Przejdź do treści
Biblioteka skilli
Programowanie · Automatyzacja

using-git-worktrees

/using-git-worktrees

Zapewnia izolowaną przestrzeń pracy przed implementacją, narzędziem natywnym hosta albo git worktree jako zapasowym rozwiązaniem.

Repozytorium
herdrpowers ↗
Licencja
MIT
Ostatnia zmiana repozytorium
26.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
1
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 26.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Zapewnia izolowaną przestrzeń pracy przed implementacją, narzędziem natywnym hosta albo git worktree jako zapasowym rozwiązaniem.

Oryginalny opis (EN)

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

Jak działa

  1. Overview
  2. Step 0: Detect Existing Isolation
  3. Step 1: Create Isolated Workspace
  4. Step 2: Project Setup
  5. Step 3: Verify Clean Baseline
  6. Quick Reference
  7. Common Rationalizations
Sekcje z nagłówków SKILL.md, w oryginale · 211 linii, 1 639 słów
Podgląd SKILL.md
---
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.**

```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 this task's design doc or plan sits untracked in the primary checkout, carry it over now (Step 1c).

**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" "$BASE_BRANCH"
cd "$path"
pwd   # absolute path — every delegation brief must carry it
```

**Base the branch explicitly.** `<BASE_BRANCH>` comes from the repository's `Herdrpowers Configuration` section; without it, `git worktree add` bases the new branch on whatever HEAD happens to be, which silently produces a branch off the wrong commit when the session is not sitting on the base. If the key is not declared, ask which branch to base on rather than defaulting to HEAD.

**Record the absolute path.** Delegated panes do not inherit the orchestrator's working directory — every brief states this path and requires the pane to confirm it is there before doing anything else.

**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.

### 1c. Carry the Task's Design and Plan Docs (both mechanisms)

The design doc and the implementation plan are usually written before the worktree exists, so they sit **untracked in the primary checkout**. Once the worktree is ready, move them into it so they land in the feature branch's commits and the primary checkout stays clean.

1. Locate the primary checkout and check only this task's docs — the paths the invoking workflow wrote under `<DESIGN_DOC_PATH_PATTERN>` / `<PLAN_PATH_PATTERN>`:

   ```bash
   MAIN=$(git worktree list --porcelain | head -1 | sed 's/^worktree //')
   git -C "$MAIN" status --porcelain -- "<design-doc-path>" "<plan-path>"
   ```

2. Move **only `??` (untracked) entries**. A tracked file stays put: moving it would dirty the primary checkout — the opposite of the point — and if it is already committed on `<BASE_BRANCH>`, the worktree has it via the branch.

   ```bash
   mkdir -p "<worktree>/<docs-dir>"   # target directory may not exist in the worktree yet
   mv "$MAIN/<docs-dir>/<file>" "<worktree>/<docs-dir>/"
   ```

   `git mv` cannot cross worktrees (each working tree has its own index) — use plain `mv`, then `git add` and commit inside the worktree. A docs-only commit before implementation starts is fine.

3. **Several worktrees in one run** (a coordination worktree plus per-track ones): the docs go into the **coordination worktree only**. Per-track delegation briefs reference them by the coordination worktree's absolute path.

4. Report the new absolute paths. Every later delegation brief and review request must cite the new location — the old path no longer exists.

Move only this task's docs — never sweep the whole plans directory; other tasks' drafts stay where they are. If nothing matches untracked (a workflow with no plan phase, docs already committed, or working in place after declined consent / sandbox fallback), skip silently.

## 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
```

**CodeGraph (optional):** if a codegraph plugin/tool is available *and* the main
checkout has a `.codegraph/` index, run `codegraph init` in the worktree. The
index is machine-local and gitignored, so `git worktree add` never copies it —
without this the worktree has no index and codegraph queries silently fall back
to plain search. Check the main checkout, not the worktree (`.codegraph/` is
absent there by definition). If the main checkout is not indexed, skip it:
indexing is the user's decision.

## 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 |
| Main checkout has `.codegraph/` | `codegraph init` in the worktree (Step 2) |
| Main checkout not indexed | Skip codegraph — user's decision |
| Design/plan docs untracked in primary checkout | `mv` into the worktree + commit there (Step 1c) |
| Docs already tracked/committed | Leave them — the branch carries them |
| Coordination + per-track worktrees | Docs into the coordination worktree only |

## 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. |
| "Panes can read the plan from the main checkout anyway" | They can, but then the plan never lands in the branch's history and the primary checkout stays dirty. Carry it over (Step 1c) and cite the new path. |
| "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. |

Wersje

RepozytoriumWynikLicencja
Ta strona · transparent-pegasus/herdrpowers100MIT
jjuraszek/pi-gauntlet100MIT
event4u-app/agent-config100MIT
yusixian/anjian100MIT
GanyuanRan/Aegis100MIT
sitien173/refract100MIT
innei/ryugi100MIT
rootcastleco/rei-skills100MIT
davila7/claude-code-templates100MIT

Migawka bazy z 13.11.2026 · wersja paczki 513fc66ef6da (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100sr-using-git-worktrees
    Zapewnia odizolowaną przestrzeń roboczą dla nowej funkcji, przez natywne narzędzia albo git worktree, przed wdrożeniem planu.
  • 95dev_manage_git-worktrees
    Tworzy izolowane git worktrees z mądrym wyborem katalogu i weryfikacją bezpieczeństwa, do pracy nad funkcjami niezależnie od bieżącego workspace'u.
  • 100loom-using-git-worktrees
    Tworzy izolowaną gałąź lub worktree git przed rozpoczęciem kodowania i sprawdza, czy testy bazowe przechodzą.
  • 100worktree
    Tworzy izolowane worktree gita przed wdrażaniem planu, z wyborem katalogu i sprawdzeniem poprawności.
  • 90dev10x:git-worktree
    Tworzy worktree Gita do izolacji pracy nad funkcją, natywnie w bieżącej sesji albo jako osobny katalog.
  • 100use-git-worktree
    Przygotowuje izolowane katalogi robocze przez git worktree przy nowej funkcji, z doborem katalogu i sprawdzeniem bezpieczeństwa.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.