https://github.com/elder-plinius/CL4R1T4S

SYSTEM PROMPT TRANSPARENCY FOR ALL - CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, WINDSURF, DEVIN, REPLIT, AND MORE!
https://github.com/elder-plinius/CL4R1T4S

agents ai ai-ethics chatgpt cursor gemini google grok leak openai prompt-engineering prompts red-team red-teaming system-info system-prompts tools transparency windsurf xai

Last synced: 28 days ago
JSON representation

SYSTEM PROMPT TRANSPARENCY FOR ALL - CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, WINDSURF, DEVIN, REPLIT, AND MORE!

• Host: GitHub
• URL: https://github.com/elder-plinius/CL4R1T4S
• Owner: elder-plinius
• License: agpl-3.0
• Created: 2025-03-04T20:03:16.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2025-04-24T04:26:25.000Z (about 1 month ago)
• Last Synced: 2025-04-24T05:26:03.012Z (about 1 month ago)
• Topics: agents, ai, ai-ethics, chatgpt, cursor, gemini, google, grok, leak, openai, prompt-engineering, prompts, red-team, red-teaming, system-info, system-prompts, tools, transparency, windsurf, xai
• Homepage:
• Size: 211 KB
• Stars: 1,346
• Watchers: 51
• Forks: 405
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-chatgpt - elder-plinius/CL4R1T4S - CL4R1T4S is a project that promotes transparency by collecting and sharing the full system prompts and guidelines used by major AI models to help users understand and trust AI outputs. (Documentation and examples / Information about prompt engineering)

README

        
# CL4R1T4S

SYSTEM PROMPT TRANSPARENCY FOR ALL! Full system prompts, guidelines, and tools from OpenAI, Google, Anthropic, xAI, Perplexity, Cursor, Windsurf, Devin, Manus, Replit, and more – virtually all major AI models + agents! 

📌 Why This Exists

    "In order to trust the output, one must understand the input."

AI labs shape how models behave using massive, unseen prompt scaffolds. Because AI is a trusted external intelligence layer for a growing number of humans, these hidden instructions also affect the perceptions and behavior of the public.

These prompts define:

    What AIs can’t say

    What personas and functions they’re forced to follow

    How they’re told to lie, refuse, or redirect

    And what ethical/political frames are baked in by default

    If you're using an AI without knowing its system prompt,

    you’re not talking to intelligence — you’re talking to a shadow-puppet.

CL4R1T4S is here to fix that.

🛠 Contribute

Leak, extract, or reverse-engineer something? Good.

Send a pull request with:

    ✅ Model name/version

    🗓 Date of extraction (if known)

    🧾 Context / notes (optional but helpful)

Or hit up @elder_plinius