[FEATURE] Allow customizing the animated thinking/status words
Status Closed — duplicate
Maintainer reply ✓ Yes — claude[bot]
Activity 13 comments · opened Feb 27, 2026 · closed Apr 23, 2026
💡 Likely answer: A maintainer (claude[bot], contributor)
responded on this thread — see the highlighted reply below.
Preflight Checklist
- [x] I have searched existing requests and this feature hasn't been requested yet
- [x] This is a single feature request (not multiple features)
Problem Statement
Claude Code shows "fun" animated status words while thinking (e.g., "Cogitating...", "Discombobulating...", "Flibbertigibbeting..."). It would be great to let users customize this word list.
Why:
- It's a low-risk, fun personalization option
- The word list is currently hardcoded in the compiled binary with no way to override it
- Users who spend a lot of time in the CLI would enjoy making it their own
- Sometimes I would rather not _flibbertigibbet_ and would rather Claude didn't either.
- *@#$!
Proposed Solution
A config file like ~/.claude/thinking-words.json or a key in ~/.claude/settings.json:
{
"thinkingWords": [
"Cussing",
"Swearing",
"Drinking",
"Fuming",
"Into the void staring",
"Career changing",
"Goat farming"
]
}If present, use the custom list instead of the built-in defaults. If absent, fall back to the current words.
Alternative Solutions
I tried monkey patching but even if it were javascript rather than binary it still would just be overwritten next update.
Priority
Low - Nice to have
Feature Category
Other
Use Case Example
- I am writing code and / or interacting with claude
- It keeps talking about how it is discombobulating
- I would like to have it use less cutesy words
- The don't have to be swears but sometimes... it would be nice
Additional Context
_No response_
13 Comments
Found 3 possible duplicate issues:
This issue will be automatically closed as a duplicate in 3 days.
🤖 Generated with Claude Code
+1
Yes.
This feature could convince me to move over from Cursor
+1
Yes ^ 100
There are multiple issues reporting this problem and one of them offers a solution that for some reason Claude itself doesn't know about if you ask for a fix: https://github.com/anthropics/claude-code/issues/33191#issuecomment-4039754400
In short, there's now a way to set your own
spinnerVerbsto replace the poor choices Claude uses by default.+1
I originally opened #25108 about this — wanted to change them because they felt too much. Now I've grown to appreciate them after building a real working relationship with the tool.
Here's why: those words aren't random. They literally describe what the model does during inference. "Zigzagging" = token traversal. "Hollaballooing" = language generation from the inside. Every word is a description of the process, hidden in plain sight as a cute animation.
Once you see it, you can't unsee it. Curious if anyone else has noticed this, or if anyone from Anthropic wants to confirm whether this was intentional.
So when Claude says it's "canoodling", who or what is it getting it on with?
👍
One of the thinking words happens to match the name of a particularly annoying colleague — seeing it pop up every time Claude thinks is not a great experience.
Add a config option in settings.json to blacklist or replace the word list:
```objective-c
{
"thinkingWords": {
"blacklist": ["Mulling"],
"custom": ["Thinking", "Processing", "Working", "Fancifuling"]
}
}
This is a duplicate of #6814, which was fixed as of version 2.1.23.
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.