory selection and .gitignore verification
- Auto-detects and runs project setup (npm install, cargo build, pip install, go mod download)
- Verifies clean baseline by running project tests before starting work
How to install using-git-worktrees
npx skills add https://github.com/obra/superpowers --skill using-git-worktrees- Git repository initialized
- For native tools: platform-specific worktree support (Cursor, Claude Code, or similar)
- For git fallback: git installed and configured
How to use using-git-worktrees
- 1.Run Step 0 detection to check if you're already in an isolated workspace (compare GIT_DIR and GIT_COMMON, verify not in submodule)
- 2.If not isolated, ask for user consent to create a worktree
- 3.Use native worktree tools if available (Step 1a); otherwise use git worktree add (Step 1b)
- 4.For git fallback, select directory from: explicit instructions > existing .worktrees/ or worktrees/ > default .worktrees/
- 5.Verify project-local directory is in .gitignore before creating worktree
- 6.Run auto-detected project setup (npm install, cargo build, pip install, or go mod download)
- 7.Run baseline tests to verify clean workspace state
Use cases
- Starting a feature branch while protecting your current workspace from changes
- Implementing multiple independent features in parallel without branch switching
- Testing implementation plans in isolation before committing to main branch
- Working on experimental changes without affecting ongoing work in the primary checkout
- Developers working on feature branches
- Teams using git worktrees for parallel development
- Anyone needing isolated workspaces for experimental or risky changes
using-git-worktrees FAQ
Step 0 detection will identify this (GIT_DIR != GIT_COMMON and not a submodule). Skip worktree creation and proceed directly to project setup.
No. Always prefer native tools (Step 1a). Using git worktree add when a native tool exists creates phantom state the harness can't manage. This is the #1 mistake to avoid.
The sandbox has blocked worktree creation. Fall back to working in the current directory instead, then run setup and baseline tests in place.
Follow priority order: explicit user instructions > existing .worktrees/ or worktrees/ directory > default to .worktrees/. Always verify the directory is in .gitignore for project-local locations.
Report the failures and ask for explicit permission to proceed. Don't continue without understanding whether failures are pre-existing or new issues.
Full instructions (SKILL.md)
Source of truth, from obra/superpowers.
name: using-git-worktrees description: Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
Using Git Worktrees
Overview
Ensure work happens in an isolated workspace. Prefer your platform's native worktree tools. Fall back to manual git worktrees only when no native tool is available.
Core principle: Detect existing isolation first. Then use native tools. Then fall back to git. Never fight the harness.
Announce at start: "I'm using the using-git-worktrees skill to set up an isolated workspace."
Step 0: Detect Existing Isolation
Before creating anything, check if you are already in an isolated workspace.
GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)
BRANCH=$(git branch --show-current)
Submodule guard: GIT_DIR != GIT_COMMON is also true inside git submodules. Before concluding "already in a worktree," verify you are not in a submodule:
# If this returns a path, you're in a submodule, not a worktree — treat as normal repo
git rev-parse --show-superproject-working-tree 2>/dev/null
If GIT_DIR != GIT_COMMON (and not a submodule): You are already in a linked worktree. Skip to Step 2 (Project Setup). Do NOT create another worktree.
Report with branch state:
- On a branch: "Already in isolated workspace at
<path>on branch<name>." - Detached HEAD: "Already in isolated workspace at
<path>(detached HEAD, externally managed). Branch creation needed at finish time."
If GIT_DIR == GIT_COMMON (or in a submodule): You are in a normal repo checkout.
Has the user already indicated their worktree preference in your instructions? If not, ask for consent before creating a worktree:
"Would you like me to set up an isolated worktree? It protects your current branch from changes."
Honor any existing declared preference without asking. If the user declines consent, work in place and skip to Step 2.
Step 1: Create Isolated Workspace
You have two mechanisms. Try them in this order.
1a. Native Worktree Tools (preferred)
The user has asked for an isolated workspace (Step 0 consent). Do you already have a way to create a worktree? It might be a tool with a name like EnterWorktree, WorktreeCreate, a /worktree command, or a --worktree flag. If you do, use it and skip to Step 2.
Native tools handle directory placement, branch creation, and cleanup automatically. Using git worktree add when you have a native tool creates phantom state your harness can't see or manage.
Only proceed to Step 1b if you have no native worktree tool available.
1b. Git Worktree Fallback
Only use this if Step 1a does not apply — you have no native worktree tool available. Create a worktree manually using git.
Directory Selection
Follow this priority order. Explicit user preference always beats observed filesystem state.
-
Check your instructions for a declared worktree directory preference. If the user has already specified one, use it without asking.
-
Check for an existing project-local worktree directory:
ls -d .worktrees 2>/dev/null # Preferred (hidden) ls -d worktrees 2>/dev/null # AlternativeIf found, use it. If both exist,
.worktreeswins. -
If there is no other guidance available, default to
.worktrees/at the project root.
Safety Verification (project-local directories only)
MUST verify directory is ignored before creating worktree:
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, then proceed.
Why critical: Prevents accidentally committing worktree contents to repository.
Create the Worktree
# Determine path based on chosen location
path="$LOCATION/$BRANCH_NAME"
git worktree add "$path" -b "$BRANCH_NAME"
cd "$path"
Sandbox fallback: If git worktree add fails with a permission error (sandbox denial), tell the user the sandbox blocked worktree creation and you're working in the current directory instead. Then run setup and baseline tests in place.
Step 2: 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
Step 3: Verify Clean Baseline
Run tests to ensure workspace starts clean:
# Use project-appropriate command
npm test / cargo test / pytest / go test ./...
If tests fail: Report failures, ask whether to proceed or investigate.
If tests pass: Report ready.
Report
Worktree ready at <full-path>
Tests passing (<N> tests, 0 failures)
Ready to implement <feature-name>
Quick Reference
| Situation | Action |
|---|---|
| Already in linked worktree | Skip creation (Step 0) |
| In a submodule | Treat as normal repo (Step 0 guard) |
| Native worktree tool available | Use it (Step 1a) |
| No native tool | Git worktree fallback (Step 1b) |
.worktrees/ exists | Use it (verify ignored) |
worktrees/ exists | Use it (verify ignored) |
| Both exist | Use .worktrees/ |
| Neither exists | Check instruction file, then default .worktrees/ |
| Directory not ignored | Add to .gitignore + commit |
| Permission error on create | Sandbox fallback, work in place |
| Tests fail during baseline | Report failures + ask |
| No package.json/Cargo.toml | Skip dependency install |
Common Mistakes
Fighting the harness
- Problem: Using
git worktree addwhen the platform already provides isolation - Fix: Step 0 detects existing isolation. Step 1a defers to native tools.
Skipping detection
- Problem: Creating a nested worktree inside an existing one
- Fix: Always run Step 0 before creating anything
Skipping ignore verification
- Problem: Worktree contents get tracked, pollute git status
- Fix: Always use
git check-ignorebefore creating project-local worktree
Assuming directory location
- Problem: Creates inconsistency, violates project conventions
- Fix: Follow priority: explicit instructions > existing project-local directory > default
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 a worktree when Step 0 detects existing isolation
- Use
git worktree addwhen you have a native worktree tool (e.g.,EnterWorktree). This is the #1 mistake — if you have it, use it. - Skip Step 1a by jumping straight to Step 1b's git commands
- Create worktree without verifying it's ignored (project-local)
- Skip baseline test verification
- Proceed with failing tests without asking
Always:
- Run Step 0 detection first
- Prefer native tools over git fallback
- Follow directory priority: explicit instructions > existing project-local directory > default
- Verify directory is ignored for project-local
- Auto-detect and run project setup
- Verify clean test baseline
Related skills
More from obra/superpowers and the wider catalog.
brainstorming
Explore user intent and design before implementation—mandatory first step for any creative work.
systematic-debugging
Find root cause before fixing—systematic debugging prevents wasted effort and masked problems.
writing-plans
Create detailed implementation plans for multi-step tasks before writing code.
using-superpowers
Establish skill-first workflow—invoke relevant skills before any response, even with 1% applicability.
requesting-code-review
Dispatch a code reviewer subagent to catch issues before they cascade.
test-driven-development
Write tests first, watch them fail, then implement—the disciplined way to build reliable code.