HimanshuJ16/frank

7 stars · Last commit 2026-09-14

Makes your AI coding agent tell you the truth. No "You're absolutely right!", no caving when you push back on correct code, and no "done" without a command that proves it. Works with 20 agents.

PluginTDD & Testing Debugging Documentation Design & UI DevOps & Infra Productivity AI & Prompting Security

README preview

<p align="center">
  <img src="assets/logo.svg" width="260" alt="Frank">
</p>

<h1 align="center">Frank</h1>

<p align="center">
  <em>Local rules and hooks for evidence-first coding-agent replies.</em>
</p>

<p align="center">
  <img src="https://img.shields.io/github/stars/HimanshuJ16/frank?style=flat-square&color=111111&label=stars&cacheSeconds=3600" alt="Stars">
  <img src="https://img.shields.io/npm/v/@himanshujangir/frank?style=flat-square&color=111111&label=npm" alt="npm">
  <img src="https://img.shields.io/badge/gate-Claude%20Code%20%2B%20Codex-111111?style=flat-square" alt="Gate on Claude Code and Codex">
  <img src="https://img.shields.io/badge/license-MIT-111111?style=flat-square" alt="MIT license">
</p>

<!-- numbers:start -->
<p align="center">
  <strong>It asks for a real receipt after a code change. It does not prove the code is correct.</strong><br>

View full repository on GitHub →