메뉴
Capability matrix for all agent types
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | source-command-agents-agent-capabilities |
| description | Capability matrix for all agent types |
Use this skill when the user asks to run the migrated source command agents-agent-capabilities.
Matrix of agent capabilities and their specializations for Codex Flow V3.
| Agent | Code | Test | Review | Design | Research |
|---|---|---|---|---|---|
| coder | 5 | 3 | 2 | 2 | 2 |
| reviewer | 3 | 2 | 5 | 3 | 2 |
| tester | 2 | 5 | 2 | 1 | 2 |
| planner | 2 | 1 | 2 | 5 | 4 |
| researcher | 2 | 1 | 2 | 3 | 5 |
| Agent | Security | Memory | Performance | Architecture |
|---|---|---|---|---|
| security-architect | 5 | 2 | 3 | 5 |
| security-auditor | 5 | 2 | 2 | 3 |
| memory-specialist | 3 | 5 | 4 | 3 |
| performance-engineer | 2 | 3 | 5 | 4 |
| core-architect | 3 | 3 | 3 | 5 |
| Agent | Coordination | Consensus | Scaling | Fault Tolerance |
|---|---|---|---|---|
| hierarchical-coordinator | 5 | 4 | 4 | 4 |
| mesh-coordinator | 4 | 4 | 5 | 4 |
| adaptive-coordinator | 5 | 4 | 5 | 4 |
| collective-intelligence-coordinator | 4 | 5 | 4 | 4 |
| Agent | PR | Issues | CI/CD | Release | Review |
|---|---|---|---|---|---|
| pr-manager | 5 | 3 | 2 | 3 | 4 |
| code-review-swarm | 4 | 2 | 2 | 2 | 5 |
| issue-tracker | 2 | 5 | 2 | 2 | 2 |
| release-manager | 3 | 3 | 4 | 5 | 2 |
| workflow-automation | 2 | 3 | 5 | 4 | 2 |
| Level | Description |
|---|---|
| 5 | Expert - Primary specialization |
| 4 | Advanced - Strong capability |
| 3 | Intermediate - Good capability |
| 2 | Basic - Limited capability |
| 1 | Minimal - Not a focus |
| Capability | Agents | Performance Gain |
|---|---|---|
| Flash Attention | memory-specialist, performance-engineer | 2.49x-7.47x |
| HNSW Search | memory-specialist | 150x-12,500x |
| Quantization | performance-engineer | 50-75% memory |
| SONA Adaptation | sona-learning-optimizer | <0.05ms |
| Agent | BFT | Raft | Gossip | CRDT |
|---|---|---|---|---|
| byzantine-coordinator | 5 | 2 | 2 | 2 |
| raft-manager | 2 | 5 | 2 | 2 |
| gossip-coordinator | 2 | 2 | 5 | 3 |
| crdt-synchronizer | 2 | 2 | 3 | 5 |
| quorum-manager | 4 | 4 | 3 | 3 |
coder: Read, Write, Edit, MultiEdit, Glob, Grep, Bash
reviewer: Read, Glob, Grep
tester: Read, Write, Bash, Glob
hierarchical-coordinator: mcp__ruflo__swarm_*, mcp__ruflo__agent_*
mesh-coordinator: mcp__ruflo__swarm_*, mcp__ruflo__coordination_*
adaptive-coordinator: mcp__ruflo__topology_*, mcp__ruflo__swarm_*
pr-manager: mcp__github__*, Bash (gh CLI)
code-review-swarm: mcp__github__*, mcp__ruflo__swarm_*
release-manager: mcp__github__*, mcp__ruflo__workflow_*
# List all capabilities for an agent type
npx Codex-flow agent spawn -t coder --help
# View agent definition
cat .Codex/agents/core/coder.md
security-architect - Design and threat modelingsecurity-auditor - Vulnerability assessmentsecurity-manager - Consensus securityperformance-engineer - Optimizationmemory-specialist - Memory/search optimizationperformance-analyzer - Bottleneck analysishierarchical-coordinator - Complex hierarchical tasksmesh-coordinator - Research and explorationadaptive-coordinator - Dynamic requirementspr-manager - PR lifecyclecode-review-swarm - Comprehensive reviewsworkflow-automation - CI/CD automationMaster 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