agent-coordination
Agent Coordination manages multi-agent workflows using Gas Town's hook-based distribution system, where persistent Crew agents and transient Polecat workers execute tasks assigned through a hierarchical hook structure governed by the GUPP principle. Use this skill when distributing work across agents, managing handoffs between workers, reviving stuck processes, or establishing role-based task hierarchies in collaborative AI systems.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/agent-coordination && cp -r /tmp/agent-coordination/library/methodologies/gastown/skills/agent-coordination ~/.claude/skills/agent-coordinationSKILL.md
- Managing agent handoffs - Nudging stuck agents - Coordinating Crew and Polecat workers - Setting up hook hierarchies ## Agent Types - **Crew**: Long-lived, named agents for persistent collaboration - **Polecats**: Transient workers with persistent identity but ephemeral sessions - **Dogs**: Deacon helpers for infrastructure tasks ## Hook Hierarchy Three-tier hook system (base -> role -> rig+role): 1. **Base hooks**: Apply to all agents 2. **Role hooks**: Apply to agents in a specific role 3. **Rig+Role hooks**: Apply to agents on a specific rig in a specific role ## Key Commands - `gt agents` - List available agents - `gt feed` - Feed work to an agent's hook - `gt handoff` - Hand off work between agents - `gt nudge` - Nudge a stuck agent - `gt seance` - Revive a dead agent session ## Tool Use Invoke via babysitter process: `methodologies/gastown/gastown-orchestrator` (assign-workers step)
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.