mcpbeat Sign in

Worktrunk Skill for Claude

> Use this skill when the user asks about Worktrunk (wt), git worktree management, running parallel AI agents with worktrees, setting up wt hooks, configuring wt.toml, using `wt switch`, `wt list`, `wt merge`, `wt remove`, `wt step`, LLM commit messages, or integrating Worktrunk with your AI agent. Also trigger when the user wants to run multiple AI agent sessions in parallel across isolated git branches, or automate dev server / database / dependency setup per worktree. Always use this skill for any question involving the `wt` CLI, worktree lifecycle automation, or the worktrunk plugin.

4k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
1
copies elsewhere
how many repositories repackaged it
133
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/jjmartres/opencode --skill worktrunk

The instruction itself

17 sections, as written by the author

Worktrunk Skill

Worktrunk (wt) is a CLI for git worktree management designed to run AI agents

(like Claude Code) in parallel across isolated branches. Think of it as making

git worktree as easy as git branch.

Quick Reference

| Task | Command |

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

| Create worktree + switch | wt switch --create feat |

| Create worktree + launch Claude | wt switch --create feat -x claude |

| List all worktrees | wt list |

| Merge & clean up | wt merge main |

| Remove current worktree | wt remove |

| Commit staged changes | wt step commit |

Installation

# macOS/Linux (recommended)
brew install worktrunk && wt config shell install

# Cargo
cargo install worktrunk && wt config shell install

# Windows
winget install max-sixty.worktrunk
git-wt config shell install

Shell integration (wt config shell install) is required so that wt switch

can actually change the shell's directory.

Core Workflow

1. Create and Switch

wt switch --create feature-auth         # New branch + worktree
wt switch --create feature-auth -x claude  # + launch Claude in it
wt switch existing-branch               # Switch to existing worktree
wt switch -                             # Previous worktree

Worktrees are placed at ../repo.branch-name by default (configurable).

2. Inspect Status

wt list                    # All worktrees with status, commits, CI
wt list --full --branches  # Include remote branches without worktrees
wt list --format=json      # Machine-readable output

Key indicators in wt list:

  • @ = current worktree
  • + / - = staged / unstaged changes
  • / = ahead / behind remote
  • / = ahead / behind default branch
  • 🤖 = Claude is working (Claude Code plugin)
  • 💬 = Claude waiting for input

3. Parallel Agents Pattern

wt switch -x claude -c feature-a -- 'Add user authentication'
wt switch -x claude -c feature-b -- 'Fix the pagination bug'
wt switch -x claude -c feature-c -- 'Write tests for the API'

-x / --execute runs a command after switching; arguments after -- are passed to it.

4. Merge or Clean Up

PR workflow:

wt step commit              # Commit staged changes with optional LLM message
gh pr create                # Open PR
wt remove                   # After PR merged

Local merge (squash + rebase + fast-forward):

wt merge main
# Commits, rebases onto main, fast-forward merges, removes worktree

Hooks

Hooks automate worktree lifecycle events. Define in .config/wt.toml (project)

or ~/.config/worktrunk/config.toml (user/global).

See references/hooks.md for the full hook reference, template variables, and

common patterns (dev servers, databases, cold-start elimination).

Hook Types at a Glance

| Hook | When | Blocking |

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

| post-create | After creation | Yes (blocks --execute) |

| post-start | After creation | No (background) |

| post-switch | Every switch | No |

| pre-commit | Before merge commit | Yes |

| pre-merge | Before merge | Yes |

| post-merge | After merge | Yes |

| pre-remove | Before removal | Yes |

| post-remove | After removal | No |

Essential Hook Patterns

Eliminate cold starts (copy deps/caches/env from main):

[post-start]
copy = "wt step copy-ignored"

Dev server per worktree (deterministic port from branch name):

[post-start]
server = "npm run dev -- --port {{ branch | hash_port }}"
[pre-remove]
server = "lsof -ti :{{ branch | hash_port }} -sTCP:LISTEN | xargs kill 2>/dev/null || true"

Local CI gate (run tests before merge):

[pre-merge]
test = "npm test"
build = "npm run build"

Template Variables & Filters

In hook commands (Jinja2 syntax):

| Variable | Value |

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

| {{ branch }} | Branch name |

| {{ repo }} | Repository directory name |

| {{ worktree_path }} | Absolute path to this worktree |

| {{ default_branch }} | Default branch name |

| {{ target }} | Target branch (merge hooks only) |

| Filter | Example | Output |

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

| sanitize | {{ branch \| sanitize }} | / and \- |

| sanitize_db | {{ branch \| sanitize_db }} | DB-safe identifier |

| hash_port | {{ branch \| hash_port }} | Stable port 10000-19999 |

LLM Commit Messages

Generate commit messages from diffs:

wt step commit              # Commit staged changes, generate message
wt step commit --all        # Stage all + commit

Configure in ~/.config/worktrunk/config.toml:

[commit.generation]
model = "claude-opus-4-5"   # or any supported model
provider = "anthropic"

Claude Code Integration

Install the plugin for activity tracking (🤖 / 💬 in wt list) and

configuration skill:

claude plugin marketplace add max-sixty/worktrunk
claude plugin install worktrunk@worktrunk

Add to ~/.claude/settings.json for statusline:

{
  "statusLine": {
    "type": "command",
    "command": "wt list statusline --format=claude-code"
  }
}

Zellij Integration

Spawn agent handoffs directly into Zellij panes (great with your existing Zellij setup):

zellij run -- wt switch --create fix-auth -x claude -- \
  'Fix the session timeout bug in auth module'

Or use hooks for a full multi-pane layout per worktree:

# .config/wt.toml
[post-create]
zellij = """
zellij action new-tab --name {{ branch | sanitize }}
zellij action new-pane -- claude
"""

Common Commands for devops Work

For microservice's repos, a typical .config/wt.toml:

[post-create]
env = "cp {{ primary_worktree_path }}/.env.local .env.local 2>/dev/null || true"

[post-start]
copy = "wt step copy-ignored"

[pre-merge]
lint = "make lint"
test = "make test"

[post-merge]
notify = "echo '✓ Merged {{ branch }} → {{ target }}'"

Further Reference

  • references/hooks.md — Complete hook documentation with all patterns
  • references/commands.md — Full command reference (switch, list, merge, remove, step, config)
  • Official docs: https://worktrunk.dev
  • Claude Code integration: https://worktrunk.dev/claude-code/
  • Tips & patterns: https://worktrunk.dev/tips-patterns/

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take jjmartres/worktrunk from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference brew, cargo, go. Without those the skill loads but fails at the first command.