# Set Up Workflow: Claude Code Worktree Isolation: Permission Scoping and Advanced Workflow Patterns
## What This Is
Claude Code's Worktree Isolation enables running multiple coding tasks simultaneously in separate, contained environments. This allows development teams to build several features or test different solutions at the same time without conflict, significantly accelerating project timelines.
Source: https://claudelog.com/faqs/what-is-worktree-isolation-in-claude-code/
## Before You Start
Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)
Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?
## Source Access Note
The source URL (https://claudelog.com/faqs/what-is-worktree-isolation-in-claude-code/) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.
## What to Implement
This is an **AI Workflow** — an end-to-end automation pattern or integration pipeline.
- Study the workflow architecture from the source and context below
- Identify which parts I can implement locally vs. parts that need external services
- For local parts: implement them using my existing stack and API keys
- For external parts: tell me exactly what services I need and help me configure the integration code
- Wire up any required API calls using keys from my .env files
## Additional Context
- Scan the user's current project for a `.claude/agents/` directory. If it doesn't exist, create it. Then, create a new subagent configuration file (e.g., `isolated-refactor.md`) with the frontmatter `isolation: worktree` and a whitelisted tool like `filesystem`.
- Invoke a Claude Code task using the new subagent to demonstrate the isolated workflow. Use a command like `claude --agent isolated-refactor --worktree refactor-test 'Refactor the largest function in src/main.js into smaller, single-responsibility functions.'`
- After the task completes, execute `git worktree list` to show the newly created `refactor-test` worktree. Explain to the user that this worktree is isolated from the main branch and that Claude Code will prompt for cleanup upon session exit.
## Reference Implementation
```
---
agent: isolated-builder
isolation: worktree
tools:
- filesystem
- shell
---
This subagent is designed to build a feature in an isolated worktree.
It only has access to the filesystem and shell tools.
```
## Guidelines
- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it