Claude Code just shipped a small feature that is bigger than it looks.
Subagents can now spawn their own subagents, up to 5 levels deep.
So your workflow can become an agent tree:
implementer -> reviewer -> verifier
Powerful, but watch token burn.
Just landed nested subagent support in Claude Code
Starting to experiment more with agents kicking off agents as a way to better manage context. Capped at depth=5 to start, going out in today’s release.
Lmk what you think!