Wt

What it does

When your agent uses it

• Tasks that involve Git worktrees

Example prompts

• “/wt”

Requirements

• Pre-approved tools (allowed-tools): Bash, Read

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit 6244d46. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Wt loads about 896 tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 283 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~27

When it runs · the whole SKILL.md, loaded when a task matches

~896

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from llama-farm/llamafarm at commit 6244d46, republished under its Apache-2.0 licence (© llama-farm). 283 words, ~896 tokens.

name

wt

description

Manage LlamaFarm worktrees for isolated parallel development. Create, start, stop, and clean up worktrees.

allowed-tools

Bash, Read

user-invocable

true

# 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

# 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

# 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

# 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

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

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

© llama-farm, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/wt of llama-farm/llamafarm.

Open the folder on GitHubat commit 6244d46