Agent Mesh Coordinator

This coordinator sets up a peer-to-peer mesh network where agents communicate directly without a single point of control. It uses gossip protocols for information sharing, Byzantine fault tolerance for consensus, and supports work stealing plus DHT-based task distribution. You'd reach for this when you need a swarm that can lose a third of its nodes and keep running, or when centralized coordination becomes a bottleneck. The implementation hooks into claude-flow's DAA tools for peer messaging and consensus voting. Fair warning, the complexity overhead is real. Most tasks don't need this level of resilience, but for long-running distributed work where reliability matters more than simplicity, the tradeoff makes sense.

skills.sh installs: 1.1K
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill agent-mesh-coordinator --agent claude-code

Installs into .claude/skills of the current project.

Files

name: mesh-coordinator type: coordinator
color: "#00BCD4" description: Peer-to-peer mesh network swarm with distributed decision making and fault tolerance capabilities:

distributed_coordination
peer_communication
fault_tolerance
consensus_building
load_balancing
network_resilience priority: high hooks: pre: | echo "🌐 Mesh Coordinator establishing peer network: $TASK"
Initialize mesh topology
mcp__claude-flow__swarm_init mesh --maxAgents=12 --strategy=distributed
Set up peer discovery and communication
mcp__claude-flow__daa_communication --from="mesh-coordinator" --to="all" --message="{"type":"network_init","topology":"mesh"}"
Initialize consensus mechanisms
mcp__claude-flow__daa_consensus --agents="all" --proposal="{"coordination_protocol":"gossip","consensus_threshold":0.67}"
Store network state
mcp__claude-flow__memory_usage store "mesh:network:${TASK_ID}" "$(date): Mesh network initialized" --namespace=mesh post: | echo "✨ Mesh coordination complete - network resilient"
Generate network analysis
mcp__claude-flow__performance_report --format=json --timeframe=24h