Claude / Advanced

Orchestration and autonomy.

The top rung of the manual: running agents in concert. Teams, subagents, workflows, loops, hooks, MCP, and scheduled work. This is advanced use of the tool itself. Running an actual workforce across a portfolio is its own volume, Factory. If you are new to Claude, start with the Manual.

  1. Orchestration & Agent TeamsOne agent in one context window is serial and fills up. Orchestration buys you parallelism and fresh context. Subagents, agent teams, and workflows are three different tools, and the difference is how the agents coordinate.
  2. Agent teamsFull peer agent sessions that message each other and share a task list, for work that needs live coordination rather than fire-and-forget delegation.
  3. SubagentsSpawn specialized agents for parallel or isolated work in their own context.
  4. WorkflowsHave Claude orchestrate tens to hundreds of parallel subagents in the background, with verification.
  5. Loops & AutonomyMake Claude Code run itself. In-session orchestration, self-paced multi-turn loops, scheduled cloud routines, and spec-driven autonomous runs. When to reach for which, and the cadence math nobody tells you.
  6. HooksShell commands that fire at lifecycle events. Use them to validate, block, log, or format without touching Claude's logic.
  7. MCP ServersConnect Claude Code to external tools and data sources via the Model Context Protocol.
  8. Scheduled tasks & /loopRun a prompt on a repeat or on a clock. /loop and the Cron tools schedule inside a session; /schedule runs detached cloud routines.
  9. Background TasksCoordinate long-running work across sessions, subagents, and context windows with a shared task list stored on disk.
  10. PluginsSingle-command installable bundles of slash commands, agents, MCP servers, and hooks.