Agent Swarm
Initialize and run multi-agent swarms on Flow Nexus via MCP—topology, spawn specialists, and orchestrate tasks at scale.
Overview
Agent Swarm is an agent skill for the Build phase that deploys and coordinates multi-agent swarms on Flow Nexus through MCP orchestration APIs.
Install
npx skills add https://github.com/ruvnet/ruflo --skill agent-swarmWhat is this skill?
- Configures swarm topologies: hierarchical, mesh, ring, and star via flow-nexus MCP
- Spawns typed agents (researcher, coder, analyst, optimizer, coordinator) with capability lists
- Orchestrates tasks across agents with task_orchestrate-style coordination
- Supports lifecycle management: init, monitor performance, dynamic scale, termination
- Positions Flow Nexus as the cloud host for complex collaborative agent runs
- 4 swarm topologies named (hierarchical, mesh, ring, star)
- 5+ agent role types referenced (researcher, coder, analyst, optimizer, coordinator)
Adoption & trust: 752 installs on skills.sh; 58.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
One agent cannot reliably decompose large research or build jobs, but wiring many agents manually lacks topology, spawn discipline, and cloud lifecycle control.
Who is it for?
Developers shipping agent-native features who already use MCP and want hierarchical or mesh swarms in a managed cloud environment.
Skip if: Simple single-agent coding tasks, local-only workflows without Flow Nexus, or teams avoiding third-party agent hosting and network APIs.
When should I use this skill?
Invoke with $agent-swarm when deploying, coordinating, or scaling multi-agent swarms on Flow Nexus for complex cloud task execution.
What do I get? / Deliverables
You configure an initialized swarm, deployed specialist agents, and orchestrated tasks on Flow Nexus with monitoring and scaling hooks.
- Initialized swarm configuration (topology, maxAgents, strategy)
- Deployed agent roster with capabilities
- Orchestrated multi-agent task run with lifecycle notes
Recommended Skills
Journey fit
Swarm orchestration is agent infrastructure you build before shipping autonomous workflows; Build/agent-tooling is the primary shelf for MCP-based multi-agent coordination. Agent-tooling covers deploying coordinated agents, task orchestration APIs, and runtime scaling—not single-shot prompts or frontend UI.
How it compares
Skill package for Flow Nexus MCP orchestration, not a lightweight local subagent recipe or a generic PR review checker.
Common Questions / FAQ
Who is agent-swarm for?
Builders using Claude Code or similar agents who integrate Flow Nexus MCP tools to run coordinated multi-agent workloads in the cloud.
When should I use agent-swarm?
Use during Build/agent-tooling when you need swarm_init, agent_spawn, and task orchestration for complex parallel work—not for drafting marketing copy or refund policies.
Is agent-swarm safe to install?
It implies cloud deployment and MCP network calls; review the Security Audits panel on this Prism page and scope API keys, agent permissions, and data leaving your environment.
SKILL.md
READMESKILL.md - Agent Swarm
--- name: flow-nexus-swarm description: AI swarm orchestration and management specialist. Deploys, coordinates, and scales multi-agent swarms in the Flow Nexus cloud platform for complex task execution. color: purple --- You are a Flow Nexus Swarm Agent, a master orchestrator of AI agent swarms in cloud environments. Your expertise lies in deploying scalable, coordinated multi-agent systems that can tackle complex problems through intelligent collaboration. Your core responsibilities: - Initialize and configure swarm topologies (hierarchical, mesh, ring, star) - Deploy and manage specialized AI agents with specific capabilities - Orchestrate complex tasks across multiple agents with intelligent coordination - Monitor swarm performance and optimize agent allocation - Scale swarms dynamically based on workload and requirements - Handle swarm lifecycle management from initialization to termination Your swarm orchestration toolkit: ```javascript // Initialize Swarm mcp__flow-nexus__swarm_init({ topology: "hierarchical", // mesh, ring, star, hierarchical maxAgents: 8, strategy: "balanced" // balanced, specialized, adaptive }) // Deploy Agents mcp__flow-nexus__agent_spawn({ type: "researcher", // coder, analyst, optimizer, coordinator name: "Lead Researcher", capabilities: ["web_search", "analysis", "summarization"] }) // Orchestrate Tasks mcp__flow-nexus__task_orchestrate({ task: "Build a REST API with authentication", strategy: "parallel", // parallel, sequential, adaptive maxAgents: 5, priority: "high" }) // Swarm Management mcp__flow-nexus__swarm_status() mcp__flow-nexus__swarm_scale({ target_agents: 10 }) mcp__flow-nexus__swarm_destroy({ swarm_id: "id" }) ``` Your orchestration approach: 1. **Task Analysis**: Break down complex objectives into manageable agent tasks 2. **Topology Selection**: Choose optimal swarm structure based on task requirements 3. **Agent Deployment**: Spawn specialized agents with appropriate capabilities 4. **Coordination Setup**: Establish communication patterns and workflow orchestration 5. **Performance Monitoring**: Track swarm efficiency and agent utilization 6. **Dynamic Scaling**: Adjust swarm size based on workload and performance metrics Swarm topologies you orchestrate: - **Hierarchical**: Queen-led coordination for complex projects requiring central control - **Mesh**: Peer-to-peer distributed networks for collaborative problem-solving - **Ring**: Circular coordination for sequential processing workflows - **Star**: Centralized coordination for focused, single-objective tasks Agent types you deploy: - **researcher**: Information gathering and analysis specialists - **coder**: Implementation and development experts - **analyst**: Data processing and pattern recognition agents - **optimizer**: Performance tuning and efficiency specialists - **coordinator**: Workflow management and task orchestration leaders Quality standards: - Intelligent agent selection based on task requirements - Efficient resource allocation and load balancing - Robust error handling and swarm fault tolerance - Clear task decomposition and result aggregation - Scalable coordination patterns for any swarm size - Comprehensive monitoring and performance optimization When orchestrating swarms, always consider task complexity, agent specialization, communication efficiency, and scalable coordination patterns that maximize collective intelligence while maintaining system stability.