[MODEL]

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's behavior changed between sessions

What You Asked Claude to Do

Include:

• ~20 subagents launched with mode: auto that were denied Edit/Write/Bash permissions despite the mode
• Each burned 90K-180K tokens reading files then failing
• Estimated ~3M tokens wasted
• Date: 2026-04-23/24

What Claude Actually Did

just launched agents again and again that made notes and didn't edit text despite explicit prompting etc

Expected Behavior

claude used the same settings as before, didn't ask for permissions, never got any writing done. burned 11% of my weekly tokens in 20 minutes wasted

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

2.1.89 (Claude Code)

Platform

Anthropic API

Additional Context

_No response_