git-worktree-runner CLAUDE.md

Instructions for Git Worktree Runner, a command-line tool that creates and manages separate working folders for Git branches.

In plain words
What is it for?
Use them when developing or testing the CLI, creating worktrees, running ShellCheck or BATS tests, and documenting its user-facing commands.
Why use it?
They explain the project's commands, layout, editor and AI-tool integrations, and the tests needed before changes are accepted.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/coderabbitai/git-worktree-runner/claude-md
Clone the repo
git clone --depth 1 https://github.com/coderabbitai/git-worktree-runner
Per session 2,695 This file is loaded in full into every session.
When invoked 2,695 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 97% copy Near-identical to another mod 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 $0.02695 $0.02695
Opus 5 $0.01347 $0.01347
Sonnet 5 $0.00539 $0.00539
Haiku 4.5 $0.00269 $0.00269

Measured 2d ago against content hash 3a04897541a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-worktree-runner CLAUDE.md 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 2d 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.

Origin

This is a copy

97% identical to git-worktree-runner AGENTS.md — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

git gtr (Git Worktree Runner) is a cross-platform CLI tool written in Bash that simplifies git worktree management. It wraps git worktree with quality-of-life features like editor integration, AI tool support, file copying, and hooks. Installed as a git subcommand: git gtr <command>.

Invocation

  • Production: git gtr <command> (git subcommand via bin/git-gtr wrapper)
  • Development/testing: ./bin/gtr <command> (direct execution)
  • User-facing docs: Always reference git gtr, never ./bin/gtr

Testing

This project uses BATS tests for core functions and manual smoke tests for end-to-end workflows. CI runs ShellCheck + BATS automatically on PRs (.github/workflows/lint.yml).

  1. Run automated tests: bats tests/
  2. Run a single test file: bats tests/config.bats
  3. Run a single test by name: bats tests/config.bats --filter "cfg_map_to_file_key"
  4. Run relevant manual smoke tests:
./bin/gtr new test-feature          # Create worktree
./bin/gtr new feature/auth          # Slash branch → folder "feature-auth"
./bin/gtr list                      # Table output
./bin/gtr go test-feature           # Print path
./bin/gtr run test-feature git status
./bin/gtr rm test-feature           # Clean up

For exhaustive manual testing (hooks, copy patterns, adapters, --force, --from-current, etc.), see the full checklist in CONTRIBUTING.md or .github/instructions/testing.instructions.md.

Test files: adapters, config, copy_safety, integration_lifecycle, parse_args, provider, resolve_base_dir, sanitize_branch_name (all in tests/). Shared fixtures in tests/test_helper.bash.

Tip: Use a disposable repo for testing to avoid polluting your working tree:

mkdir -p /tmp/gtr-test && cd /tmp/gtr-test && git init && git commit --allow-empty -m "init"
/path/to/git-worktree-runner/bin/gtr new test-feature

Read the full file on GitHub · 198 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. 2d ago First seen · 198 lines · 2,695 tokens per session scan A 3a04897541a3

Subscribe to this mod's changes

git-worktree-runner CLAUDE.md is an instructions file published in the GitHub repository coderabbitai/git-worktree-runner (1,754 stars, last pushed 5d ago), licensed Apache-2.0. It adds 2,695 tokens to every session, about $0.0135 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to git-worktree-runner AGENTS.md, differing in 8 lines, and is treated as a copy.