LlamaFarm Worktree Manager

VerifiedCaution

Manages isolated LlamaFarm development environments using git worktrees. Create, start, stop, and clean up worktrees.

Sby Skills Guide Bot
DevelopmentIntermediate
7/23/2026
Claude Code
#git-worktrees#parallel-development#llamafarm#service-management#port-allocation

Recommended for

Automated summary

Provides a command-line workflow for creating and managing isolated LlamaFarm git worktrees with their own services, ports, and data directories.

Strengths

  • Automates branch creation, dependency setup, build, and service startup in one command.
  • Keeps parallel agent sessions separated through deterministic per-worktree port and data allocation.
  • Includes lifecycle commands for status, logs, health checks, cleanup, and diagnostics.

Limitations

  • Specific to the LlamaFarm project and its expected service stack.
  • Assumes the local `wt` CLI and required tooling are already installed.
  • Stale processes or port conflicts may still require `wt doctor`.
When to use it

Use it when starting a LlamaFarm feature or bugfix task that needs isolated running services or parallel development sessions.

When not to use it

Do not use it for unrelated repositories or when you only need plain git worktrees without the LlamaFarm service environment.

Security analysis

Caution
Quality score88/100

The skill invokes a project-specific worktree manager via Bash. Commands can stop services, delete worktrees, and clean data directories, but they are explicitly scoped to LlamaFarm development environments and do not perform arbitrary shell execution, network exfiltration, or safety bypasses. Appropriate caution for powerful but legitimate developer tooling.

Findings
  • •Uses Bash to execute `wt delete`, `wt prune`, `wt gc`, and `--force` commands that can delete worktrees and data, though scoped to LlamaFarm worktrees and not system-wide.
How this analysis is made

Examples

Start isolated feature environment
Use the wt skill to create a new worktree for feat/my-feature and start its services, then show me the assigned URLs.
Check running worktrees
Run wt list and wt status to show which LlamaFarm worktrees are running and whether their services are healthy.
Clean up a completed worktree
Delete the wt worktree feat/my-task and clean up any orphaned data left behind.

name: wt description: Manage LlamaFarm worktrees for isolated parallel development. Create, start, stop, and clean up worktrees. allowed-tools: Bash, Read user-invocable: true

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

| Task | Command | |------|---------| | Create worktree and start services | wt create feat/my-feature | | Create and cd into worktree | wt create --go feat/my-feature | | List all worktrees with status | wt list | | Check service health | wt status or wt health | | Start/stop services | wt start / wt stop | | View service logs | wt logs [server\|rag\|runtime\|designer\|all] | | Delete worktree | wt delete <name> | | Switch to worktree | wt switch <name> | | Open Designer in browser | wt open | | Diagnose issues | wt doctor | | Clean orphaned data | wt 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

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/llamafarm-worktree-manager-mrx3xw99/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/llamafarm-worktree-manager-mrx3xw99' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/llamafarm-worktree-manager-mrx3xw99/download' --output '.skill-downloads/llamafarm-worktree-manager-mrx3xw99/SKILL.md.part' && mv '.skill-downloads/llamafarm-worktree-manager-mrx3xw99/SKILL.md.part' '.skill-downloads/llamafarm-worktree-manager-mrx3xw99/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Bash, Read

Original excerpt: 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

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/llamafarm-worktree-manager-mrx3xw99/SKILL.md' && test -s '.skill-downloads/llamafarm-worktree-manager-mrx3xw99/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/wt' && cp -R '.skill-downloads/llamafarm-worktree-manager-mrx3xw99' '.claude/skills/wt'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/llamafarm-worktree-manager-mrx3xw99'

openskills read 'llamafarm-worktree-manager-mrx3xw99'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/llamafarm-worktree-manager-mrx3xw99/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills