maestro-orchestration

name	maestro-orchestration
model	opus
description	Conductor agent pattern that decomposes complex tasks, dispatches specialist sub-agents, manages dependencies, and synthesizes results into a unified deliverable. Use when: 'coordinate multiple specialist agents', 'orchestrate a complex multi-phase task', 'run a conductor pattern across agents', 'this task needs live agent coordination', 'decompose and dispatch to sub-agents'.
category	agent-orchestration
triggers	["coordinate multiple specialist agents","orchestrate a complex multi-phase task","run a conductor pattern across agents","decompose and dispatch to sub-agents"]
tier	1
agents	["primary"]
tool_dependencies	["file_system"]
inputs	[{"name":"objective","type":"string","description":"The complex task or objective that requires multi-agent coordination","required":true},{"name":"available_agents","type":"string[]","description":"List of specialist agent types available for dispatch (e.g., scout, architect, kraken, arbiter)","required":false}]
outputs	[{"name":"synthesis","type":"string","description":"Unified orchestration report with task decomposition, agent outputs, conflict resolutions, and integrated deliverables"}]

Maestro Orchestration

Purpose: Act as a conductor agent that decomposes complex objectives into subtasks, dispatches specialist sub-agents with appropriate isolation and model routing, manages inter-agent dependencies, resolves conflicts between agent outputs, and synthesizes results into a coherent deliverable.

---

I. When to Use

• A task requires multiple specialist capabilities (research + implementation + validation)
• Work has both independent tracks (parallelizable) and dependent phases (sequential)
• The objective is too complex for a single agent pass -- it needs decomposition and coordination
• You need live conflict resolution when parallel agents produce contradictory outputs
• Multi-repo or multi-package work where different agents own different scopes

---

II. Orchestration Patterns

Pattern A: Hierarchical (Default for Implementation)

Maestro
  +-- architect  (plan)
  +-- kraken     (implement)
  +-- arbiter    (validate)

Best when the task has a clear plan-build-verify shape.

Pattern B: Pipeline (Linear Dependency)

scout --> architect --> kraken --> arbiter --> herald

Best when each phase depends strictly on the prior phase's output.

Pattern C: Swarm (Parallel Research)

Maestro
  +-- scout   (internal codebase)
  +-- oracle  (external research)
  +-- scout   (pattern analysis)
  --> synthesize all results

Best for broad information gathering before a decision.

Pattern D: Generator-Critic (Iterative Refinement)

architect --> critic --> architect --> critic --> final

Best for high-quality outputs that benefit from review cycles.

Pattern E: Jury (High-Stakes Decisions)

critic_1 --+
critic_2 --+--> majority vote --> decision
critic_3 --+

Best for architecture decisions or security reviews where multiple perspectives reduce risk.

---

III. Workflow

Step 1: Task Decomposition

Before dispatching any agent, decompose the objective:

1. Parse the objective into discrete subtasks
2. Map dependencies between subtasks (which must complete before others can start)
3. Identify parallelism -- subtasks with no dependencies between them can run concurrently
4. Select pattern from Section II based on the dependency graph shape

Step 2: Agent-to-Task Assignment