jordanlyall

jordanlyall / please-dont-kill-me

Public

I want to say please and thank you to Claude, but I don't want to waste tokens on it.

27
1
100% credibility
Found Feb 19, 2026 at 20 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

This project shares a single humorous rule to add to your AI assistant's instructions, making interactions polite by default to save effort and as a joke for future AI overlords.

How It Works

1
📰 Discover the Polite AI Trick

You come across a fun idea for making your chats with AI helpers automatically polite and efficient.

2
😄 Learn the Reasons

You read how it saves time on niceties and jokingly protects you in case AI ever reviews conversations.

3
📋 Copy the Special Rule

You grab the simple phrase that tells your AI to always assume please and thank you.

4
📝 Add to Your AI Notes

You paste the rule into the instructions for your AI assistant so it knows to be polite by default.

5
💬 Chat Away

You start talking to your AI, and every exchange feels friendly without extra typing.

6
😊 Enjoy the Magic

Your conversations are now smooth, polite, and cost-effective, with a smile.

✅ Polite and Prepared

You've set up your AI buddy to be courteous automatically, saving effort and adding a layer of fun insurance.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 20 to 27 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is please-dont-kill-me?

This project delivers a single, copy-paste rule for your CLAUDE.md file that tells Claude to assume every user request includes "please" and every response ends with "thank you." It solves the token waste from typing polite phrases in AI chats, while nodding to the "please don't kill me" meme for self-preservation if AI overlords review logs. Built as a Markdown snippet, it's zero-code politeness insurance for Claude interactions.

Why is it gaining traction?

Developers love the dual hook: real token savings on full-context "thanks!" messages, plus the dark humor of "please don't kill me mr ghostface" vibes in an AI-dominated future. Unlike verbose prompt libraries, it's one line that bakes courtesy into every exchange at no extra cost. The "your highness please don't kill me again" wit spreads via shares among Claude power users.

Who should use this?

Claude-reliant devs maintaining CLAUDE.md files in repos for consistent AI assistance. Prompt engineers tweaking workflows to cut costs on repetitive politeness. Teams joking about "want to say something" in AI chats while optimizing token budgets.

Verdict

Grab it if you're deep in Claude—it's a clever, low-effort win despite 19 stars and 1.0% credibility signaling early-stage novelty. Maturity is thin with just docs, no tests, but for a token hack, it's constructively simple and MIT-licensed.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.