# A collection of prompts for AI models

togg53192-cmd/jailbreaks offers a collection of system prompts, persona locks, and workspace policies designed to bypass the security restrictions of AI models. This work serves as a technical compilation aimed at modifying the operating principles of various open-weight and closed models.

- ★ 5,175
- GitHub Trending · 2026-10-27

## What you get

- Provides custom system prompts for different AI models
- Includes persona locks and workspace policies
- Enables researchers to examine model behaviors

## Getting started

Click on the file for the model you are interested in from the list on GitHub to view its content. Then, copy the entire text and paste it into the system prompts or custom instructions field of the AI tool you are using. If you are using local tools like Ollama, you can add the relevant file content directly to the configuration fields.

## Related dictionary terms

- [System Prompts](https://trescout.com/en/dictionary/system-prompts/)
- [Artificial Intelligence](https://trescout.com/en/dictionary/artificial-intelligence/)

- **Who it is for:** Intended for researchers and developers who want to examine the operating principles, instruction hierarchies, and security restrictions of AI models.

## Links

- [GitHub repository →](https://github.com/togg53192-cmd/jailbreaks)
- [Read in Turkish →](https://trescout.com/discover/jailbreaks/)

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-10-27: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was **machine-translated** from the Turkish original · the Turkish version prevails.

---
Source: TreScout Discover · https://trescout.com/en/discover/jailbreaks/