agentic-harness-patterns-skill
Learn portable engineering patterns for reliable AI agent harnesses.
Learn portable engineering patterns for reliable AI agent harnesses.
This bilingual skill teaches engineers how to design the systems surrounding an AI model loop. Six chapters and eleven deep-dive references cover memory, skill loading, tools and permissions, context engineering, multi-agent coordination, and lifecycle design, with tradeoffs and common failure modes. The patterns were distilled from source-level analysis of the Claude Code runtime, but they are presented as runtime-agnostic principles for people building coding agents, plugins, or orchestration systems—not as a source mirror or a beginner user guide.
Resource types
Use cases
Platforms
Provides Claude skill examples, the Agent Skills specification, and a template for custom skills.
Design agent workflows visually and expose them as APIs or MCP tools.
Runtime
Audience
Public GitHub facts last synced Jul 14, 2026.
Build LLM apps with visual workflows, RAG, agents, and APIs.
Combine interchangeable models, data sources, and tools in LLM applications.