🤝 Community & Governance

Claude's Underground Prompt Hacks: I Tested 120 'Cheat Codes' That Flip Its Brain

Claude spits out fence-sitting drivel half the time. Slap on a 'cheat code' prefix, though, and it transforms — I've verified 120 that actually work, no hype.

theAIcatchup Apr 10, 2026 4 min read
List of Claude prompt prefixes like L99 and /ghost on a hacker-themed background

⚡ Key Takeaways

  • 120 community prompt prefixes like L99 and /ghost reliably alter Claude's output style and depth. 𝕏
  • Tested combos excel for specific tasks: emails, decisions, debugging. 𝕏
  • Temporary hacks — expect Anthropic to formalize or kill them soon. 𝕏
Published by

theAIcatchup

Community-driven. Code-first.

#AI prompts #Anthropic Claude #Claude AI #Claude cheat codes #llm-hacks #prompt engineering

Worth sharing?

Get the best Open Source stories of the week in your inbox — no noise, no spam.

Originally reported by Dev.to

Related Stories

📬

Stay in the loop

The week's most important stories from theAIcatchup, delivered once a week.

No spam. Unsubscribe any time.