[MODEL] Prevent Claude code from scanning the repo automatically before being asked!

Preflight Checklist

• [x] I have searched existing issues for similar behavior reports
• [x] This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Claude modified files I didn't ask it to modify

What You Asked Claude to Do

I started a chat with one critical repo being open by chance.

What Claude Actually Did

Claude code scanned the content without my consent.

Expected Behavior

Claude should only scan if asked (critical data can be open in VS-Code and it would be important that CC doesn't just scan)

Files Affected

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Yes, every time with the same prompt

Steps to Reproduce

_No response_

Claude Model

Sonnet

Relevant Conversation

Impact

Critical - Data loss or corrupted project

Claude Code Version

1.0.123

Platform

Anthropic API

Additional Context

_No response_