/btw
Ask a quick side question about your current work without adding to the conversation history. The question and answer appear in a dismissible overlay and never enter the main context.
$ npx -y skills add LukeRenton/explore-claude-code --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/btw
Context preview
What this command does when you run it.
Ask a quick side question about your current work without adding to the conversation history. The question and answer appear in a dismissible overlay and never enter the main context.
Command definition
btw.md/btw
Ask a quick side question about your current work without adding to the conversation history. The question and answer appear in a dismissible overlay and never enter the main context.
Usage
/btw what was the name of that config file again?
/btw what does the second argument to this function do?
/btw why did you choose that approach?
How It Works
1. You type `/btw` followed by your question 2. Claude answers using everything already in the current conversation context 3. The answer appears in an overlay. Press Space, Enter, or Escape to dismiss 4. Neither the question nor the answer is added to conversation history
Key Properties
| Property | Detail | |---|---| | Conversation visibility | Full. Can reference anything Claude has already seen this session | | Tool access | None. Cannot read files, run commands, or search | | Follow-up turns | None. Single question, single answer | | Cost | Minimal. Reuses the parent conversation's [prompt cache](^A cache that stores the conversation prefix so repeated requests avoid re-processing the same tokens) | | Works mid-response | Yes. Runs independently without interrupting Claude's current turn |
/btw vs Subagents
`/btw` is the inverse of a [subagent](^An isolated Claude instance with its own context and tools. See the agents section for details):
| | /btw | Subagent | |---|---|---| | Context | Full conversation | Starts empty | | Tools | None | Full tool access | | Best for | Asking about what Claude already knows | Going out to find something new |
When to Use It
- You need a quick answer but do not want to derail a long-running task
- You want to reference something Claude said earlier without cluttering context
- You are mid-conversation and want to check a detail without breaking flow
Read more
/btw
Ask a quick side question about your current work without adding to the conversation history. The question and answer appear in a dismissible overlay and never enter the main context.
Usage
/btw what was the name of that config file again? /btw what does the second argument to this function do? /btw why did you choose that approach?
How It Works
1. You type `/btw` followed by your question 2. Claude answers using everything already in the current conversation context 3. The answer appears in an overlay. Press Space, Enter, or Escape to dismiss 4. Neither the question nor the answer is added to conversation history
Key Properties
| Property | Detail | |---|---| | Conversation visibility | Full. Can reference anything Claude has already seen this session | | Tool access | None. Cannot read files, run commands, or search | | Follow-up turns | None. Single question, single answer | | Cost | Minimal. Reuses the parent conversation's [prompt cache](^A cache that stores the conversation prefix so repeated requests avoid re-processing the same tokens) | | Works mid-response | Yes. Runs independently without interrupting Claude's current turn |
/btw vs Subagents
`/btw` is the inverse of a [subagent](^An isolated Claude instance with its own context and tools. See the agents section for details):
| | /btw | Subagent | |---|---|---| | Context | Full conversation | Starts empty | | Tools | None | Full tool access | | Best for | Asking about what Claude already knows | Going out to find something new |
When to Use It
- You need a quick answer but do not want to derail a long-running task
- You want to reference something Claude said earlier without cluttering context
- You are mid-conversation and want to check a detail without breaking flow
Learn Claude Code by exploring it as it was designed - interactive IDE-style docs for commands, MCP, skills, CLAUDE.md and more.
Repo: LukeRenton/explore-claude-code
Other commands on explore-claude-code.
- /my-command
Review the changes in this PR. Focus on:
Open command - /review-pr
Review the changes in this PR. Focus on:
Open command - /write-tests
Write tests for: $ARGUMENTS
Open command - /BUILT-IN-COMMANDS
Commands baked into Claude Code that execute fixed logic directly. Type `/` at the prompt to see them all, or type `/` followed by any letters to filter. Unlike [bundled skills](^Prompt-driven workflows like /simplify and /batch that use Claude's tools to orchestrate work. See
Open command - /compact
Compresses your conversation to reclaim context window space. Claude summarises the conversation so far, discards the original messages, and continues with the summary as its new starting point.
Open command - /diff
Opens an interactive diff viewer showing uncommitted changes in your working directory and per-turn diffs from Claude's edits.
Open command

