worktree

A command for managing interactive Git worktrees, which are separate working directories linked to the same repository. It can create, list, inspect, and remove those worktrees.

In plain words
What is it for?
Use it to create a parallel workspace, list existing worktrees, inspect one, or remove one. It is for interactive worktrees, not the agent's built-in isolated worktrees.
Why use it?
It makes it easier to work on multiple branches in separate directories without mixing their files or branch state.

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/restarter/lets-workflow/worktree
Clone the repo
git clone --depth 1 https://github.com/restarter/lets-workflow
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,232 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 $0.00016 $0.06232
Opus 5 $0.00008 $0.03116
Sonnet 5 $0.00003 $0.01246
Haiku 4.5 $0.00002 $0.00623

Measured 2d ago against content hash 0e1dc3ad2cf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

plugins/lets/commands/worktree.md · 432 lines

How it starts

The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worktree Management

Thin dispatcher for interactive parallel worktrees. All filesystem/git work lives in the Go subcommand lets worktree (cli/internal/worktreecmd/); this skill captures user intent via AskUserQuestion, shells out with --json, and renders the result.

Interactive worktrees only. Agent worktrees (isolation: worktree) use native Claude Code behavior — not this command.

IMPORTANT: If the spec below invokes any deferred tool (e.g. AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own — the tool invocation is part of the contract. This is critical.

Step 1: Determine Subcommand

If argument provided (e.g., /lets:worktree create auth-feature), parse it:

  • create <name> -> go to Create. First strip any --cmux / --no-cmux / --tmux / --no-tmux / --auto / --flow <value> / --branch <ref> token out of the argument and carry them as overrides (--cmux/--no-cmux/--tmux/--no-tmux = launcher; --auto = autonomous permission mode; --flow plan|plan-workflow = which command the launch lands in — all for Step C3.5; --branch <ref> decouples the attached/created branch from the dir name — Step C2). Bind the remainder as <name> (so create auth --flow plan-workflow --auto => name auth, not the flags; create pwa-46696 --branch feature/pwa-46696 => name pwa-46696, branch feature/pwa-46696).
  • list -> go to List
  • remove <name> -> go to Remove
  • info -> go to Info

If no argument, use AskUserQuestion:

AskUserQuestion(
  questions=[{
    question: "What do you want to do with worktrees?",
    header: "Action",
    options: [
      { label: "Create", description: "Create a new worktree for parallel work" },
      { label: "List", description: "Show all active worktrees" },
      { label: "Remove", description: "Remove a worktree and clean up" },
      { label: "Info", description: "Show current worktree status" }
    ],
    multiSelect: false
  }]
)

Read the full file on GitHub · 432 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 · 432 lines · 16 tokens per session scan A 0e1dc3ad2cf8

Subscribe to this mod's changes

worktree is a command published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 16 tokens to every session and 6,232 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.