# Claude Code System Prompts Research

> Documents the internal system prompts, agent directives, and multi-agent orchestration of Claude Cod

Documents the internal system prompts, agent directives, and multi-agent orchestration of Claude Code, including the 2-stage auto-mode security classifier, CLAUDE.md memory loading, prompt caching, and context compaction. Use when asked how Claude Code's system prompt, sub-agents, permission classifier, memory files, or context window management are designed or work.

- Page: https://ss33.ai/skills/reason-machines/claude-code-system-prompts-research-52742652014
- Publisher: reason-machines
- Category: [AI & Agents](https://ss33.ai/skills/category/ai-and-agents-y6jz7i) › [Skill & prompt authoring](https://ss33.ai/skills/category/ai-and-agents-y6jz7i/skill-and-prompt-authoring-p179rh)
- Source: https://github.com/reason-machines/trending-skills/blob/c61b1a456af4015e9a367e0245292281bb3c87d9/skills/claude-code-system-prompts-research/SKILL.md

## Skill

This skill's licence does not allow redistribution, so the store does not serve its text. Get it from the author: https://github.com/reason-machines/trending-skills/blob/c61b1a456af4015e9a367e0245292281bb3c87d9/skills/claude-code-system-prompts-research/SKILL.md