git-worktree

A command for managing Git worktrees, which let you check out multiple branches into separate folders from one repository. It can create, list, remove, or clean up these working directories.

In plain words
What is it for?
Use it to create a separate folder for a feature or experiment, inspect existing worktrees, remove one after use, or clean up stale Git records.
Why use it?
It lets you work on several branches in parallel without repeatedly switching the contents of one folder. Its safeguards also help prevent removing a worktree without confirmation.

Command

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/hmj1026/dhpk/git-worktree
Clone the repo
git clone --depth 1 https://github.com/hmj1026/dhpk
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 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 $0.00014 $0.00344
Opus 5 $0.00007 $0.00172
Sonnet 5 $0.00003 $0.00069
Haiku 4.5 $0.00001 $0.00034

Measured yesterday against content hash 6fa0c28a5935, 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 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 yesterday.

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.

commands/git-worktree.md · 44 lines

What it actually says

Contract

Use for worktree lifecycle operations; do not remove or prune a worktree without confirmation. See the command contract. Stop when a branch/path is missing or dirty; completion reports exact commands and resulting status.

Context

  • Worktrees: !git worktree list 2>/dev/null || echo 'not in a git repo'
  • Branch: !git rev-parse --abbrev-ref HEAD

Task

Follow the git-worktree skill workflow.

Sub-commands

Sub-command Action
add Create new worktree (ask for branch + purpose)
list Show all worktrees with status
remove Remove a worktree (with confirmation)
prune Clean up stale worktree records
(none) Show current worktrees and suggest actions

Naming

Use wt-{repo-shortname}-{purpose} format, placed in repo's parent directory.

Output

For add: the exact git worktree add command and next steps. For list: formatted table of worktrees. For remove: confirmation prompt then git worktree remove command.

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. yesterday First seen · 44 lines · 14 tokens per session scan A 6fa0c28a5935

Subscribe to this mod's changes

git-worktree is a command published in the GitHub repository hmj1026/dhpk (2 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 344 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 2026-08-31.