메뉴
COC template implementation reference — how the five layers are implemented in Kailash COC templates (agents, skills, rules, hooks, commands). Use when asking about template structure, not COC concepts (use co-reference for specs).
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
Kailash DataFlow - zero-config data operations framework with automatic model-to-node generation and Data Fabric Engine. Use when asking about 'database operations', 'DataFlow', 'database models', 'CRUD operations', 'bulk operations', 'database queries', 'database migrations', 'multi-tenancy', 'multi-instance', 'database transactions', 'PostgreSQL', 'MySQL', 'SQLite', 'MongoDB', 'pgvector', 'vector search', 'document database', 'RAG', 'semantic search', 'existing database', 'database performance', 'database deployment', 'database testing', 'TDD with databases', 'external data sources', 'data products', 'db.source', 'db.product', 'db.start', 'fabric engine', 'source adapters', 'REST source', 'webhooks', or 'data fabric'. DataFlow is NOT an ORM - it generates 11 workflow nodes per SQL model, 8 nodes for MongoDB, and 3 nodes for vector operations.
Kailash Nexus - zero-config multi-channel platform for deploying workflows as API + CLI + MCP simultaneously. Use when asking about 'Nexus', 'multi-channel', 'platform deployment', 'API deployment', 'CLI deployment', 'MCP deployment', 'unified sessions', 'workflow deployment', 'production deployment', 'API gateway', 'session management', 'health monitoring', 'enterprise platform', 'plugins', 'event system', or 'workflow registration'. Also covers K8s integration: 'K8s probes', 'healthz', 'readyz', 'startup probe', 'ProbeManager', 'ProbeState', 'OpenAPI', 'openapi.json', 'OpenApiGenerator', 'security headers', 'CSRF middleware', 'CSRFMiddleware', 'SecurityHeadersMiddleware', 'middleware presets', 'Preset', or 'HSTS'.
Kailash Kaizen - production-ready AI agent framework with signature-based programming, multi-agent coordination, and enterprise features. Use when asking about 'AI agents', 'agent framework', 'BaseAgent', 'multi-agent systems', 'agent coordination', 'signatures', 'agent signatures', 'RAG agents', 'vision agents', 'audio agents', 'multimodal agents', 'agent prompts', 'prompt optimization', 'chain of thought', 'ReAct pattern', 'Planning agent', 'PEV agent', 'Tree-of-Thoughts', 'pipeline patterns', 'supervisor-worker', 'router pattern', 'ensemble pattern', 'blackboard pattern', 'parallel execution', 'agent-to-agent communication', 'A2A protocol', 'streaming agents', 'agent testing', 'agent memory', 'agentic workflows', 'AgentRegistry', 'OrchestrationRuntime', 'distributed agents', 'agent registry', '100+ agents', 'capability discovery', 'fault tolerance', 'health monitoring', 'trust protocol', 'EATP', 'TrustedAgent', 'trust chains', 'secure messaging', 'enterprise trust', 'credential rotation', 'trust verificati
Kailash cheatsheets: patterns, nodes, workflows, cycles, performance, security, multi-tenancy, saga, custom nodes.
Kailash dev guides: custom nodes, MCP, async, testing, deployment, RAG, security, monitoring, SDK internals.
Workflow templates: finance, healthcare, logistics, manufacturing, retail, ETL, RAG, document processing, API.
| name | coc-reference |
| description | COC template implementation reference — how the five layers are implemented in Kailash COC templates (agents, skills, rules, hooks, commands). Use when asking about template structure, not COC concepts (use co-reference for specs). |
| tools | ["Read","Glob","Grep"] |
How the COC five-layer architecture is implemented in the Kailash COC template repos. For COC spec/concepts (fault lines, value inversion, autonomous execution), see co-reference/coc-spec.md.
| CO Layer | COC Artifact Type | Count | Purpose |
|---|---|---|---|
| L1 Intent | Agents | 30+ | Specialized domain experts |
| L2 Context | Skills + CLAUDE.md | 28+ dirs, 400+ files | Institutional knowledge library |
| L3 Guardrails | Rules + Hooks | 9 rules, 9 hooks | Deterministic enforcement |
| L4 Instructions | Commands | 20 commands | Phase-gated workflow |
| L5 Learning | Learning pipeline | observations + digest + codification | Knowledge compounding |
Critical rules have 5-8 independent enforcement layers:
Rule file (soft — AI interprets)
+ Hook script (hard — deterministic, exit code 2 blocks)
+ Anti-amnesia hook (re-injects every message, survives compression)
+ Code review by reviewer
+ Security review by security-reviewer
+ CI pipeline check
The anti-amnesia hook (user-prompt-rules-reminder.js) is the single most important mechanism — fires on every user message.
| Phase | Command | Quality Gate |
|---|---|---|
| Analysis | /analyze | reviewer |
| Planning | /todos | Human approval |
| Implementation | /implement | reviewer + security-reviewer |
| Validation | /redteam | reviewer |
| Knowledge | /codify | gold-standards-validator |
| Release | /release | Human approval |
Evidence-based completion: AI cannot claim "done" without file-and-line proof.
Observations (JSONL)
→ Pattern analysis (confidence = frequency 40% + success 30% + recency 20% + consistency 10%)
→ Evolution suggestions (Skills ≥0.7, Commands ≥0.6, Agents ≥0.8)
→ Human approval required
All synced from loom/ (source of truth) via /sync.