When the main Claude Code assistant spins up a subagent (a separate Claude instance handling a sub-task, launched via the Task/agent tool), the instructions given to the orchestrating model now explain that the subagent already receives the same CLAUDE.md project instruction files that were loaded at the start of the session. This applies to all subagents except the built-in Explore and Plan agent types, which don't get these files injected.
Previously the orchestrating model might have re-read CLAUDE.md itself or pasted its rules into the subagent's prompt, wasting effort on something the subagent already had. Documenting this should make orchestration a bit more efficient and avoid redundant instructions being stuffed into subagent prompts.
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
* `/init` generates a starter CLAUDE.md for your projecthow-claude-code-works see the edit
| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. |claude-directory see the edit
Anthropic's documentation has since written up CLAUDE.md, on Explore the .claude directory.