Collection of Leaked System Prompts from Mainstream AI Products

asgeirtj · github · 2026-07-05

This repository curates and continuously updates extracted system prompts from major AI products. It covers Anthropic (Fable 5, Opus 4.8, Claude Code/Design), OpenAI (ChatGPT 5.5, Codex), Google (Gemini 3.5 Flash, etc.), xAI Grok, and tools like Cursor, Copilot, and Perplexity. The project has nearly 50,000 stars.

Original post →

More from Safety

Safety channel →