What Claude Code /btw Actually Does
The /btw command in Claude Code lets you ask a side question without adding anything to the conversation history. You type /btw followed by your question, get an answer in a dismissible overlay, and the main conversation continues as if nothing happened.
That sounds simple. It is. But simple is not obvious, and the implications only clicked after I started using it daily.
Here is what makes /btw different from just asking a normal question:
The question and answer are ephemeral. They appear in an overlay. Press Space, Enter, or Escape — gone. Nothing enters the conversation history. Your context window stays clean.
It has full visibility into the current conversation. Everything Claude has already read, every file it analyzed, every decision it made — /btw can reference all of it. It just cannot reach for anything new.
It works while Claude is processing. Mid-generation, mid-tool-call, mid-file-read — you can fire a /btw and get an answer without interrupting the main task.
And it has no tool access. This is the critical constraint. Claude cannot read files, run commands, or search when answering a /btw. It answers strictly from what is already in the session context.
The official documentation describes it perfectly: /btw is the inverse of a subagent. A subagent has full tools but starts with an empty context. /btw sees your full conversation but has no tools. Use /btw to ask about what Claude already knows. Use a subagent to go find out something new.
Five Scenarios Where Claude Code /btw Earns Its Keep
I tracked my /btw usage for two weeks across three different projects. These five patterns covered about 90% of my use cases.
Top comments (0)