# Inside the Agent SDK loop: how Claude Code runs your prompts

How Claude Code and the Agent SDK execute prompts through a five-step tool loop, expose typed lifecycle messages, and bound work with permissions, turns, and budgets.

- Published: 2026-04-02
- Category: agentic-systems
- Tags: agent-sdk, architecture, claude-code, coding-agents
- HTML: https://harnez.ai/posts/inside-the-agent-loop/

This Markdown sibling contains the article metadata and canonical link. Use the HTML URL for the complete rendered article.