Tools to create, manage, and delete isolated git worktrees to run parallel development sessions without port or data conflicts.

Install

mkdir -p .claude/skills/wt-llama-farm && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11864" && unzip -o skill.zip -d .claude/skills/wt-llama-farm && rm skill.zip

Installs to .claude/skills/wt-llama-farm

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Manage LlamaFarm worktrees for isolated parallel development. Create, start, stop, and clean up worktrees.
106 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Create isolated development environments using git worktrees.
  • Start and stop services within a worktree.
  • List all worktrees with their status and port assignments.
  • Clean up orphaned data and worktrees.
  • Diagnose common issues in worktrees.

How it works

The skill manages isolated LlamaFarm development environments by creating git worktrees, each with its own services, ports, and data directories, allowing parallel agent sessions without conflicts.

Inputs & outputs

You give it
Worktree name and optional commands (e.g., create, delete, start)
You get back
Managed git worktree with running/stopped services, or diagnostic information

When to use wt

  • Create an isolated environment for a feature branch
  • Run multiple agent sessions simultaneously
  • Clean up orphaned data or worktrees
  • Check service health across worktrees

About this skill

wt - Worktree Manager Skill

Manages isolated LlamaFarm development environments using git worktrees. Each worktree has its own services, ports, and data directories - enabling parallel agent sessions without conflicts.

Full Documentation

For complete documentation, architecture details, and advanced usage: @scripts/wt/README.md


Quick Reference

TaskCommand
Create worktree and start serviceswt create feat/my-feature
Create and cd into worktreewt create --go feat/my-feature
List all worktrees with statuswt list
Check service healthwt status or wt health
Start/stop serviceswt start / wt stop
View service logswt logs [server|rag|runtime|designer|all]
Delete worktreewt delete <name>
Switch to worktreewt switch <name>
Open Designer in browserwt open
Diagnose issueswt doctor
Clean orphaned datawt gc

When to Use wt

Use wt when:

  • Starting isolated work on a feature/task that needs running services
  • Running parallel coding sessions (multiple agents or terminals)
  • Testing changes without affecting the main development environment
  • Avoiding port conflicts between concurrent LlamaFarm instances

Common Workflows

Starting a New Task

# Create isolated environment with services running
wt create --go feat/my-task

# Work in the worktree...
# Services are already running on auto-assigned ports

# Check status anytime
wt status

# View logs if needed
wt logs server

Checking What's Running

# List all worktrees with their port assignments
wt list

# Example output:
# NAME              STATUS    SERVER   DESIGNER  RUNTIME
# feat-my-task      running   8150     5150      11150
# fix-bug           stopped   8234     5234      11234

Cleaning Up

# Stop services and remove a worktree
wt delete feat-my-task

# Remove data for worktrees that no longer exist
wt gc

# Remove worktrees for branches merged to main
wt prune

Troubleshooting

# Diagnose common issues (ports, stale PIDs, missing tools)
wt doctor

# Restart stuck services
wt stop && wt start

# Force delete if normal delete fails
wt delete my-worktree --force

Service URLs

Each worktree gets unique ports. Check URLs with:

wt url
# Outputs:
#   Server:   http://localhost:8150
#   Designer: http://localhost:5150
#   Runtime:  http://localhost:11150

If the Caddy proxy is running, use port-free URLs:

http://server.feat-my-task.localhost
http://designer.feat-my-task.localhost

Key Environment Details

  • Worktrees location: ~/worktrees/llamafarm/
  • Data directories: ~/.llamafarm/worktrees/<name>/
  • Port allocation: Deterministic hash of worktree name (14345+offset, 5000+offset, 11000+offset)
  • Logs: ~/.llamafarm/worktrees/<name>/logs/

Notes for the Agent

  1. Always use wt create --go when setting up a new task environment - it handles everything (branch, deps, build, services)
  2. Check wt list first before creating a new worktree to see what already exists
  3. Use wt status to verify services are healthy before running tests or making API calls
  4. Run wt doctor when encountering unexplained service issues
  5. Clean up with wt delete when a task is complete to free resources

When not to use it

  • When isolated development environments are not needed.
  • When conflicts between parallel agent sessions are not a concern.
  • When manual management of git worktrees is preferred.

Limitations

  • Worktrees are located in `~/worktrees/llamafarm/`.
  • Data directories are in `~/.llamafarm/worktrees/<name>/`.
  • Port allocation is based on a deterministic hash of the worktree name.

How it compares

This skill provides a centralized command-line interface for managing multiple isolated git worktrees with their own services and data, simplifying parallel development compared to manual git worktree operations.

Compared to similar skills

wt side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
wt (this skill)06moReviewIntermediate
create-worktree-skill29moNo flagsIntermediate
makefile-dev-workflow06moReviewBeginner
terminal01moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry