MCPInstall

v3 swarm coordination

15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timeline.

Installs
1.1K
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/ruvnet/ruflo --skill v3-swarm-coordination
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads v3 swarm coordination automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

V3 Swarm Coordination

What This Skill Does

Orchestrates the complete 15-agent hierarchical mesh swarm for claude-flow v3 implementation, coordinating parallel execution across domains while maintaining dependencies and timeline adherence.

Quick Start

# Initialize 15-agent v3 swarm
Task("Swarm initialization", "Initialize hierarchical mesh for v3 implementation", "v3-queen-coordinator")

# Security domain (Phase 1 - Critical priority)
Task("Security architecture", "Design v3 threat model and security boundaries", "v3-security-architect")
Task("CVE remediation", "Fix CVE-1, CVE-2, CVE-3 vulnerabilities", "security-auditor")
Task("Security testing", "Implement TDD security framework", "test-architect")

# Core domain (Phase 2 - Parallel execution)
Task("Memory unification", "Implement AgentDB 150x improvement", "v3-memory-specialist")
Task("Integration architecture", "Deep agentic-flow@alpha integration", "v3-integration-architect")
Task("Performance validation", "Validate 2.49x-7.47x targets", "v3-performance-engineer")

15-Agent Swarm Architecture

Hierarchical Mesh Topology

                    👑 QUEEN COORDINATOR
                         (Agent #1)
                             │
        ┌────────────────────┼────────────────────┐
        │                   │                    │
   🛡️ SECURITY         🧠 CORE              🔗 INTEGRATION
   (Agents #2-4)       (Agents #5-9)        (Agents #10-12)
        │                   │                    │
        └────────────────────┼────────────────────┘
                             │
        ┌────────────────────┼────────────────────┐
        │                   │                    │
   🧪 QUALITY          ⚡ PERFORMANCE        🚀 DEPLOYMENT
   (Agent #13)         (Agent #14)          (Agent #15)

Agent Roster

IDAgentDomainPhaseResponsibility
1Queen CoordinatorOrchestrationAllGitHub issues, dependencies, timeline
2Security ArchitectSecurityFoundationThreat modeling, CVE planning
3Security ImplementerSecurityFoundationCVE fixes, secure patterns
4Security TesterSecurityFoundationTDD security testing
5Core ArchitectCoreSystemsDDD architecture, coordination
6Core ImplementerCoreSystemsCore module implementation
7Memory SpecialistCoreSystemsAgentDB unification
8Swarm SpecialistCoreSystemsUnified coordination engine
9MCP SpecialistCoreSystemsMCP server optimization
10Integration ArchitectIntegrationIntegrationagentic-flow@alpha deep integration
11CLI/Hooks DeveloperIntegrationIntegrationCLI modernization
12Neural/Learning DevIntegrationIntegrationSONA integration
13TDD Test EngineerQualityAllLondon School TDD
14Performance EngineerPerformanceOptimizationBenchmarking validation
15Release EngineerDeploymentReleaseCI/CD and v3.0.0 release

Implementation Phases

Phase 1: Foundation (Week 1-2)

Active Agents: #1, #2-4, #5-6

const phase1 = async () => {
  // Parallel security and architecture foundation
  await Promise.all([
    // Security domain (critical priority)
    Task("Security architecture", "Complete threat model and security boundaries", "v3-security-architect"),
    Task("CVE-1 fix", "Update vulnerable dependencies", "security-implementer"),
    Task("CVE-2 fix", "Replace weak password hashing", "security-implementer"),
    Task("CVE-3 fix", "Remove hardcoded credentials", "security-implementer"),
    Task("Security testing", "TDD London School security framework", "test-architect"),

    // Core architecture foundation
    Task("DDD architecture", "Design domain boundaries and structure", "core-architect"),
    Task("Type modernization", "Update type system for v3", "core-implementer")
  ]);
};

Phase 2: Core Systems (Week 3-6)

Active Agents: #1, #5-9, #13

const phase2 = async () => {
  // Parallel core system implementation
  await Promise.all([
    Task("Memory unification", "Implement AgentDB with 150x-12,500x improvement", "v3-memory-specialist"),
    Task("Swarm coordination", "Merge 4 coordination systems into unified engine", "swarm-specialist"),
    Task("MCP optimization", "Optimize MCP server performance", "mcp-specialist"),
    Task("Core implementation", "Implement DDD modular architecture", "core-implementer"),
    Task("TDD core tests", "Comprehensive test coverage for core systems", "test-architect")
  ]);
};

Phase 3: Integration (Week 7-10)

Active Agents: #1, #10-12, #13-14

const phase3 = async () => {
  // Parallel integration and optimization
  await Promise.all([
    Task("agentic-flow integration", "Eliminate 10,000+ duplicate lines", "v3-integration-architect"),
    Task("CLI modernization", "Enhance CLI with hooks system", "cli-hooks-developer"),
    Task("SONA integration", "Implement <0.05ms learning adaptation", "neural-learning-developer"),
    Task("Performance benchmarking", "Validate 2.49x-7.47x targets", "v3-performance-engineer"),
    Task("Integration testing", "End-to-end system validation", "test-architect")
  ]);
};

Phase 4: Release (Week 11-14)

Active Agents: All 15

const phase4 = async () => {
  // Full swarm final optimization
  await Promise.all([
    Task("Performance optimization", "Final optimization pass", "v3-performance-engineer"),
    Task("Release preparation", "CI/CD pipeline and v3.0.0 release", "release-engineer"),
    Task("Final testing", "Complete test coverage validation", "test-architect"),

    // All agents: Final polish and optimization
    ...agents.map(agent =>
      Task("Final polish", `Agent ${agent.id} final optimization`, agent.name)
    )
  ]);
};

Coordination Patterns

Dependency Management

class DependencyCoordination {
  private dependencies = new Map([
    // Security first (no dependencies)
    [2, []], [3, [2]], [4, [2, 3]],

    // Core depends on security foundation
    [5, [2]], [6, [5]], [7, [5]], [8, [5, 7]], [9, [5]],

    // Integration depends on core systems
    [10, [5, 7, 8]], [11, [5, 10]], [12, [7, 10]],

    // Quality and performance cross-cutting
    [13, [2, 5]], [14, [5, 7, 8, 10]], [15, [13, 14]]
  ]);

  async coordinateExecution(): Promise<void> {
    const completed = new Set<number>();

    while (completed.size < 15) {
      const ready = this.getReadyAgents(completed);

      if (ready.length === 0) {
        throw new Error('Deadlock detected in dependency chain');
      }

      // Execute ready agents in parallel
      await Promise.all(ready.map(agentId => this.executeAgent(agentId)));

      ready.forEach(id => completed.add(id));
    }
  }
}

GitHub Integration

class GitHubCoordination {
  async initializeV3Milestone(): Promise<void> {
    await gh.createMilestone({
      title: 'Claude-Flow v3.0.0 Implementation',
      description: '15-agent swarm implementation of 10 ADRs',
      dueDate: this.calculate14WeekDeadline()
    });
  }

  async createEpicIssues(): Promise<void> {
    const epics = [
      { title: 'Security Overhaul (CVE-1,2,3)', agents: [2, 3, 4] },
      { title: 'Memory Unification (AgentDB)', agents: [7] },
      { title: 'agentic-flow Integration', agents: [10] },
      { title: 'Performance Optimization', agents: [14] },
      { title: 'DDD Architecture', agents: [5, 6] }
    ];

    for (const epic of epics) {
      await gh.createIssue({
        title: epic.title,
        labels: ['epic', 'v3', ...epic.agents.map(id => `agent-${id}`)],
        assignees: epic.agents.map(id => this.getAgentGithubUser(id))
      });
    }
  }

  async trackProgress(): Promise<void> {
    // Hourly progress updates from each agent
    setInterval(async () => {
      for (const agent of this.agents) {
        await this.postAgentProgress(agent);
      }
    }, 3600000); // 1 hour
  }
}

Communication Bus

class SwarmCommunication {
  private bus = new QuicSwarmBus({
    maxAgents: 15,
    messageTimeout: 30000,
    retryAttempts: 3
  });

  async broadcastToSecurityDomain(message: SwarmMessage): Promise<void> {
    await this.bus.broadcast(message, {
      targetAgents: [2, 3, 4],
      priority: 'critical'
    });
  }

  async coordinateCoreSystems(message: SwarmMessage): Promise<void> {
    await this.bus.broadcast(message, {
      targetAgents: [5, 6, 7, 8, 9],
      priority: 'high'
    });
  }

  async notifyIntegrationTeam(message: SwarmMessage): Promise<void> {
    await this.bus.broadcast(message, {
      targetAgents: [10, 11, 12],
      priority: 'medium'
    });
  }
}

Performance Coordination

Parallel Efficiency Monitoring

class EfficiencyMonitor {
  async measureParallelEfficiency(): Promise<EfficiencyReport> {
    const agentUtilization = await this.measureAgentUtilization();
    const coordinationOverhead = await this.measureCoordinationCost();

    return {
      totalEfficiency: agentUtilization.average,
      target: 0.85, // >85% utilization
      achieved: agentUtilization.average > 0.85,
      bottlenecks: this.identifyBottlenecks(agentUtilization),
      recommendations: this.generateOptimizations()
    };
  }
}

Load Balancing

class SwarmLoadBalancer {
  async balanceWorkload(): Promise<void> {
    const workloads = await this.analyzeAgentWorkloads();

    for (const [agentId, load] of workloads.entries()) {
      if (load > this.getCapacityThreshold(agentId)) {
        await this.redistributeWork(agentId);
      }
    }
  }

  async redistributeWork(overloadedAgent: number): Promise<void> {
    const availableAgents = this.getAvailableAgents();
    const tasks = await this.getAgentTasks(overloadedAgent);

    // Redistribute tasks to available agents
    for (const task of tasks) {
      const bestAgent = this.selectOptimalAgent(task, availableAgents);
      await this.reassignTask(task, bestAgent);
    }
  }
}

Success Metrics

Swarm Coordination

  • Parallel Efficiency: >85% agent utilization time
  • Dependency Resolution: Zero deadlocks or blocking issues
  • Communication Latency: <100ms inter-agent messaging
  • Timeline Adherence: 14-week delivery maintained
  • GitHub Integration: <4h automated issue response

Implementation Targets

  • ADR Coverage: All 10 ADRs implemented successfully
  • Performance: 2.49x-7.47x Flash Attention achieved
  • Search: 150x-12,500x AgentDB improvement validated
  • Code Reduction: <5,000 lines (vs 15,000+)
  • Security: 90/100 security score achieved

Related V3 Skills

  • v3-security-overhaul - Security domain coordination
  • v3-memory-unification - Memory system coordination
  • v3-integration-deep - Integration domain coordination
  • v3-performance-optimization - Performance domain coordination

Usage Examples

Initialize Complete V3 Swarm

# Queen Coordinator initializes full swarm
Task("V3 swarm initialization",
     "Initialize 15-agent hierarchical mesh for complete v3 implementation",
     "v3-queen-coordinator")

Phase-based Execution

# Phase 1: Security-first foundation
npm run v3:phase1:security

# Phase 2: Core systems parallel
npm run v3:phase2:core-systems

# Phase 3: Integration and optimization
npm run v3:phase3:integration

# Phase 4: Release preparation
npm run v3:phase4:release

FAQ

What does the v3 swarm coordination skill do?

15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timeline.

How do I install v3 swarm coordination?

Run npx skills add https://github.com/ruvnet/ruflo --skill v3-swarm-coordination in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/v3-swarm-coordination/ (personal) or .claude/skills/v3-swarm-coordination/ (project).

Which AI agents can use v3 swarm coordination?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is v3 swarm coordination safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains v3 swarm coordination?

It is published by ruvnet in ruvnet/ruflo. It has 1,123 recorded installs.

More from ruvnet/ruflo

View all →

ruflo

ruvnet/ruflo

Open the skill to read its SKILL.md instructions.

4K installs

Multi-agent swarm coordination for complex tasks. Uses hierarchical topology with specialized agents to break down and execute complex work across multiple files and modules. Use when: 3+ files need changes, new feature implementation, cross-module refactoring, API changes with tests, security-related changes, performance optimization across codebase, database schema changes. Skip when: single file edits, simple bug fixes (1-2 lines), documentation updates, configuration changes, quick exploration.

Agent skill for arch-system-design - invoke with $agent-arch-system-design

1.4K installs

agent-workflow

ruvnet/ruflo

Agent skill for workflow - invoke with $agent-workflow

security-audit

ruvnet/ruflo

Comprehensive security scanning and vulnerability detection. Includes input validation, path traversal prevention, CVE detection, and secure coding pattern enforcement. Use when: authentication implementation, authorization logic, payment processing, user data handling, API endpoint creation, file upload handling, database queries, external API integration. Skip when: read-only operations on public data, internal development tooling, static documentation, styling changes.

Security1.4K installs

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

Popular security skills

View category →

azure-compliance

microsoft/azure-skills

Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.

OfficialSecurity567K installs

minimal-run-and-audit

lllllllama/rigorpilot-skills

Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized reprooutputs/ files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

Security477.4K installs

seo-audit

coreyhaines31/marketingskills

When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," "indexing issues," "stuck on page 2," "striking distance keywords," "title tag rewrite," "low CTR," "local SEO," "Google Business Profile," or "map pack." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema. For AI search optimization, see ai-seo.

Security238.7K installs

firebase-security-rules-auditor

firebase/agent-skills

Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership checks. Use when auditing/reviewing rules, running red-team rule assessments, or scoring against auditor checklists. Don't use for Firebase CLI (login, deploy), Auth, Crashlytics, Remote Config, or database queries.

OfficialSecurity139.1K installs

audit

pbakaus/impeccable

Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.

Security81.9K installs

competitors

coreyhaines31/marketingskills

When the user wants to create competitor comparison or alternative pages for SEO and buyer-facing use. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'competitor teardown,' 'audit our competitor pages,' 'are our comparison pages out of date,' or 'competitive asset audit.' Use this for any content that positions your product against competitors. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. For auditing existing claims (not researching competitors from scratch, which is competitor-profiling; not technical SEO on these pages, which is seo-audit), use the asset audit here. For internal battle cards and sales-specific competitor docs, see sales-enablement.

Security79.3K installs