by max-sixty
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
# Add to your Claude Code skills
git clone https://github.com/max-sixty/worktrunkLast scanned: 4/19/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-04-19T06:01:52.196Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}worktrunk is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by max-sixty. Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. It has 6,596 GitHub stars.
Yes. worktrunk passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/max-sixty/worktrunk" and add it to your Claude Code skills directory (see the Installation section above).
worktrunk is primarily written in Rust. It is open-source under max-sixty on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh worktrunk against similar tools.
No comments yet. Be the first to share your thoughts!
Based on votes and bookmarks from developers who liked this skill
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
August 2026: Worktrunk was released at the start of the year, and has quickly become the most popular git worktree manager. It's built with love (there's no slop!). Please let me know any frictions at all; I'm intensely focused on continuing to make Worktrunk excellent, and the biggest help is folks posting problems they perceive.
Worktrunk is a CLI for git worktree management, designed for running AI agents in parallel.
Worktrunk's three core commands make worktrees as easy as branches. Plus, Worktrunk has a bunch of quality-of-life features to simplify working with many parallel changes, including hooks to automate local workflows.
A quick demo:

📚 Full documentation at worktrunk.dev 📚
AI agents like Claude Code and Codex can handle longer tasks without supervision, such that it's possible to manage 5-10+ in parallel. Git's native worktree feature give each agent its own working directory, so they don't step on each other's changes.
But the git worktree UX is clunky. Even a task as small as starting a new
worktree requires typing the branch name three times: git worktree add -b feat ../repo.feat, then cd ../repo.feat.
Worktrees are addressed by branch name; paths are computed from a configurable template. Commands that take a branch also accept the path of the worktree it is checked out in.
Core commands:
target/, node_modules/, etc between worktreeswt list --full — CI status and AI-generated summaries per branchwt switch pr:123 to jump straight to a PR's branchhash_port template filter gives each worktree a unique portwt <name> commands and branch-scoped state for hook templatesMultiple parallel agents, same simple commands:

Homebrew (macOS & Linux):
brew install worktrunk && wt config shell install
Shell integration allows commands to change directories.
Cargo:
cargo install worktrunk && wt config shell install
Windows. wt defaults to Windows Terminal's command, so Winget additionally installs Worktrunk as git-wt to avoid the conflict:
winget install max-sixty.worktrunk
git-wt config shell install
Alternatively, disable Windows Terminal's alias (Settings → Apps → Advanced app settings → App execution aliases → "Terminal"/"Terminal Preview") to use wt directly.
Free code signing provided by SignPath.io, certificate by SignPath Foundation — policy.
Arch Linux:
sudo pacman -S worktrunk && wt config shell install
Conda / Pixi (community-maintained feedstock):
conda install -c conda-forge worktrunk && wt config shell install
Or with Pixi: pixi global install worktrunk && wt config shell install.
Create a worktree for a new feature:
$ wt switch --create feature-auth
✓ Created branch feature-auth from main and worktree @ ~/repo.feature-auth
This creates a new branch and worktree, then switches to it. Do your work, then check all worktrees with wt list:
$ wt list
Branch Status HEAD± main↕ main…± Remote⇅ Commit Age Message
@ feature-auth + ↑ +27 -8 ↑1 +31 4bc72dc 2h Add authenticati…
^ main ^⇡ ⇡1 0e631ad 1d Initial commit
○ Showing 2 worktrees, 1 with changes, 1 ahead, 1 column hidden
The @ marks the current worktree. + means staged changes, ↑1 means 1 commit ahead of main, ⇡ means unpushed commits.
When done, either:
PR workflow — commit, push, open a PR, merge via GitHub/GitLab, then clean up:
wt step commit # commit staged changes
gh pr create # or glab mr create
wt remove # after PR is merged
*Local merge