Claude Opus 5.5 system prompt published in official docs, confirming Mythos tier

npinto · x · 2026-09-24

Anthropic's official docs publish the full system prompt for Claude Opus 5.5 (claude.ai and mobile apps), with big reveals:

The poster jokes this is a system prompt "leaked without knowing" — the behavioral constraints make it worth a close read for alignment and prompt-engineering folks.

Original post →

More from Models

Models channel →