メニュー
Spawn a new agent with V3 capabilities
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | source-command-agents-spawn |
| description | Spawn a new agent with V3 capabilities |
Use this skill when the user asks to run the migrated source command agents-spawn.
Spawn a new agent with full V3 capabilities including neural patterns, memory integration, and swarm coordination.
npx Codex-flow agent spawn [options]
| Option | Short | Description | Default |
|---|---|---|---|
--type | -t | Agent type to spawn | Required |
--name | -n | Agent name/identifier | Auto-generated |
--provider | -p | AI provider (anthropic, openrouter, ollama) | anthropic |
--model | -m | Model to use | Provider default |
--task | Initial task for the agent | None | |
--timeout | Agent timeout in seconds | 300 | |
--auto-tools | Enable automatic tool usage | true |
npx Codex-flow agent spawn -t coder # Code implementation
npx Codex-flow agent spawn -t reviewer # Code review
npx Codex-flow agent spawn -t tester # Testing
npx Codex-flow agent spawn -t planner # Planning
npx Codex-flow agent spawn -t researcher # Research
npx Codex-flow agent spawn -t security-architect # Security design
npx Codex-flow agent spawn -t security-auditor # CVE remediation
npx Codex-flow agent spawn -t memory-specialist # AgentDB (150x-12,500x faster)
npx Codex-flow agent spawn -t performance-engineer # 2.49x-7.47x optimization
npx Codex-flow agent spawn -t core-architect # DDD design
npx Codex-flow agent spawn -t hierarchical-coordinator # Queen-led
npx Codex-flow agent spawn -t mesh-coordinator # P2P network
npx Codex-flow agent spawn -t adaptive-coordinator # Dynamic topology
npx Codex-flow agent spawn -t collective-intelligence-coordinator
npx Codex-flow agent spawn -t byzantine-coordinator # BFT consensus
npx Codex-flow agent spawn -t raft-manager # Leader-based
npx Codex-flow agent spawn -t gossip-coordinator # Eventual consistency
npx Codex-flow agent spawn -t crdt-synchronizer # CRDT replication
npx Codex-flow agent spawn -t quorum-manager # Quorum-based
npx Codex-flow agent spawn -t pr-manager # PR lifecycle
npx Codex-flow agent spawn -t code-review-swarm # Multi-agent review
npx Codex-flow agent spawn -t issue-tracker # Issue management
npx Codex-flow agent spawn -t release-manager # Release coordination
npx Codex-flow agent spawn -t workflow-automation # CI/CD automation
npx Codex-flow agent spawn -t sparc-coordinator # SPARC orchestration
npx Codex-flow agent spawn -t specification # Requirements
npx Codex-flow agent spawn -t pseudocode # Algorithm design
npx Codex-flow agent spawn -t architecture # System design
npx Codex-flow agent spawn -t refinement # Iterative improvement
# Spawn with custom name
npx Codex-flow agent spawn -t coder --name feature-bot
# Spawn with initial task
npx Codex-flow agent spawn -t researcher --task "Research React 19 features"
# Spawn with specific model
npx Codex-flow agent spawn -t architect -m Codex-3-opus-20240229
# Spawn with custom timeout
npx Codex-flow agent spawn -t tester --timeout 600
# Spawn using OpenRouter
npx Codex-flow agent spawn -t coder -p openrouter -m anthropic/Codex-3.5-sonnet
For actual execution, always use Codex's Task tool:
// Spawn ALL agents in ONE message for parallel execution
Task("Coder", "Implement authentication feature", "coder")
Task("Tester", "Write unit tests for auth", "tester")
Task("Reviewer", "Review auth implementation", "reviewer")
Use MCP tools only for swarm coordination setup:
mcp__ruflo__swarm_init({ topology: "hierarchical", maxAgents: 15 })
mcp__ruflo__agent_spawn({ type: "coordinator", name: "queen" })
Spawning coder agent: feature-bot
+-----------+----------------------------------+
| Property | Value |
+-----------+----------------------------------+
| ID | coder-lx7m9k2 |
| Type | coder |
| Name | feature-bot |
| Status | active |
| Created | 2026-01-08T03:30:00.000Z |
| Capabilities | code, debug, refactor, test |
+-----------+----------------------------------+
Agent feature-bot spawned successfully
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
Web browser automation with AI-optimized snapshots for Codex-flow agents