using-git-worktrees

Guidance for using Git worktrees, which are separate working directories connected to the same Git repository. They let developers work on features or experiments without changing the main working directory.

In plain words
What is it for?
Use it for feature work, parallel development, or experiments that need a clean starting point, installed dependencies, baseline tests, and an easy rollback path.
Why use it?
Isolating work reduces the chance that unfinished changes, experiments, or parallel tasks interfere with the main branch.

Skill for Claude CodeCodex

Part of the mtk plugin — 45 skills, 6 agents, 7 hooks, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/moberghr/mtk-agent-toolkit/using-git-worktrees
Any agent
npx skills add moberghr/mtk-agent-toolkit --skill using-git-worktrees
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code, Codex.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 1 MCP server.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,038 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.01038
Opus 5 $0.00015 $0.00519
Sonnet 5 $0.00006 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 2d ago against content hash 22bf809f8b99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-git-worktrees scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/using-git-worktrees/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Git Worktrees

Overview

Git worktrees provide isolated workspaces without the overhead of multiple clones. This skill ensures worktrees are created safely, dependencies are installed, and baseline tests pass before work begins.

When To Use

  • Feature implementation that should not contaminate the main branch
  • Parallel development on multiple features
  • Experimentation that needs a clean rollback path
  • Any work where isolation reduces risk

When NOT To Use

  • Quick single-file fixes on the current branch
  • When the engineer explicitly wants to work on the current branch

Workflow

  1. Determine worktree location:

    • Check for .worktrees/, worktrees/, or .claude/worktrees/ (Claude Code's native worktree location) directories in the repo
    • Check CLAUDE.md for worktree preferences
    • If neither exists, ask the engineer where to place worktrees
    • Default: .worktrees/ in the repo root
  2. Verify gitignore safety:

    • Check if the worktree directory is listed in .gitignore
    • If not, add it and commit the .gitignore change before creating the worktree
    • Never create a worktree in a directory that would be tracked by git
  3. Create the worktree:

    git worktree add <path> -b <branch-name>
    
    • Branch naming: feat/<slug> or fix/<slug> matching the task (S4.1)
    • Announce: "Creating isolated worktree at <path> on branch <branch-name>"
  4. Install dependencies: Auto-detect and install based on project files:

    • *.csproj / *.sln -> dotnet restore
    • package.json -> npm install or equivalent
    • requirements.txt / pyproject.toml -> pip install or poetry install
    • go.mod -> go mod download
    • Cargo.toml -> cargo fetch
  5. Run baseline tests:

    • Execute the project's test command to confirm a clean starting state
    • If baseline tests fail, report the failures before starting work
    • This prevents blaming new work for pre-existing failures

Read the full file on GitHub · 112 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 112 lines · 29 tokens per session scan A 22bf809f8b99

Subscribe to this mod's changes

using-git-worktrees is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (6 stars, last pushed 8d ago), licensed MIT. It adds 29 tokens to every session and 1,038 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens