Claude Code System Prompts Research
Documents the internal system prompts, agent directives, and multi-agent orchestration of Claude Cod
by reason-machines
The skill
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.
This skill's licence does not allow redistribution, so the store does not show its text. Read it at the source.
Use this skill
Connect your agent to the Skill Store MCP server and ask for it by ref: reason-machines/claude-code-system-prompts-research-52742652014.
Details
- Publisher
- reason-machines
- Category
- AI & Agents › Skill & prompt authoring
- Updated
- 2026-10-09
References
More from reason-machines
- 3Dsvg Interactive React Turn SVGs into interactive React 3D components using the 3dsvg library and visual editor
- 724 Office Ai Agent Self-evolving AI agent system with 26 tools, three-layer memory, MCP plugins, and 24/7 self-repai…
- Acgti Anime Persona Quiz ACG Type Indicator — MBTI-inspired anime character persona quiz built with Vue 3, TypeScript, and…
- Advertising Skills Ai Agents This skill library installs SKILL.md files for direct-response advertising, Schwartz-style copywriti