Skip to content

The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.

2.9 KB
Raw Blame

description: Tools the agent uses to plan, delegate and ask for help. icon: sitemap

Agent coordination

Besides doing the work, the agent has tools for organizing it: planning multi-step jobs, spawning sub-agents, and pausing to ask you when something is unclear.

Tools in this family

Tool What it does
todo Rewrites the session to-do list across a long task. The chat shows it as a checklist that ticks off as work progresses.
spawn_subagent Starts an asynchronous child selected by agent_id; use task_key to resume a compatible child, including a paused one.
use_skill Loads an inline skill's playbook and tools (coding, web3, system, scheduling, docs, mcp) so the agent can call them.
ask_user_clarification Pauses and asks you a precise question instead of guessing.
plan_exit Leaves the planning phase and starts executing.

spawn_subagent accepts an agent_id to choose a specialist, an optional model to pin that child to a model for one call, and an optional task_key to reuse a compatible child. If model is omitted, model selection uses the configured pin or normal routing hints. Calls return an asynchronous task reference; they do not wait for the child. Reusing the same task_key continues a compatible child and resumes a clarification-paused child when its checkpoint is available. Set fresh: true when the task needs a new child instead of reusing a matching session. Without a chat delivery thread, the child still runs asynchronously and its completion is recorded in the parent run log.

The returned task reference identifies the asynchronous child. Its result is delivered to the parent chat when a delivery thread is available; headless runs retain the result in the run log.

Why these are tools

Long tasks fall apart when an agent tries to hold everything in one head. Splitting work with to-dos and sub-agents helps in three ways:

  • Each sub-agent keeps useful local context for the same job instead of being respawned every turn.
  • The main thread keeps a high-level view of progress.
  • A failure in one branch does not spoil the rest.

Asking for clarification is a tool on purpose. It makes "I should ask the user" a visible decision the agent can be steered toward, instead of something that only happens by chance.

See also

  • Coder: the coding tools, most of them loaded through the coding skill.
  • Cron and scheduling: how background agent runs are scheduled.