[DOCS] Sub-agents page still says subagents cannot spawn other subagents; v2.1.172 allows up to 5 levels of nesting

Open 💬 0 comments Opened Jun 10, 2026 by coygeek

Documentation Type

Incorrect/outdated documentation

Documentation Location

https://code.claude.com/docs/en/sub-agents

Section/Topic

The "Built-in subagents" tab list (Plan subagent description) and the "Choose the right subagent" callout

Current Documentation

In the Plan subagent description:

When you're in plan mode and Claude needs to understand your codebase, it delegates research to the Plan subagent. This prevents infinite nesting (subagents cannot spawn other subagents) while still gathering necessary context.

In the "Choose the right subagent" section:

Subagents cannot spawn other subagents. If your workflow requires nested delegation, use Skills or chain subagents from the main conversation.

What's Wrong or Missing?

The v2.1.172 release notes ship subagent nesting:

Sub-agents can now spawn their own sub-agents (up to 5 levels deep)

Both quoted passages now contradict shipped behavior. The "prevent infinite nesting" rationale for the Plan subagent is no longer accurate, and the "use Skills or chain subagents" workaround is unnecessary for the common case.

Suggested Improvement

Replace the Plan tab's "prevent infinite nesting" sentence with a note that subagents can delegate up to 5 levels deep, and replace the callout with something like:

Subagents can spawn their own subagents up to 5 levels deep. For deeper workflows, use Skills or chain subagents from the main conversation.

Impact

Medium - Makes feature difficult to understand

Additional Context

Version: v2.1.172

View original on GitHub ↗