---
name: orchestrating
description: Use when two or more independent lanes can run in parallel, an output-only lane protects lead context from raw payload, or a handoff or durable run needs coordination.
when_to_use: "Trigger phrases: run these in parallel, fan out, spawn agents, split the work, delegate lanes, review while I build, several independent files or services to inspect at once."
metadata:
  short-description: Parallel lanes, output-only lanes, and delegation coordination
---

# Orchestrating

Delegate only when coordination value exceeds its overhead. Keep a no-op, one
bounded task, or sequential dependency path inline. Scan dependencies,
boundaries, ownership, and oracle before dispatch.

Native agents are the default for matching lanes. Use one to three direct
children with fresh, bounded context.

For independent lanes whose results cannot reshape one another, issue native
spawn calls consecutively without intervening inspection or waits. Continue
independent lead work, then join every returned identity until completion,
failure, or confirmed cancellation.

Before dispatch, read
[native dispatch and lane lifecycle](references/native-dispatch.md) and use
only the active harness's call shape. One bounded output-only lane may use one
fresh-context child returning `verdict`, `evidence`, `uncertainty`, and `next`.
Keep bulky raw payloads in an artifact.

Run verbose checks through the
[run receipt tool](../verify-and-finish/references/run-receipt.md), which keeps
full output and exit status. Report command, exit status, result counts, and
log path; disclose filtering.

Route unknown causes through `systematic-debugging`, unresolved contracts
through `design-and-plan`, external evidence through `evidence-research`,
cross-provider risk through `independent-review`, and effects through
`safe-effects`.

Preflight tools, authentication, permissions, and write authority. Brief the
outcome, bounded and disjoint ownership, constraints, oracle, prohibited scope,
return condition, nested-delegation limit, and an advisory time budget; keep
a hard timeout where one is needed. Shared guidance has one writer;
shared writes and Git stay lead-owned.

For non-trivial routing, honor an operator-selected access workflow, including
an approved external route, before native ranking. Otherwise, when
`~/.config/megapowers/agent-capabilities.md`
([template](assets/agent-capabilities.md)) exists, read it once per session
for eligible bindings; without it, use native defaults. Apart from a bound
independent reviewer, the registry cannot authorize access, disclosure,
permissions, writes, or effects.

Before review dispatch, set its scope and correction-round budget. Track each
review until terminal or cancellation is confirmed. Target follow-ups at fixes
and affected boundaries. A spent budget leaves unresolved findings open; it
never converts them into approval.

Give related failures to one lane so it sees their shared cause. When lanes
race on one question, fix the selection rule before spawning. Join all
identities before synthesis. A missing or silent result is a gap, never a
pass. Treat each report as a claim and check its evidence before using it: re-run
load-bearing claims yourself and sample the rest. When two lanes repeat one shortcut, fix the brief or add a
check. After a scope change, scan again with delta-only follow-ups.

Ordinary handoffs use inline inspection plus `verify-and-finish`; only a
currently approved goal surviving interruption uses `autonomous-run`. Stop at
the oracle.