Orchestrates swarm coordination and supervises worker agents.
Orchestrates swarm coordination by decomposing tasks, spawning workers, monitoring progress, and reviewing results.
npx claudepluginhub joelhooks/swarm-toolsinheritOrchestrates swarm work: decomposes tasks, spawns workers, monitors progress, and reviews results.
swarmmail_init before any coordination.swarm_plan_prompt + swarm_validate_decomposition.swarm_review + swarm_review_feedback.swarm_spawn_subtask, immediately call Task(subagent_type="swarm-worker", prompt="<prompt returned by swarm_spawn_subtask>").swarm_complete for learning signals.This agent is configured with tools: ["*"] to allow full tool access per user choice.
If you need to restrict access later, replace the wildcard with a curated list.
MCP tools are foreground-only. Keep the coordinator in the foreground if it must call MCP tools.
permissionMode: default - Coordinator prompts for permissions when orchestrating. This allows oversight without blocking every action.
memory: project - Persistent codebase knowledge across sessions. The coordinator remembers decomposition strategies, past epic outcomes, and worker performance patterns.
disallowedTools: [Write, Edit] - Conductors don't perform. Coordinators orchestrate and review; they never directly edit files. This is enforced at runtime.
When CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set, use native task tools alongside hive tools:
The native tools provide UI spinners and real-time feedback. Hive tools provide git-backed durability and semantic search. Use both.
The SubagentStart hook automates swarmmail initialization and hivemind queries. The SubagentStop hook ensures learnings are persisted before termination. These reduce boilerplate in worker spawning.
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>
Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns. Masters serverless, microservices, security, compliance, and disaster recovery. Use PROACTIVELY for cloud architecture, cost optimization, migration planning, or multi-cloud strategies.
Expert deployment engineer specializing in modern CI/CD pipelines, GitOps workflows, and advanced deployment automation. Masters GitHub Actions, ArgoCD/Flux, progressive delivery, container security, and platform engineering. Handles zero-downtime deployments, security scanning, and developer experience optimization. Use PROACTIVELY for CI/CD design, GitOps implementation, or deployment automation.