# asgeirtj/system_prompts_leaks

Source: [GitHub](https://github.com/asgeirtj/system_prompts_leaks)  
Feed7 permalink: https://feed7.dev/p/system-prompts-leaks-0pth2c5  
Published: Unknown  
Trust: Needs Review (needs_review)

## Why Included

A maintained archive of extracted system prompts from 100+ AI products — Claude Fable 5, Claude Code, ChatGPT 5.5, Gemini, Cursor — useful for studying how vendors actually instruct their agents.

## Source Summary

**The gist** The repo collects extracted system prompts from roughly **100+** models and products across **Anthropic, OpenAI, Google, xAI**, Microsoft, Meta, and Mistral — including Claude Fable 5, Claude Code, ChatGPT 5.5, and Cursor — organized by vendor with a recently-updated index. It sits at **49.5k stars** with **599 commits** and updates as recent as July 2026.

## Practical Implication

**Why it matters** Vendor system prompts are the closest thing to a reference library for **prompting** and harness design: how labs structure tool instructions, refusal rules, and formatting constraints. Reading how **Claude Code** or **Cursor** is instructed can directly inform the system prompt of your own agent.

## Agent-Ready Context

**The gist** The repo collects extracted system prompts from roughly **100+** models and products across **Anthropic, OpenAI, Google, xAI**, Microsoft, Meta, and Mistral — including Claude Fable 5, Claude Code, ChatGPT 5.5, and Cursor — organized by vendor with a recently-updated index. It sits at **49.5k stars** with **599 commits** and updates as recent as July 2026.

**Why it matters** Vendor system prompts are the closest thing to a reference library for **prompting** and harness design: how labs structure tool instructions, refusal rules, and formatting constraints. Reading how **Claude Code** or **Cursor** is instructed can directly inform the system prompt of your own agent.

**Watch out** Nothing here is verified: prompts are obtained via **extraction-style prompting**, the repo states **no validation methodology**, and vendors revise prompts constantly — treat any entry as a possibly **stale or partial** reconstruction.

## Context Map

- Layer: context
- Domains: coding
- Topics: prompting, context-engineering, coding-agents

## Uncertainty

- Nothing here is verified: prompts are obtained via **extraction-style prompting**, the repo states **no validation methodology**, and vendors revise prompts constantly — treat any entry as a possibly **stale or partial** reconstruction.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.