setup-worktree

A command that creates an isolated Git worktree and branch for a GitHub issue.

In plain words
What is it for?
It is for finding the issue and repository, creating the required Gru worktree, and reporting where to continue with gru do.
Why use it?
It gives each issue its own working directory, so changes can be developed without mixing them with other work.

Command for Claude Code

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 commands/fotoetienne/gru/setup-worktree
Clone the repo
git clone --depth 1 https://github.com/fotoetienne/gru

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.00367
Opus 5 $0.00006 $0.00183
Sonnet 5 $0.00002 $0.00073
Haiku 4.5 $0.00001 $0.00037

Measured 2d ago against content hash fce972a25bb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup-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 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.

.claude/commands/setup-worktree.md · 44 lines

What it actually says

Create a git worktree using Gru's filesystem structure for working on an issue.

Issue: $ARGUMENTS

Steps

1. Fetch Issue Details

  • Use gh issue view $ARGUMENTS to get the issue title and number
  • Extract the issue number for naming the branch and worktree

2. Determine Repository Info

  • Get the repository owner and name from git remote
  • Parse from git remote get-url origin

3. Setup Gru Filesystem Structure

  • Ensure bare repo exists at ~/.gru/repos/owner/repo.git/
    • If not, create it: git clone --bare <remote-url> ~/.gru/repos/owner/repo.git
  • Create worktree from bare repo:
    cd ~/.gru/repos/owner/repo.git
    git worktree add ~/.gru/work/owner/repo/issue-<issue#> -b issue-<issue#>
    

4. Check if Worktree Already Exists

  • Look in ~/.gru/work/owner/repo/ for existing worktree for this issue
  • If found, inform user and provide path
  • If not found, create new worktree

5. Next Steps

Inform the user:

✓ Worktree created at ~/.gru/work/owner/repo/issue-<issue#>
✓ Branch: issue-<issue#>

Next steps:
  cd ~/.gru/work/owner/repo/issue-<issue#> && gru do <issue#>
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 · 44 lines · 12 tokens per session scan A fce972a25bb0

Subscribe to this mod's changes

setup-worktree is a command published in the GitHub repository fotoetienne/gru (11 stars, last pushed 25d ago), licensed Apache-2.0. It adds 12 tokens to every session and 367 once invoked, about $0.0001 per session on Opus 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.