rtk: Command for Claude Code

.claude/commands/tech/worktree.md

worktree is a command for Claude Code from rtk-ai/rtk. It costs 7 tokens per session (1,434 once invoked), scanned A, original, Apache-2.0.

A Git worktree setup command for Rust projects that creates an isolated branch directory and can run a background Cargo check. Cargo is Rust’s tool for building and checking Rust code.

In plain words
What is it for?
Use it to create worktrees for feature or fix branches, optionally skip the check for faster setup, and inspect the status of a background Cargo check.
Why use it?
It provides a separate place for each branch and gives quick feedback about Rust compilation without disturbing the current working directory.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; mentions Claude Code.

This is rtk-ai/rtk's own configuration. It tells Claude Code how to work on rtk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rtk configures →

About the project

rtk is a command-line proxy that filters and compresses output from development commands before it reaches an LLM's context. It is used with coding agents to reduce the tokens consumed by commands such as Git operations. The catalogue includes skills, commands, agents, and instructions for using rtk in agent workflows.

rtk-ai/rtk · 84,655 stars · on GitHub · rtk-ai.app

Reuse

Borrowing it

Nothing to install: this file belongs to rtk-ai/rtk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/commands/tech/worktree.md
Clone the repo
git clone --depth 1 https://github.com/rtk-ai/rtk

Made for: Claude Code.

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 worktree

README.md
[![agentmods](https://agentmods.dev/badge/commands/rtk-ai/rtk/worktree/github.svg)](https://agentmods.dev/commands/rtk-ai/rtk/worktree)
Your own site
<a href="https://agentmods.dev/commands/rtk-ai/rtk/worktree"><img src="https://agentmods.dev/badge/commands/rtk-ai/rtk/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 worktree

Your own site · 80×15
<a href="https://agentmods.dev/commands/rtk-ai/rtk/worktree"><img src="https://agentmods.dev/badge/commands/rtk-ai/rtk/worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,434 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00007 $0.01434
Opus 5.5 $0.00003 $0.00574
Sonnet 5.5 $0.00001 $0.00287
Haiku 4.5 $0.00001 $0.00143

Measured 1mo ago against content hash a0021c64d67f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

worktree scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/tech/worktree.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Worktree Setup

Create isolated git worktrees with instant feedback and background Cargo check.

Performance: ~1s setup + background cargo check

Usage

/tech:worktree feature/new-filter     # Creates worktree + background cargo check
/tech:worktree fix/typo --fast        # Skip cargo check (instant)
/tech:worktree feature/perf --no-check  # Skip cargo check

Behavior: Creates the worktree and displays the path. Navigate manually with cd .worktrees/{branch-name}.

⚠️ Important - Claude Context: If Claude Code is currently running, restart it in the new worktree:

/exit                                    # Exit current Claude session
cd .worktrees/fix-bug-name              # Navigate to worktree
claude                                   # Start Claude in worktree context

Check cargo check status: /tech:worktree-status feature/new-filter

Branch Naming Convention

Always use Git branch naming with slashes:

  • ✅ feature/new-filter → Branch: feature/new-filter, Directory: .worktrees/feature-new-filter
  • ✅ fix/bug-name → Branch: fix/bug-name, Directory: .worktrees/fix-bug-name
  • ❌ feature-new-filter → Wrong: Missing category prefix

Implementation

Execute this single bash script with branch name from $ARGUMENTS:

#!/bin/bash
set -euo pipefail

trap 'kill $(jobs -p) 2>/dev/null || true' EXIT

# Validate git repository - always use main repo root (not worktree root)
GIT_COMMON_DIR="$(git rev-parse --git-common-dir 2>/dev/null)"
if [ -z "$GIT_COMMON_DIR" ]; then
  echo "❌ Not in a git repository"
  exit 1
fi
REPO_ROOT="$(cd "$GIT_COMMON_DIR/.." && pwd)"

# Parse flags
RAW_ARGS="$ARGUMENTS"
BRANCH_NAME="$RAW_ARGS"
SKIP_CHECK=false

if [[ "$RAW_ARGS" == *"--fast"* ]]; then
  SKIP_CHECK=true
  BRANCH_NAME="${BRANCH_NAME// --fast/}"
fi
if [[ "$RAW_ARGS" == *"--no-check"* ]]; then
  SKIP_CHECK=true
  BRANCH_NAME="${BRANCH_NAME// --no-check/}"
fi

# Validate branch name
if [[ "$BRANCH_NAME" =~ [[:space:]\$\`] ]]; then
  echo "❌ Invalid branch name (spaces or special characters not allowed)"
  exit 1
fi
if [[ "$BRANCH_NAME" =~ [~^:?*\\\[\]] ]]; then
  echo "❌ Invalid branch name (git forbidden characters: ~ ^ : ? * [ ])"
  exit 1
fi

# Paths - sanitize slashes to avoid nested directories
WORKTREE_NAME="${BRANCH_NAME//\//-}"
WORKTREE_DIR="$REPO_ROOT/.worktrees/$WORKTREE_NAME"
LOG_FILE="/tmp/worktree-cargo-check-${WORKTREE_NAME}.log"

# 1. Check .gitignore (fail-fast)
if ! grep -qE "^\.worktrees/?$" "$REPO_ROOT/.gitignore" 2>/dev/null; then
  echo "❌ .worktrees/ not in .gitignore"
  echo "Run: echo '.worktrees/' >> .gitignore && git add .gitignore && git commit -m 'chore: ignore worktrees'"
  exit 1
fi

# 2. Create worktree (fail-fast)
echo "Creating worktree for $BRANCH_NAME..."
mkdir -p "$REPO_ROOT/.worktrees"
if ! git worktree add "$WORKTREE_DIR" -b "$BRANCH_NAME" 2>/tmp/worktree-error.log; then
  echo "❌ Failed to create worktree"
  cat /tmp/worktree-error.log
  exit 1
fi

# 3. Background cargo check (unless --fast / --no-check)
if [ "$SKIP_CHECK" = false ] && [ -f "$WORKTREE_DIR/Cargo.toml" ]; then
  (
    cd "$WORKTREE_DIR"
    echo "⏳ Cargo check started at $(date +%H:%M:%S)" > "$LOG_FILE"
    if cargo check --all-targets >> "$LOG_FILE" 2>&1; then
      echo "✅ Cargo check passed at $(date +%H:%M:%S)" >> "$LOG_FILE"
    else
      echo "❌ Cargo check failed at $(date +%H:%M:%S)" >> "$LOG_FILE"
    fi
  ) &
  CHECK_RUNNING=true
else
  CHECK_RUNNING=false
fi

# 4. Report (instant feedback)
echo ""
echo "✅ Worktree ready: $WORKTREE_DIR"

if [ "$CHECK_RUNNING" = true ]; then
  echo "⏳ Cargo check running in background..."
  echo "📝 Check status: /tech:worktree-status $BRANCH_NAME"
  echo "📝 Or view log: cat $LOG_FILE"
elif [ "$SKIP_CHECK" = true ]; then
  echo "⚡ Cargo check skipped (--fast / --no-check mode)"
fi

echo ""
echo "🚀 Next steps:"
echo ""
echo "If Claude Code is running:"
echo "   1. /exit"
echo "   2. cd $WORKTREE_DIR"
echo "   3. claude"
echo ""
echo "If Claude Code is NOT running:"
echo "   cd $WORKTREE_DIR && claude"
echo ""
echo "✅ Ready to work!"

Read the full file on GitHub · 189 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 · 189 lines · 7 tokens per session scan A a0021c64d67f

Subscribe to this mod's changes

worktree is a command published in the GitHub repository rtk-ai/rtk (84,655 stars, last pushed yesterday), licensed Apache-2.0. It adds 7 tokens to every session and 1,434 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.