automation

agent-worktree: Parallel AI‑Agent Development with Isolated Git Worktrees

Name: agent-worktree: Parallel AI‑Agent Development with Isolated Git Worktrees
Author: nekocode

Empower your AI coding agents to work in parallel, each in its own isolated environment. Ideal for founders needing scalable, conflict‑free codebases.

From the repo · “A Git worktree workflow tool for AI coding agents. Enables parallel development with isolated environments.”

280 stars18 forksRustGuide quality 9/10 · reviewed Oct 15Updated 10/20/2026100% free · open source

What it does

The agent-worktree tool enables parallel development with isolated environments for AI coding agents using Git worktree workflow.

When to use it

•You need to manage multiple AI coding agent development environments simultaneously.
•Your team requires isolated environments for different AI coding agent tasks or experiments.
•You want to improve development efficiency by running multiple AI coding agent tasks in parallel.

Ready-to-paste prompt

agent-worktree new my-experiment --agent my-agent --task my-task

Heads up: The agent-worktree tool requires Rust and Cargo to be installed on your system, and you need to have a GitHub repository set up for your AI coding agent project.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/agent-worktree && curl -fsSL https://workflowstacks.com/api/skills/agent-worktree/claude-skill -o ~/.claude/skills/agent-worktree/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How agent-worktree: Parallel AI‑Agent Development with Isolated Git Worktrees works

Codeflow

Free to inspect

Agent-worktree: Parallel AI‑Agent Development with Isolated Git Worktrees is a medium Rust project (~6k lines across 44 code files, plus 21 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size

Medium codebase

~6k lines · 44 code files · 50 min skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Rust

No API keys detected

Rust 96%Shell 3%JavaScript 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
src/main.rs
Where the program starts running
3
Cargo.toml
Dependencies and the commands it exposes

What's in each folder

src/Core code — the actual logic42 files

npm/Folder7 files

scripts/Helper scripts4 files

tests/Tests — proof it works18 files

READMEHas testsDocumentedNo CIMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/agent-worktree && curl -fsSL https://workflowstacks.com/api/skills/agent-worktree/claude-skill -o ~/.claude/skills/agent-worktree/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

nekocode

Language

Rust

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Score your leads by ideal-customer fit

You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.