A command that creates a separate Git worktree, which is an independent working copy of a repository, and starts another Claude agent there. Each worktree gets its own cmux workspace, a separate development session.

Use it to start parallel agents for features, bug fixes, or read-only investigations, choosing the starting branch, task, mode, and Claude model.

It lets you work on multiple tasks at the same time without mixing files or branches in your main working copy.

new — Skill for Claude Code by CRJFisher: A command that creates a separate Git worktree, which…

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add CRJFisher/spinoff

Claude Code

/plugin install spinoff

Made for: Claude Code.

Or install spinoff, the plugin that ships this one along with the rest of its 3 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/crjfisher/spinoff/new.svg)](https://agentmods.dev/skills/crjfisher/spinoff/new)

Your own site

<a href="https://agentmods.dev/skills/crjfisher/spinoff/new"><img src="https://agentmods.dev/badge/skills/crjfisher/spinoff/new.svg" alt="Measured on agentmods" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,108 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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.01108
Opus 5	$0.00011	$0.00554
Sonnet 5	$0.00004	$0.00222
Haiku 4.5	$0.00002	$0.00111

Measured 5d ago against content hash 344c1ec771f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

new 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 5d 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.

skills/new/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Spinoff

Create an isolated git worktree for parallel development on a specific task.

Each spinoff runs in Claude Code's native sandbox with a dedicated cmux workspace. This enables running multiple Claude agents in parallel on different tasks.

Usage

/spinoff:new <task-name> [options]

Examples:

/spinoff:new fix-auth-bug - Create spinoff from current branch
/spinoff:new feat-dark-mode --base develop - Create from develop branch
/spinoff:new JIRA-1234 --task "Implement user profile page" - With task for agent
/spinoff:new explore-auth --task "analyze the auth architecture" --mode plan - Read-only exploration

Options:

--base <branch> - Base branch to create worktree from (default: current branch)
--task <description> - Task description passed to Claude agent
--mode <plan|implement> - Agent mode: plan (read-only) or implement (sandbox + auto-commit). Falls back to project default_mode.
--model <model> - Claude model to use (e.g. haiku, sonnet, opus). If omitted, uses user's default.

Your Task

1. Check Prerequisites

Verify you're in a git repository:

git rev-parse --show-toplevel

If this fails, inform the user they need to be in a git repository.

2. Check for Spinoff Config

Look for the project's spinoff configuration:

ls -la .claude/spinoff.json

If the config exists: Proceed to step 3.

If the config does NOT exist:

Inform the user: "This project doesn't have spinoff configured yet."
Ask if they want to set it up now.
If yes, ask the user to run /spinoff:init to create it.
After setup completes, proceed to step 3.

3. Parse Arguments

Parse $ARGUMENTS for:

Task name (required, first positional argument)
--base (optional)
--task (optional)
--mode <plan|implement> (optional)
--model (optional)

If no task name provided, ask the user for a descriptive task name. Good examples:

Read the full file on GitHub · 157 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago First seen · 157 lines · 22 tokens per session scan A 344c1ec771f9

Subscribe to this mod's changes

new is a skill published in the GitHub repository CRJFisher/spinoff (2 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 1,108 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.

Building agents Git and workflow

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens