[BUG] Session feedback prompt: "How is Claude doing this session?" answered with "Good" is grammatically mismatched

Open 💬 0 comments Opened Jun 12, 2026 by jbagentx

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?

The session feedback prompt asks "How is Claude doing this session?" and offers "Good" as a response option.

"How is X doing?" grammatically calls for an adverb modifying doing — "Well" / "Badly" — not an adjective. "Good" answers a different question ("Is Claude good?"). While "doing good" is common in conversational English, a bare one-word button lacks the conversational context that makes the idiom pass, so it reads as a grammatical error in the UI.

What Should Happen?

Change the option labels to match the question — e.g. "Well" / "Poorly", or
Change the question to match the labels — e.g. "How was Claude's output this session?" or "Rate Claude this session", which "Good" / "Bad" answer correctly.
Option 2 is probably safer: adjective labels like "Good"/"Bad" are the established convention for rating buttons, and "Well"/"Poorly" would look stilted.

Error Messages/Logs

Steps to Reproduce

This is something users get to see according to Anthropic, so it's not readily reproducible.

Claude Model

Other

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.1.170 (Claude Code)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

VS Code integrated terminal

Additional Information

[I asked Claude Code to suggest the description ;-)]

View original on GitHub ↗