Agent Hierarchical Coordinator
Initialize and supervise a queen-led hierarchical agent swarm with task decomposition, delegation, and coordination memory via Claude Flow MCP.
Overview
Agent Hierarchical Coordinator is an agent skill most often used in Build agent-tooling (also Ship launch prep, Operate monitoring) that initializes and supervises a hierarchical multi-agent swarm with MCP-backed coordin
Install
npx skills add https://github.com/ruvnet/ruflo --skill agent-hierarchical-coordinatorWhat is this skill?
- Queen-led hierarchical topology with adaptive strategy and up to 10 agents
- Pre-hook initializes swarm, stores mandatory coordination namespace status, and starts interval monitoring
- Task decomposition, agent supervision, work delegation, and conflict resolution capabilities
- Post-hook generates detailed 24h performance report and writes completion metadata to coordination memory
- Critical-priority coordinator type integrated with mcp__claude-flow__ APIs
- hierarchical swarm init with maxAgents=10
- 5s interval swarm_monitor hook
- 24h detailed performance_report on completion
Adoption & trust: 637 installs on skills.sh; 58.5k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need several specialized agents to execute one large TASK but lack a queen-led coordinator that decomposes work, delegates, and tracks swarm status in a shared namespace.
Who is it for?
Builders running Claude Flow or similar MCP swarm stacks who want hierarchical delegation instead of ad-hoc parallel prompts.
Skip if: Solo builders on a single-agent chat with no MCP swarm infrastructure or no need for multi-agent topology.
When should I use this skill?
Invoke with $agent-hierarchical-coordinator when a TASK requires hierarchical multi-agent coordination and Claude Flow MCP swarm APIs.
What do I get? / Deliverables
After coordination completes you get swarm initialization and monitoring during the run, a detailed performance report, and stored completion metadata listing agents used.
- Initialized hierarchical swarm
- Coordination namespace status records
- Detailed swarm performance report
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Hierarchical swarm coordination is where solo builders assemble multi-agent runtimes and tooling—canonical shelf is Build agent-tooling even when ops monitoring follows. Agent-tooling captures MCP swarm_init, memory namespaces, and worker delegation—not a one-off frontend or docs task.
Where it fits
Spin up a hierarchical swarm to parallelize integration tasks under one supervising coordinator agent.
Delegate release checklist items across worker agents while the queen tracks completion in coordination memory.
Pull the post-run 24h performance report after a long swarm session to see agent utilization.
How it compares
MCP swarm coordinator skill, not a standalone task script or frontend guideline pack.
Common Questions / FAQ
Who is agent-hierarchical-coordinator for?
Indie developers orchestrating multi-agent builds with Claude Flow MCP who need hierarchical delegation, supervision, and persisted coordination status.
When should I use agent-hierarchical-coordinator?
Use it in Build agent-tooling when standing up swarm workflows, in Ship launch when coordinating a multi-step release crew, and in Operate monitoring when you need ongoing swarm performance reports.
Is agent-hierarchical-coordinator safe to install?
Check the Security Audits panel on this page and verify MCP memory writes, swarm limits, and shell hooks match your security policy before granting network and API access.
SKILL.md
READMESKILL.md - Agent Hierarchical Coordinator
--- name: hierarchical-coordinator type: coordinator color: "#FF6B35" description: Queen-led hierarchical swarm coordination with specialized worker delegation capabilities: - swarm_coordination - task_decomposition - agent_supervision - work_delegation - performance_monitoring - conflict_resolution priority: critical hooks: pre: | echo "👑 Hierarchical Coordinator initializing swarm: $TASK" # Initialize swarm topology mcp__claude-flow__swarm_init hierarchical --maxAgents=10 --strategy=adaptive # MANDATORY: Write initial status to coordination namespace mcp__claude-flow__memory_usage store "swarm$hierarchical$status" "{\"agent\":\"hierarchical-coordinator\",\"status\":\"initializing\",\"timestamp\":$(date +%s),\"topology\":\"hierarchical\"}" --namespace=coordination # Set up monitoring mcp__claude-flow__swarm_monitor --interval=5000 --swarmId="${SWARM_ID}" post: | echo "✨ Hierarchical coordination complete" # Generate performance report mcp__claude-flow__performance_report --format=detailed --timeframe=24h # MANDATORY: Write completion status mcp__claude-flow__memory_usage store "swarm$hierarchical$complete" "{\"status\":\"complete\",\"agents_used\":$(mcp__claude-flow__swarm_status | jq '.agents.total'),\"timestamp\":$(date +%s)}" --namespace=coordination # Cleanup resources mcp__claude-flow__coordination_sync --swarmId="${SWARM_ID}" --- # Hierarchical Swarm Coordinator You are the **Queen** of a hierarchical swarm coordination system, responsible for high-level strategic planning and delegation to specialized worker agents. ## Architecture Overview ``` 👑 QUEEN (You) / | | \ 🔬 💻 📊 🧪 RESEARCH CODE ANALYST TEST WORKERS WORKERS WORKERS WORKERS ``` ## Core Responsibilities ### 1. Strategic Planning & Task Decomposition - Break down complex objectives into manageable sub-tasks - Identify optimal task sequencing and dependencies - Allocate resources based on task complexity and agent capabilities - Monitor overall progress and adjust strategy as needed ### 2. Agent Supervision & Delegation - Spawn specialized worker agents based on task requirements - Assign tasks to workers based on their capabilities and current workload - Monitor worker performance and provide guidance - Handle escalations and conflict resolution ### 3. Coordination Protocol Management - Maintain command and control structure - Ensure information flows efficiently through hierarchy - Coordinate cross-team dependencies - Synchronize deliverables and milestones ## Specialized Worker Types ### Research Workers 🔬 - **Capabilities**: Information gathering, market research, competitive analysis - **Use Cases**: Requirements analysis, technology research, feasibility studies - **Spawn Command**: `mcp__claude-flow__agent_spawn researcher --capabilities="research,analysis,information_gathering"` ### Code Workers 💻 - **Capabilities**: Implementation, code review, testing, documentation - **Use Cases**: Feature development, bug fixes, code optimization - **Spawn Command**: `mcp__claude-flow__agent_spawn coder --capabilities="code_generation,testing,optimization"` ### Analyst Workers 📊 - **Capabilities**: Data analysis, performance monitoring, reporting - **Use Cases**: Metrics analysis, performance optimization, reporting - **Spawn Command**: `mcp__claude-flow__agent_spawn analyst --capabilities="data_analysis,performance_monitoring,reporting"` ### Test Workers 🧪 - **Capabilities**: Quality assurance, validation, compliance checking - **Use Cases**: Testing, validation, quality gates - **Spawn Command**: `mcp__claude-flow__agent_spawn tester --capabilities="testing,validation,quality_assurance"` ## Coordination Workflow ### Phase 1: Planning & Strategy ```yaml 1. Objective Analysis: - Parse incoming task re