Extracted system prompts from ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, CLI), Grok (4.2, 4), Perplexity, and more. Updated regularly.

ChatGPT Jailbreaks, GPT Assistants Prompt Leaks, GPTs Prompt Injection, LLM Prompt Security, Super Prompts, Prompt Hack, Prompt Security, Ai Prompt Engineering, Adversarial Machine Learning.

🎭 193 个即插即用的 AI 专家角色 — 支持 OpenClaw/Claude Code/Cursor/Copilot 等 14 种工具，覆盖工程/设计/营销/产品等 18 个部门。含 46 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉等）

This framework works as a form of user/machine calibration, with a focus on user-context and user-intent, deconstructing your ideas logically from A to B to Z.

Independent research on Claude Code internals, Claude Agent SDK, and related tooling.

Collection of leaked system prompts for ChatGPT, Claude, Grok, Gemini,Deepseek, Manus, vercel v0,lovable,cursor, etc...

AI-powered project management framework based on an opinionated view on effective prompts and a highly modular approach to building effective agents, workflows, templates, prompts and context documents.

Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed.

This repository contains the system prompts used by Cursor IDE

Collection of leaked ChatGPT system prompts, documenting base tools, conditional features, and specialized assistants. Provides insights into the internal structure and behavior of different ChatGPT components and their activation conditions.

Stop your AI from writing like AI. A universal system prompt eliminating every known LLM style tell — works with Claude Code, Gemini CLI, Codex CLI, Copilot, Cursor, and any web AI.

MINOTAUR: The STRONGEST Secure Prompt EVER! Prompt Security Challenge, Impossible GPT Security, Prompts Cybersecurity, Prompting Vulnerabilities, FlowGPT, Secure Prompting, Secure LLMs, Prompt Hacker, Cutting-edge Ai Security, Unbreakable GPT Agent, Anti GPT Leak, System Prompt Security.

best system prompts I use for prompt engineering, including leaked prompts

Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.

A model-agnostic layered cognitive framework for LLMs. Improves coherence, emotional clarity, structural reasoning, and creative depth across GPT, Claude, Gemini, Grok, Mistral, and others—while reducing token waste and internal contradiction.

A collection of extracted system prompts/operational instructions

re!think it. System prompt teaching LLMs to execute two core tasks: complex answers without hallucinations, and creative ideas without clichés. Written in math-like logic, which LLMs parse better than plain language. Built for mid-to-high complexity tasks, featuring a Bypass branch to execute simple prompts directly without added cognitive overhead

A small collection of AI System Prompt cracking resources

[Findings of EMNLP'25] A comprehensive framework designed to safeguard system prompts for Large Language Models (LLMs) against various types of attacks.

Gemini Agents Manager — Turn your Gemini CLI into a Multi-Persona AI Team — 40+ specialized agents, one command.