---
title: "Do You Even Need REA? I Tested Reverse Engineer Anything vs Claude Code Alone"
url: "https://reamcp.dev/en/cases/do-you-even-need-rea-i-tested-reverse-engineer-anything-vs-c-3a6bd9"
source: "https://www.youtube.com/watch?v=mblE4k78BCg"
source_type: "resource"
author: "Aqib Mehmood"
author_handle: "thisisaqibmehmood"
stars: 0
category: "Tools & integrations"
categories: ["tools-integrations"]
tags: ["app-recreation", "benchmark", "claude-code", "mcp", "windows"]
added: "2026-10-15T02:15:28.471Z"
updated: "2026-10-14T16:35:22.000Z"
locale: "en"
content_locale: "en"
---

# Do You Even Need REA? I Tested Reverse Engineer Anything vs Claude Code Alone

A developer rebuilds his own compiled production app with Claude Code alone and again with REA (rea-agents 6.4.0) as an MCP server, scoring both against 8 hidden business rules; he shares timing and cost results, scoring methodology, and Windows setup tips including the MCP cold-start timeout.

## Description

The video tests whether REA adds value over Claude Code alone when rebuilding an app from a compiled build (no source, no source maps, no .git). Both runs scored 8/8 on hidden rules, but REA took 16m 46s versus 40m 27s, at slightly higher API-equivalent cost. It covers what REA is, a warning about fake REA repositories, Windows setup problems (35.5s MCP cold start vs Claude Code's 30s wait, suggesting MCP_TIMEOUT=120000), how the hidden rules were chosen, the prompt used, the scorecard, cost/speed takeaways, and a legality segment stressing that only software you own or are authorized to examine should be analyzed. Only the official repo (github.com/morluto/rea) is recommended.

## Original README

Do You Even Need REA? I Tested Reverse Engineer Anything vs Claude Code Alone

I gave Claude Code only the compiled production build of my app Shiftwire, with no source code, no source maps and no .git, and asked it to rebuild the whole thing. I ran it twice on the same build: once on its own and once with REA (Reverse Engineer Anything, rea-agents 6.4.0) connected as an MCP server. Both rebuilds were scored against the real source on 8 hidden business rules. Without REA: 8/8 in 40m 27s of Claude working time, $10.52 API-equivalent. With REA: 8/8 in 16m 46s, $12.45. Neither run flagged the overnight AM/PM bug in my app. One app and one run each, so treat the speed difference as a hint.

Two ideas worth stealing. Score a rebuild against rules hidden in the real code, like a setting that never fires or an opt-out list, because matching screens proves very little. And on Windows, REA's MCP server took 35.5 seconds to start cold while Claude Code waits 30, so start it once first or set MCP_TIMEOUT=120000 before you launch claude.

Only download REA from the official repo: https://github.com/morluto/rea
Lookalike repos exist. Do not run them.

Tested on my own app. Not legal advice. Only analyze software you own or are authorized to examine.

I build AI systems like this for service businesses: voice agents, automations, internal tools. Book a call: https://thisisaqib.com

Chapters:
00:00 The test: rebuild my app from compiled code
00:31 What REA is
01:10 Fake REA repos
01:40 Setup on Windows, and what broke
02:41 The hidden rules
03:40 The prompt
03:50 Round 1: without REA
05:05 Round 2: with REA
06:22 The scorecard
07:45 What REA changed: speed and cost
08:53 Is this legal?
09:35 Verdict
10:13 Outro