Command
/agents
Opens the interface for creating, listing, and editing custom subagents — specialized configurations Claude can delegate focused work to.
A subagent is a named configuration — its own system prompt, its own allowed tools — that the main Claude Code session can hand a specific, scoped task to, like a read-only research pass over a codebase before any edits happen. /agents is where you view the ones already defined and create new ones.
The clearest signal a subagent is worth creating: you keep typing a similar multi-step instruction ('search the codebase for X, don't edit anything, report back') across different sessions. Turning that into a named subagent means invoking it consistently instead of re-describing it every time.
Subagents are also useful for keeping a large main session's context cleaner — a research subagent can churn through many files and return just a summary, rather than that exploration filling up the main conversation.
/agentsFrequently asked questions
What does /agents do in Claude Code?
Opens the interface for creating, listing, and editing custom subagents — specialized configurations Claude can delegate focused work to.
How do I use it?
Try: /agents
Any caveats to know about?
Subagents are also useful for keeping a large main session's context cleaner — a research subagent can churn through many files and return just a summary, rather than that exploration filling up the main conversation.
Is this covered in the Claude Code Toolkit?
Yes — /agents and patterns like it are part of the full command, hook, and template pack included with a Claude Code Toolkit subscription.
Want the full command, hook, and template pack?
This is one pattern out of the full Claude Code Toolkit — subscribe for the complete set, plus everything we add going forward.
Subscribe to the toolkit — $79/mo