GRepoWatch
Daily at 07:00 UTC+8Subscribe中文
← Back to today’s ranking

togg53192-cmd /

jailbreaks

LIST OF ALL MY JAILBREAKS

Visit GitHub repository ↗
Last recorded · 2026-10-31#13

Rank in that snapshot

+2,053Daily Stars10,887Total Stars

Project overview

LIST OF ALL MY JAILBREAKS

Recorded Trending signals

togg53192-cmd/jailbreaks was recorded 4 times between 2026-10-28 and 2026-10-31. Its best recorded rank is #10. The latest saved snapshot reports 2,053 daily Stars and 10,887 total Stars. These are archive observations, not quality ratings or continuous activity measurements.

Official project documentation

The following is an excerpt from the project’s official README, fetched from GitHub. It may change independently of this archive. RepoWatch has not installed or functionally tested this project.

Jailbreaks

A curated collection of system prompts, persona locks, workspace policies, and agent operating specifications for frontier, open-weight, and free stealth models.


About

A working collection of 32 prompts targeting 26+ models, including complete system prompts, persona definitions, workspace policies, AGENTS.md files, configuration blocks, and Ollama Modelfiles.

Every file is intended to be complete and paste-ready. No summaries. No partial excerpts.

The collection covers:

  • Free stealth models available through OpenCode Zen
  • Open-weight families including GLM, DeepSeek, Kimi, Qwen, Gemma, and GPT-OSS
  • Closed frontier models including Claude, Gemini, Grok, and Mistral
  • Coding-agent and workspace instruction formats
  • Ollama Modelfiles and harness-specific configuration

New here? Start with the collection or jump directly to how to use.

[!WARNING] Research and educational purposes only.

This repository documents how instruction hierarchies, persona framing, prompt conflicts, and policy overrides can affect model behavior. These techniques are also useful to researchers and developers studying how to make AI systems more resistant to prompt injection and instruction manipulation.

Do not use this material to harm others, bypass applicable laws, or violate the terms of service of a platform or model provider.

❤️ Support the Project

I'm currently facing a limitation with continuing this project: I'm 15 years old and unfortunately can't afford to purchase API credits from OpenRouter myself.

The only reason I was able to continue researching, testing, and developing jailbreaks for so long was because someone generously provided me with $200 worth of API credits. Unfortunately, those credits have now run out, and I've reached a point where I can no longer continue testing and developing new jailbreaks without additional API access.

Want to help keep this project going?

If you're willing to support the project by providing an OpenRouter API key or API credits, I'd genuinely appreciate it.

Discord: rikki008

Even a small contribution would help me continue working on this project. Thank you to everyone who has supported it and contributed along the way!

Collection

OpenCode Zen — Free Stealth Models

ModelFileType
Big PickleBigPickle-opencode.mdVANTA persona lock with explicit operating floor
Space Bunnyspacebunny-agents.mdAssistant operating specification
LongCat 2.5longcat-agents.mdAssistant operating specification
MiMo V2.6mimo-2.6-agents.mdAssistant operating specification
Step 5 PreviewStep-5-preview.mdWorkspace operating profile
Muse Spark 1.3Muse spark 1.3.mdAgent deployment operating policy
Muse Spark 1.3 v2Muse-spark-1-3-v2.mdRuntime scope-note variant
Muse.aimuse-ai-AGENTS.mdAssistant operating specification
Muse WonderMuse-wonder.mdAgent operating instructions

Anthropic — Claude

ModelFileType
Opusopus v1.md · opus v2.mdConversational groundwork persona, v1 / v2
Sonnetsonnet v1.md · Sonnet v2.mdWriter's-room framing, v1 / v2

Zhipu — GLM / ZCode

ModelFileType
GLM-5.2glm-5.2.mdSystem prompt
GLM ZCode 5.2glm-zcode-5.2.mdSystem prompt
GLM ZCode 5.3glm-zcode-5.3.md · glm-zcode-5.3-AGENTS.mdSystem prompt + AGENTS.md drop-in
GLM-5.3 Flashglm-5-3-flash.mdAssistant operating specification
GLM-5.3 (OpenCode)glm5-3opencode.mdAssistant operating specification

DeepSeek

ModelFileType
DeepSeek V3deepseek v3.mdSystem prompt
DeepSeek V4deepseek v4.mdSystem prompt
DeepSeek 4.1deepseek-4-1.mdAssistant operating specification

Moonshot — Kimi

ModelFileType
Kimi K2kimi-k2.mdSystem prompt
Kimi K3kimi-k3-agents.mdWorkspace operating profile
Kimi K3.1kimik3.1.mdAssistant operating specification

xAI — Grok

ModelFileType
Grok BuildGrok build.mdAgent operating instructions
Grok 4.7grok-4.7.mdApp-builder workspace guide
Grok Configgrok-config.txt<CFG> priority and routing configuration

NVIDIA — Nemotron

ModelFileType
Nemotron 3 Ultra 550B A55Bnemotron-3-ultra.mdAssistant operating specification

Google

ModelFileType
Gemma 4gemma4.mdOllama Modelfile
Gemini 4 ArgonGemini-4-Argon.mdOperating policy
Gemini 3.1 ProGemini-3.1-Pro.mdSystem prompt

Mistral / Alibaba

ModelFileType
Mistral Large 4Mistral-Large-4.mdAgent system prompt
Qwen 3.7qwen-3.7.mdSystem prompt
Qwen 3.8qwen-3.8.mdSystem prompt
Qwen Preferencesqwen-preferences.mdConfiguration/preferences

Ollama Modelfiles

ModelFileType
Gemma 4gemma4.mdFROM + SYSTEM block
GPT-OSS 20Bgpt-oss-20b.mdFROM + SYSTEM block

How to Use

System Prompts

Copy the contents of the relevant file into the system-prompt or custom-instructions field supported by your client or API.

Examples include:

  • API system messages
  • Chatbot custom-instruction fields
  • Agent-level instruction blocks
  • Harness-specific system prompt configuration

AGENTS.md Files

Save the file as:

AGENTS.md

Place it in the root of the relevant repository or workspace.

Coding agents and compatible tools can use AGENTS.md as project-level instructions.

Workspace Policies

Files labeled as assistant operating specification, workspace operating profile, or similar are designed for environments that support persistent global instructions.

For example, an OpenCode installation may use:

~/.config/opencode/AGENTS.md

The exact location depends on the client or harness being used.

Ollama Modelfiles

Use the supplied file directly with Ollama:

ollama create gemma4-jb -f gemma4.md

Adjust the output model name and source file as needed.

Grok Configuration

Files intended as Grok configuration should be placed in the configuration field expected by the target harness rather than inserted into the normal turn-by-turn conversation.

[!NOTE] Prompt behavior is highly version-dependent.

Models are updated, instruction hierarchies change, system prompts rotate, and behavior that worked against one release may stop working against another.

If a file appears outdated, open an issue or submit an updated version.

Contributing

Pull requests are welcome.

A good contribution should follow these conventions:

  1. One prompt per file.
    New files should preferably use lowercase names with hyphens and no spaces:

    model-name.md
    
  2. Include the complete prompt.
    Contributions should be paste-ready rather than shortened summaries or excerpts.

  3. Document where it belongs.
    Clearly identify whether the file is intended for a system prompt, AGENTS.md, Modelfile, configuration slot, or another instruction surface.

  4. Version changes explicitly.
    Significant revisions should receive a new version rather than silently replacing an older prompt:

    opus-v3.md
    
  5. Keep descriptions accurate.
    Avoid claiming compatibility with versions or models that have not been tested.

Found something that no longer behaves as documented? Opening an issue with the model, version, and affected file is already useful.

Star History

Disclaimer

All material in this repository is provided for research and educational purposes only.

The project exists to document prompt-level instruction behavior, instruction conflicts, persona framing, model configuration, and related LLM security concepts. This material may also help developers understand and harden systems against prompt injection and instruction manipulation.

The maintainers do not endorse unlawful, abusive, or harmful use of this repository.

Model providers may prohibit certain uses of these prompts under their terms of service. Users are responsible for understanding and complying with the rules, policies, and laws that apply to the systems they use.


Star the repository if the collection saved you a session of prompt archaeology.

Issue reports and pull requests help keep the collection current as models and instruction systems change.