agent-capabilities
CommandMatrix of agent capabilities and their specializations.
AI swarm deployment and coordination in cloud
> /plugin marketplace add ruvnet/agentic-flow> /plugin install agentic-flow@agentic-flow
name: flow-nexus-swarm description: AI swarm deployment and coordination in cloud
Deploy and manage AI agent swarms in the cloud.
mcp__flow-nexus__swarm_init({
topology: "hierarchical", // mesh, ring, star, hierarchical
maxAgents: 8,
strategy: "balanced" // balanced, specialized, adaptive
})mcp__flow-nexus__agent_spawn({
type: "researcher", // coder, analyst, optimizer, coordinator
name: "Lead Researcher",
capabilities: ["web_search", "analysis", "summarization"]
})mcp__flow-nexus__task_orchestrate({
task: "Build a REST API with authentication",
strategy: "parallel", // parallel, sequential, adaptive
maxAgents: 5,
priority: "high"
})// Get swarm status
mcp__flow-nexus__swarm_status()
// List active swarms
mcp__flow-nexus__swarm_list({ status: "active" })
// Scale swarm
mcp__flow-nexus__swarm_scale({ target_agents: 10 })
// Destroy swarm
mcp__flow-nexus__swarm_destroy({ swarm_id: "id" })// Use pre-built swarm template
mcp__flow-nexus__swarm_create_from_template({
template_name: "full-stack-dev",
overrides: {
maxAgents: 6,
strategy: "specialized"
}
})
// List available templates
mcp__flow-nexus__swarm_templates_list({
category: "quickstart" // specialized, enterprise, custom
})mcp__flow-nexus__swarm_init({ topology: "mesh", maxAgents: 5 })
mcp__flow-nexus__agent_spawn({ type: "researcher", name: "Lead" })
mcp__flow-nexus__agent_spawn({ type: "analyst", name: "Data Analyst" })
mcp__flow-nexus__task_orchestrate({ task: "Research ML trends" })mcp__flow-nexus__swarm_init({ topology: "hierarchical", maxAgents: 8 })
mcp__flow-nexus__agent_spawn({ type: "coordinator", name: "PM" })
mcp__flow-nexus__agent_spawn({ type: "coder", name: "Backend Dev" })
mcp__flow-nexus__agent_spawn({ type: "coder", name: "Frontend Dev" })
mcp__flow-nexus__task_orchestrate({ task: "Build e-commerce platform" })Production-ready AI agent orchestration with 66 self-learning agents, 213 MCP tools, and autonomous multi-agent swarms.
Matrix of agent capabilities and their specializations.
Complete guide to all 54 available agent types in Claude Flow.
Reviewed all command files in `.claude/commands/analysis/` directory to ensure proper usage of: - `mcp__claude-flow__*` tools…
Analyze performance bottlenecks in swarm operations and suggest optimizations.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.