create-worktree

create-worktree is a skill for Claude Code from jeffh/claude-plugins. It costs 43 tokens per session (1,197 once invoked), scanned C, original, Apache-2.0.

A tool for creating an isolated Git or Jujutsu worktree, which is a separate working directory for a branch, with project setup and optional notes initialization.

In plain words
What is it for?
Use it when starting work on a feature, bug fix, or Linear ticket, or when you need multiple branches open in separate directories.
Why use it?
It lets you work on another feature or bug fix without disturbing the files or dependencies in your current workspace.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is if [ -d "../.claude" ]; then.

Part of the humanlayer plugin — 2 skills, 27 commands, 6 agents shipped together

Good fit Use it when starting work on a feature, bug fix, or Linear ticket, or when you need multiple branches open in separate directories.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jeffh/claude-plugins
agentmods
npx agentmods add skills/jeffh/claude-plugins/create-worktree

Made for: Claude Code.

Or install humanlayer, the plugin that ships this one along with the rest of its 2 skills, 27 commands, 6 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for create-worktree

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffh/claude-plugins/create-worktree/github.svg)](https://agentmods.dev/skills/jeffh/claude-plugins/create-worktree)
Your own site
<a href="https://agentmods.dev/skills/jeffh/claude-plugins/create-worktree"><img src="https://agentmods.dev/badge/skills/jeffh/claude-plugins/create-worktree/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for create-worktree

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffh/claude-plugins/create-worktree"><img src="https://agentmods.dev/badge/skills/jeffh/claude-plugins/create-worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,197 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01197
Opus 5.5 $0.00017 $0.00479
Sonnet 5.5 $0.00009 $0.00239
Haiku 4.5 $0.00004 $0.00120

Measured 1mo ago against content hash e30d065acf3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

create-worktree scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$WORKTREE_PATH"
humanlayer/skills/create-worktree/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Worktree

This skill creates a new worktree for development work with proper setup and verification.

When to Activate

Activate this skill when:

  • User needs to create a new worktree for a feature or bug fix
  • Starting work on a Linear ticket (ENG-XXXX format)
  • Need to work on multiple branches simultaneously
  • Want an isolated workspace with its own dependencies

Process

1. Gather Information

Ask the user for:

  • Worktree name (or generate a unique one)
  • Base branch (or use current branch)
  • Whether to initialize thoughts directory (default: yes)

2. Create Worktree

For git users:

# Set up variables
WORKTREE_NAME="[name or generated]"
BASE_BRANCH="[base or current branch]"
WORKTREES_BASE="$HOME/wt/[repo-name]"
WORKTREE_PATH="${WORKTREES_BASE}/${WORKTREE_NAME}"

# Verify worktrees base directory exists
if [ ! -d "$WORKTREES_BASE" ]; then
    echo "Creating worktrees directory: $WORKTREES_BASE"
    mkdir -p "$WORKTREES_BASE"
fi

# Check if worktree already exists
if [ -d "$WORKTREE_PATH" ]; then
    echo "Error: Worktree directory already exists: $WORKTREE_PATH"
    exit 1
fi

# Create worktree (creates branch if it doesn't exist)
if git show-ref --verify --quiet "refs/heads/${WORKTREE_NAME}"; then
    echo "Using existing branch: ${WORKTREE_NAME}"
    git worktree add "$WORKTREE_PATH" "$WORKTREE_NAME"
else
    echo "Creating new branch: ${WORKTREE_NAME}"
    git worktree add -b "$WORKTREE_NAME" "$WORKTREE_PATH" "$BASE_BRANCH"
fi

# Copy .claude directory if it exists
if [ -d ".claude" ]; then
    cp -r .claude "$WORKTREE_PATH/"
fi

# Change to worktree and run setup
cd "$WORKTREE_PATH"
make setup || {
    echo "Setup failed. Cleaning up..."
    cd - > /dev/null
    git worktree remove --force "$WORKTREE_PATH"
    git branch -D "$WORKTREE_NAME" 2>/dev/null || true
    exit 1
}

For jj users:

# Set up variables
WORKTREE_NAME="[name or generated]"
BASE_BOOKMARK="[base bookmark]"
WORKTREES_BASE="$HOME/wt/[repo-name]"
WORKTREE_PATH="${WORKTREES_BASE}/${WORKTREE_NAME}"

# Verify worktrees base directory exists
if [ ! -d "$WORKTREES_BASE" ]; then
    echo "Creating worktrees directory: $WORKTREES_BASE"
    mkdir -p "$WORKTREES_BASE"
fi

# Check if worktree already exists
if [ -d "$WORKTREE_PATH" ]; then
    echo "Error: Worktree directory already exists: $WORKTREE_PATH"
    exit 1
fi

# Create new workspace
jj workspace add --name "$WORKTREE_NAME" "$WORKTREE_PATH"

# Set bookmark in new workspace
cd "$WORKTREE_PATH"
jj bookmark create "$WORKTREE_NAME"

# Copy .claude directory if it exists from original workspace
if [ -d "../.claude" ]; then
    cp -r ../.claude .
fi

# Run setup
make setup || {
    echo "Setup failed. Cleaning up..."
    cd - > /dev/null
    jj workspace forget "$WORKTREE_NAME"
    rm -rf "$WORKTREE_PATH"
    exit 1
}

Read the full file on GitHub · 164 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 164 lines · 43 tokens per session scan C e30d065acf3c

Subscribe to this mod's changes

create-worktree is a skill published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 10d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,197 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.