asgeirtj/system_prompts_leaks — Extracted system prompts from ChatGPT (GPT-5.5 Thinking), Claude (Opus 4.7, Opus 4.6, Sonnet 4.6, Cl…

Description and use

The **asgeirtj/system_prompts_leaks** repository aggregates and regularly updates the hidden system prompts used by major conversational AI models—including ChatGPT (GPT‑5.5 Thinking), Anthropic’s Claude series, Google Gemini variants, Grok 4.3 beta, Perplexity, and others. By extracting these prompts, the project provides developers and researchers with insight into the underlying instruction sets that shape each model’s behavior, facilitating analysis, comparison, and tool development in the AI/ML space.

Problem

asgeirtj/system_prompts_leaks helps add AI capability without starting from a blank model stack.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• prototype AI features
• build RAG or agent workflows
• evaluate model tooling

Evidence

Extracted system prompts from ChatGPT (GPT-5.5 Thinking), Claude (Opus 4.7, Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, Gemini CLI), Grok (4.3 beta), Perplexity, and more. Updated regularly.

Source