Do you configure AI assistants to keep all working files inside the repository directory?

When AI assistants (e.g. GitHub Copilot, Claude, ChatGPT) perform development tasks, they sometimes create temporary files, scripts, or intermediate outputs. By default, they might use system temp directories like /tmp, /var/tmp, or the user's home directory. This creates several problems: files become hard to find, they're outside version control, and cleanup becomes unpredictable.

Configuring AI assistants to work exclusively within the repository boundaries ensures all work is visible, properly managed, and easy to clean up.

The Problem with System Directories

When AI assistants use system temp directories, you lose visibility:

Issues with External Files

Using directories outside the repository causes:

1. Cleanup challenges - Files left behind after tasks complete
2. Security risks - Sensitive data might be written to shared system directories
3. Review difficulties - Harder to review AI-generated code before committing

The Solution: Repository-Bounded Work

Configure your AI assistants' instruction to keep all work within the repository directory by introducing guidelines

1. Add to your AI Assistant Instructions

Add the following section to your AI assistant configuration (e.g. .github/copilot-instructions.md, .cursorrules, .ai/instructions.md):

## Working Directory and File Management

### Repository Boundaries
All work, including temporary files, must be done within the repository boundaries:

**DO**:
- Create temporary files/directories within the repository root
- Use `/tmp/` directory at repository root for temporary work files
- Add temporary directories to `.gitignore` if they shouldn't be committed
- Clean up temporary files after completing tasks

**DO NOT**:
- Create files outside the repository directory
- Work in system temp directories or home directory
- Leave temporary files scattered throughout the repository

### Temporary Files
- Use `/tmp/` at the repository root for scratch work
- This directory is already in `.gitignore`
- Always clean up temporary files when done
- Document any temporary files that need to persist

2. Create the Temporary Directory

Set up the directory structure in your repository:

mkdir -p tmp

3. Update .gitignore

Ensure your .gitignore includes the temporary directory:

# Temporary work files from AI assistants
/tmp/

Benefits

This approach provides:

✅ Visibility: All files are within the repository and easy to find
✅ Version Control Ready: Can selectively commit useful artifacts
✅ Easy Cleanup: Simple to remove all temporary files at once
✅ Security: .gitignore prevents accidental commits of sensitive temp files
✅ Tool-agnostic: Works with any AI assistant or development tool

Example Workflow

# AI assistant creates work files in repository
/work/
├── tmp/
│   ├── migration-analysis.md
│   ├── test-queries.sql
│   └── rollback-script.sql
├── src/
└── docs/

# Easy to review
$ cat tmp/migration-analysis.md
$ cat tmp/test-queries.sql

# Easy to clean up when done
$ rm -rf tmp/*

Conclusion

By configuring AI assistants to work exclusively within repository boundaries, you maintain full visibility and control over AI-generated files. This prevents file sprawl and makes it easier to review and manage all work produced during AI-assisted development sessions.