ClaudePedia
Search
Ecosystem
Guides
  • Build Your First Agent
  • Design a Custom Tool
  • Manage Conversation Context
  • Add MCP to Your Agent
  • Build a Multi-Agent System
  • Implement Permission Controls
  • Debug Your Agent
  • Stream Agent Responses
  • Extend with Hooks
Patterns
Core Systems
  • Agent Loop Architecture
  • Tool System Design
  • Prompt Architecture
  • Memory and Context
  • Error Recovery and Resilience
  • Safety and Permissions
  • Streaming and Events
  • Multi-Agent Coordination
Advanced Patterns
  • Command and Plugin Systems
  • Hooks and Extension Points
  • MCP Integration
  • Observability and Debugging
Reference
  • Pattern Index
  • Glossary
Contact
Home/Patterns/Advanced Patterns

Advanced Patterns

Extensibility and integration patterns for production agents: plugins, MCP, hooks, and observability.

4 articles

Command and Plugin Systems

How to build a scalable command registry that supports 100+ commands through metadata-first registration, lazy loading, and multi-source merging.

Hooks and Extension Points

How typed interceptors modify agent behavior at 27+ lifecycle events without touching core loop code: four execution modes, condition syntax, and error isolation.

MCP Integration

How the Model Context Protocol turns external services into agent tools: transport selection, tool bridging, and connection lifecycle management.

Observability and Debugging

Three independent observability layers for agent systems: structured event logging, per-model cost tracking, and session tracing with span hierarchy, each answering a different debugging question.

ClaudePedia v0.1.9
Home·Guides·Ecosystem·Search·Contact
NaktorSubstack