ClaudeAnthropic's Claude Code now supports nested subagents, allowing AI agents to launch other agents. This capability, capped at a depth of 5, helps manage context more effectively for complex agentic coding tasks. It advances agent orchestration by enabling specialized execution within multi-agent systems.
fork:true to a skill's frontmatter, isolating its context.This update addresses a key challenge in AI agent development: managing large context windows for complex problems. Delegating tasks to specialized subagents improves task decomposition and enables focused execution. This capability advances agent orchestration and multi-agent systems.
Claude Code's nested subagent support offers granular control over agent workflows, enhancing tasks like code review. This capability extends the tool's multi-agent features, providing isolated context for each step. It is available in the latest release, building on prior updates like the /fork command.
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!
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →
