/agent-coordination

Agent Coordination

Multi-agent setup, routing, and lifecycle management

Bespoke TierUtility & Infrastructure

Overview

Reference skill for setting up and running multi-agent workflows. Provides execution model selection (parallel, sequential, pipeline), agent roster templates, quality gate protocols, and dead-agent detection patterns.

What It Does

  • Selects execution model (parallel, sequential, or staged pipeline) based on a decision tree
  • Provides templates for agent rosters, orchestrator state files, and standing prompts
  • Enforces quality gates with max-3-retry escalation and specific feedback requirements
  • Manages agent lifecycle: registration, spawning, idle detection, respawning, and shutdown

Inputs

  • Workflow description
  • Number of agents
  • Interaction requirements

Outputs

  • Execution model recommendation
  • Orchestrator state file
  • Agent roster table
  • Standing prompt templates

Example

/agent-coordination

Building a newsletter pipeline where 5 persona agents independently score events and a coordinator merges results. Agent Coordination identifies this as parallel independent and scaffolds the roster, quality gates, and merge protocol.

Related Skills

/agent-memory

Agent Memory

Four-tier memory architecture for learning agents

/deep-planning

Deep Planning

Complex task into step-by-step execution plan

/ralph-execute

Ralph Execute

Long-running tasks that survive context loss

Deep Dives

Knowledge OS Guide

Ready to use /agent-coordination?

This skill ships with every Knowledge OS installation. Set up your system in 90 minutes.

View PricingAll 42 Skills

Built and maintained by Victor Sowers at STEEPWORKS