Agent Coordination

May 23, 2026 ยท View on GitHub

Beyond doing the work, the agent has tools for organising the work - planning multi-step jobs, delegating to specialists, spawning subagents, and pausing to ask the user when something is genuinely ambiguous.

Tools in the family

ToolWhat it does
todo_writeMaintain a structured TODO list across a long task. Marked done as work progresses.
spawn_subagentSpin up a fresh agent with its own context window for a self-contained subtask.
spawn_worker_threadBackground work that doesn't need to block the main conversation.
delegateHand a task to a specialist (e.g. an archetype with different prompts/tools/permissions).
archetype_delegationRoute to a named archetype - coder, researcher, planner, etc.
skill_delegationHand off to a skill installed in the workspace.
ask_clarificationPause and ask the user a precise question instead of guessing.
plan_exitExit a planning phase and start executing.
check_onboarding_status / complete_onboardingGate behaviour on whether the user has finished onboarding.

spawn_subagent and archetype delegation calls accept an optional model field for a one-off exact model pin. If it is omitted, the harness uses config-level per-agent pins when present and otherwise falls back to the normal model-routing hints.

Why these are tools, not implicit behaviour

Long tasks fall apart when the agent tries to keep everything in one head. Splitting work via TODOs and subagents means:

  • Each subagent gets a clean context - fewer tokens, fewer distractions.
  • The main thread keeps a high-level view of progress.
  • Failures in one branch don't poison the rest.

Asking for clarification is a tool too, on purpose: it makes "I should ask the user" a visible decision the agent can be steered toward, not an emergent behaviour.

See also

  • Coder - what a coder-archetype subagent typically uses.
  • Subconscious Loop - the always-on background agent thread.