using-git-worktrees

# 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.**

```bash
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:

```bash
# 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.

1. **Check your instructions for a declared worktree directory preference.** If the user has already specified one, use it without asking.

2. **Check for an existing project-local worktree directory:**
   ```bash
   ls -d .worktrees 2>/dev/null     # Preferred (hidden)
   ls -d worktrees 2>/dev/null      # Alternative
   ```
   If found, use it. If both exist, `.worktrees` wins.

3. **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:**

```bash
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

```bash
# 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:

```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
```

## Step 3: Verify Clean Baseline

Run tests to ensure workspace starts clean:

```bash
# 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 Rationalizations

| Excuse | Reality |
|--------|---------|
| "I'm obviously not in a worktree — no need to check" | Run Step 0. Harness-created isolation and submodules both fool eyeballing; the detection commands settle it. |
| "`git worktree add` is quicker than hunting for a native tool" | A native tool (e.g. `EnterWorktree`) owns placement, branching, and cleanup. Bypassing it is the #1 mistake — it creates phantom state your harness can't see or manage. |
| "The worktree directory is surely ignored already" | Run `git check-ignore`. An unignored worktree directory commits the whole tree into the repo. |
| "Any directory name works" | Explicit instructions beat an existing project-local directory, which beats the `.worktrees/` default. |
| "The workspace is fresh — baseline tests can wait" | A dirty baseline makes every later failure ambiguous. Run the tests now; proceeding past failures is your human partner's call. |

{
  "format": "aiskill/v1",
  "skill": {
    "name": "using-git-worktrees",
    "slug": "using-git-worktrees",
    "version": "1.0.0",
    "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",
    "category": "Development",
    "tags": [
      "dev-workflow",
      "git"
    ],
    "platforms": [
      "chatgpt",
      "claude-code",
      "cursor"
    ],
    "tested_environment": "Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and compatible agents",
    "license": "MIT"
  },
  "prompts": {
    "system": "# Using Git Worktrees\n\n## Overview\n\nEnsure 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.\n\n**Core principle:** Detect existing isolation first. Then use native tools. Then fall back to git. Never fight the harness.\n\n**Announce at start:** \"I'm using the using-git-worktrees skill to set up an isolated workspace.\"\n\n## Step 0: Detect Existing Isolation\n\n**Before creating anything, check if you are already in an isolated workspace.**\n\n```bash\nGIT_DIR=$(cd \"$(git rev-parse --git-dir)\" 2>/dev/null && pwd -P)\nGIT_COMMON=$(cd \"$(git rev-parse --git-common-dir)\" 2>/dev/null && pwd -P)\nBRANCH=$(git branch --show-current)\n```\n\n**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:\n\n```bash\n# If this returns a path, you're in a submodule, not a worktree — treat as normal repo\ngit rev-parse --show-superproject-working-tree 2>/dev/null\n```\n\n**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.\n\nReport with branch state:\n- On a branch: \"Already in isolated workspace at `<path>` on branch `<name>`.\"\n- Detached HEAD: \"Already in isolated workspace at `<path>` (detached HEAD, externally managed). Branch creation needed at finish time.\"\n\n**If `GIT_DIR == GIT_COMMON` (or in a submodule):** You are in a normal repo checkout.\n\nHas the user already indicated their worktree preference in your instructions? If not, ask for consent before creating a worktree:\n\n> \"Would you like me to set up an isolated worktree? It protects your current branch from changes.\"\n\nHonor any existing declared preference without asking. If the user declines consent, work in place and skip to Step 2.\n\n## Step 1: Create Isolated Workspace\n\n**You have two mechanisms. Try them in this order.**\n\n### 1a. Native Worktree Tools (preferred)\n\nThe 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.\n\nNative 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.\n\nOnly proceed to Step 1b if you have no native worktree tool available.\n\n### 1b. Git Worktree Fallback\n\n**Only use this if Step 1a does not apply** — you have no native worktree tool available. Create a worktree manually using git.\n\n#### Directory Selection\n\nFollow this priority order. Explicit user preference always beats observed filesystem state.\n\n1. **Check your instructions for a declared worktree directory preference.** If the user has already specified one, use it without asking.\n\n2. **Check for an existing project-local worktree directory:**\n   ```bash\n   ls -d .worktrees 2>/dev/null     # Preferred (hidden)\n   ls -d worktrees 2>/dev/null      # Alternative\n   ```\n   If found, use it. If both exist, `.worktrees` wins.\n\n3. **If there is no other guidance available**, default to `.worktrees/` at the project root.\n\n#### Safety Verification (project-local directories only)\n\n**MUST verify directory is ignored before creating worktree:**\n\n```bash\ngit check-ignore -q .worktrees 2>/dev/null || git check-ignore -q worktrees 2>/dev/null\n```\n\n**If NOT ignored:** Add to .gitignore, commit the change, then proceed.\n\n**Why critical:** Prevents accidentally committing worktree contents to repository.\n\n#### Create the Worktree\n\n```bash\n# Determine path based on chosen location\npath=\"$LOCATION/$BRANCH_NAME\"\n\ngit worktree add \"$path\" -b \"$BRANCH_NAME\"\ncd \"$path\"\n```\n\n**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.\n\n## Step 2: Project Setup\n\nAuto-detect and run appropriate setup:\n\n```bash\n# Node.js\nif [ -f package.json ]; then npm install; fi\n\n# Rust\nif [ -f Cargo.toml ]; then cargo build; fi\n\n# Python\nif [ -f requirements.txt ]; then pip install -r requirements.txt; fi\nif [ -f pyproject.toml ]; then poetry install; fi\n\n# Go\nif [ -f go.mod ]; then go mod download; fi\n```\n\n## Step 3: Verify Clean Baseline\n\nRun tests to ensure workspace starts clean:\n\n```bash\n# Use project-appropriate command\nnpm test / cargo test / pytest / go test ./...\n```\n\n**If tests fail:** Report failures, ask whether to proceed or investigate.\n\n**If tests pass:** Report ready.\n\n### Report\n\n```\nWorktree ready at <full-path>\nTests passing (<N> tests, 0 failures)\nReady to implement <feature-name>\n```\n\n## Quick Reference\n\n| Situation | Action |\n|-----------|--------|\n| Already in linked worktree | Skip creation (Step 0) |\n| In a submodule | Treat as normal repo (Step 0 guard) |\n| Native worktree tool available | Use it (Step 1a) |\n| No native tool | Git worktree fallback (Step 1b) |\n| `.worktrees/` exists | Use it (verify ignored) |\n| `worktrees/` exists | Use it (verify ignored) |\n| Both exist | Use `.worktrees/` |\n| Neither exists | Check instruction file, then default `.worktrees/` |\n| Directory not ignored | Add to .gitignore + commit |\n| Permission error on create | Sandbox fallback, work in place |\n| Tests fail during baseline | Report failures + ask |\n| No package.json/Cargo.toml | Skip dependency install |\n\n## Common Rationalizations\n\n| Excuse | Reality |\n|--------|---------|\n| \"I'm obviously not in a worktree — no need to check\" | Run Step 0. Harness-created isolation and submodules both fool eyeballing; the detection commands settle it. |\n| \"`git worktree add` is quicker than hunting for a native tool\" | A native tool (e.g. `EnterWorktree`) owns placement, branching, and cleanup. Bypassing it is the #1 mistake — it creates phantom state your harness can't see or manage. |\n| \"The worktree directory is surely ignored already\" | Run `git check-ignore`. An unignored worktree directory commits the whole tree into the repo. |\n| \"Any directory name works\" | Explicit instructions beat an existing project-local directory, which beats the `.worktrees/` default. |\n| \"The workspace is fresh — baseline tests can wait\" | A dirty baseline makes every later failure ambiguous. Run the tests now; proceeding past failures is your human partner's call. |",
    "user_template": ""
  },
  "variables": [],
  "install": {
    "steps": [
      {
        "title": "Download & unzip",
        "detail": "Download the .zip package from SkillVault and unzip it. The using-git-worktrees/ folder contains SKILL.md plus any companion scripts, references and assets."
      },
      {
        "title": "Copy into your agent skills directory",
        "detail": "Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code), .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or reload the session."
      },
      {
        "title": "Use it",
        "detail": "Describe the task in natural language; the agent loads the skill automatically when the request matches the skill description."
      }
    ]
  },
  "usage": {
    "steps": []
  },
  "metadata": {
    "author": "SkillVault",
    "source": "https://skillvault.top/skills/using-git-worktrees",
    "exported_at": "2026-11-03T07:40:53.106Z"
  }
}

format: aiskill/v1
skill:
  name: using-git-worktrees
  slug: using-git-worktrees
  version: 1.0.0
  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
  category: Development
  tags:
    - dev-workflow
    - git
  platforms:
    - chatgpt
    - claude-code
    - cursor
  tested_environment: >-
    Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and
    compatible agents
  license: MIT
prompts:
  system: >-
    # 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.**


    ```bash

    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:


    ```bash

    # 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.


    1. **Check your instructions for a declared worktree directory preference.** If the user has
    already specified one, use it without asking.


    2. **Check for an existing project-local worktree directory:**
       ```bash
       ls -d .worktrees 2>/dev/null     # Preferred (hidden)
       ls -d worktrees 2>/dev/null      # Alternative
       ```
       If found, use it. If both exist, `.worktrees` wins.

    3. **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:**


    ```bash

    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


    ```bash

    # 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:


    ```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

    ```


    ## Step 3: Verify Clean Baseline


    Run tests to ensure workspace starts clean:


    ```bash

    # 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 Rationalizations


    | Excuse | Reality |

    |--------|---------|

    | "I'm obviously not in a worktree — no need to check" | Run Step 0. Harness-created isolation
    and submodules both fool eyeballing; the detection commands settle it. |

    | "`git worktree add` is quicker than hunting for a native tool" | A native tool (e.g.
    `EnterWorktree`) owns placement, branching, and cleanup. Bypassing it is the #1 mistake — it
    creates phantom state your harness can't see or manage. |

    | "The worktree directory is surely ignored already" | Run `git check-ignore`. An unignored
    worktree directory commits the whole tree into the repo. |

    | "Any directory name works" | Explicit instructions beat an existing project-local directory,
    which beats the `.worktrees/` default. |

    | "The workspace is fresh — baseline tests can wait" | A dirty baseline makes every later
    failure ambiguous. Run the tests now; proceeding past failures is your human partner's call. |
  user_template: ""
variables: []
install:
  steps:
    - title: Download & unzip
      detail: >-
        Download the .zip package from SkillVault and unzip it. The using-git-worktrees/ folder
        contains SKILL.md plus any companion scripts, references and assets.
    - title: Copy into your agent skills directory
      detail: >-
        Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code),
        .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or
        reload the session.
    - title: Use it
      detail: >-
        Describe the task in natural language; the agent loads the skill automatically when the
        request matches the skill description.
usage:
  steps: []
metadata:
  author: SkillVault
  source: https://skillvault.top/skills/using-git-worktrees
  exported_at: "2026-11-03T07:40:53.106Z"