What
/clear starts a new conversation with empty context. It now handles two more cases:
- Agent settings: each agent's settings file is carried into the new conversation. If that fails, Claude Code logs that
/cleardid not carry the settings file of the agent. - Missing folder: if the folder Claude Code started in no longer exists,
/clearfalls back to a safe folder instead.
Hooks are scripts you set up to run at certain moments. Permission hooks run when Claude asks to use a tool, and they can rewrite what the tool is given. Claude Code now records each of these rewrites, noting what kind of hook made it and where that hook came from. It keeps hook errors in a separate list.
Why
Agents keep their settings after you clear a conversation. /clear also no longer runs into trouble when the folder you started in has been deleted.
Names in the bundle/clear
/clear
Claude Code changelog modified, high confidence
* Fixed agent teams sessions showing an empty task list when coming back with `--resume`, `--continue`, `/resume` or `--session-id`, including after `/clear` or a crash, and `/branch` writing to the original session's listsee the edit
/clear
Best practices for Claude Code modified, high confidence
* `/clear` between unrelated tasks. It costs nothing, and it means the next task doesn't keep paying for the previous one's history. `/clear oauth-migration` names the session you're leaving, so you can come back to it later.see the edit
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agrees
/clear on Claude Code changelog