[BUG] Cant see the context because of all the spam you added

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

Run /context
used to show an ASCII diagram.

Now it appends a wall of AI slop, so I can't see the output I asked for.

What Should Happen?

Hide the AI slop behind a toggle.

Error Messages/Logs

Steps to Reproduce

/context

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.0.76

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

<img width="1440" height="900" alt="Image" src="https://github.com/user-attachments/assets/8b6f7b57-8ca1-47fc-8f24-14f7cfc83da4" />

If you didn't have us as captives, I'd switch to Open Code in a heart beat. I should not have to scroll around through a huge back scroll of text to see the content I just asked for. You have patterns to hide things behind toggles. It seems like you're rushing features out without thinking them through. You are bragging on social media about how rapidly you're shipping and so I am gonna echo that energy right back at you with how much chaos you're causing. Why I have to run commands anyways to see what percentage of the context I've used. That should just always be visible, there's plenty of room. What's next? When I run slash context, you're gonna dump the raw context itself? You should be moving towards incremental discovery, and you're doing the opposite.