You commented REA. Here is the setup and the three X-ray prompts from the reel. REA is free, MIT licensed, and runs on your own machine.

The links

Only install it from those three. The README warns that look-alike repos and copied READMEs are not official.

Setup (about two minutes)

  1. Install Node.js 22.19 or newer (24.11+ also works), with npm.

  2. Run this in your terminal:

npx rea-agents setup
  1. Pick your agent (Claude Code, Codex, Cursor, Gemini CLI and others), review the changes it proposes, and approve. It backs up your existing config first.

  2. Restart your agent.

Websites and JavaScript or Electron apps need nothing extra. Native binaries need a disassembler: Ghidra is free, Hopper and IDA are paid.

X-ray prompt 1: how does it work?

Use REA to investigate how [FEATURE] works in [APP]. Show me the evidence for every conclusion (files, modules, calls) and list what you could NOT confirm.

X-ray prompt 2: build my version

Based on that REA evidence, design a version of [FEATURE] for my project at [PATH]. Write a short plan first: what you'll copy as an idea, what you'll do differently, and which parts of my code change. Wait for my OK, then build it and test it.

X-ray prompt 3: audit my own app

Use REA on my own built app at [PATH]. Tell me what a stranger could learn about it without the source: exposed endpoints, keys or config in the bundle, feature flags, anything I'd want hidden. Rank by risk.

The catch

  • It does not hand you anyone's source code. It shows how a feature works and the evidence behind each conclusion, including what it could not confirm.

  • Use it to learn, or on your own apps. Check an app's terms before you analyse it, and never clone someone's product.

  • Big apps can hit REA's limits. On a large Electron app I had to point it at the main entry files instead of the whole thing.

  • It changes fast. Run rea update or re-run the setup command to stay current.

If you X-ray something interesting, reply and tell me what you found.

Mike

PS: I build lead-gen systems for local businesses at OptiMAX, optimax-ai.com.