agentic-os

原文涵盖的主题

• Agentic OS
• When to Activate
• Architecture Overview
• Layer Responsibilities
• The Kernel
• Kernel Structure
• Key Principle
• Specialist Agents

Treat Claude Code as a persistent runtime / operating system rather than a chat session. This skill codifies the architecture used by production agentic setups: a kernel config that routes tasks to specialist agents, persistent file-based memory, scheduled automation, and a JSON/markdown data layer. Building a multi-agent workflow inside Claude Code Setting up persistent Claude Code automation that survives session restarts Creating a "personal OS" or "agentic OS" for recurring tasks User says "agentic OS", "personal OS", "multi-agent", "agent coordinator", "persistent agent" Structuring long-running projects where context must survive across sessions The Agentic OS has four layers. Each layer is a directory in your project root. | Layer | Purpose | Persistence | |---|---|---| | Kernel (CLAUDE.md) | Identity, routing, model policies, agent registry | Git-tracked | | Agents (agents/) | Specialist identities with scoped tools and memory | Git-tracked | | Commands (.claude/commands/) | User-facing slash commands (/daily-sync, /outreach) | Git-tracked | | Scripts (scripts/) | Python/JS daemons triggered by cron or webhooks | Git-tracked | | State (data/) | Append-only logs, project sta

这里只展示节选，请以完整原文和当前要求为准。