---
title: "你真的需要 REA 嗎？我測試了 Reverse Engineer Anything 與單獨使用 Claude Code 的對比"
url: "https://reamcp.dev/zh-tw/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: "工具與整合"
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: "zh-tw"
content_locale: "zh-tw"
---

# 你真的需要 REA 嗎？我測試了 Reverse Engineer Anything 與單獨使用 Claude Code 的對比

一位開發者分別僅使用 Claude Code 和使用 REA（rea-agents 6.4.0）作為 MCP 伺服器，重建了自己編譯後的生產應用程式，並根據 8 條隱藏業務規則對兩者進行評分；他分享了時間和成本結果、評分方法，以及 Windows 設定建議，包括 MCP 冷啟動逾時問題。

## Description

該影片測試了在從編譯建置（無原始碼、無 source map、無 .git）重建應用程式時，REA 是否比單獨使用 Claude Code 更有價值。兩次執行在隱藏規則上都得到了 8/8 分，但 REA 耗時 16 分 46 秒，而單獨使用 Claude Code 耗時 40 分 27 秒，API 等效成本略高。內容涵蓋 REA 是什麼、關於假冒 REA 儲存庫的警告、Windows 設定問題（MCP 冷啟動 35.5 秒 vs Claude Code 的 30 秒等待，建議設定 MCP_TIMEOUT=120000）、隱藏規則是如何選擇的、使用的提示詞、評分卡、成本/速度要點，以及一個法律合規部分，強調只應分析你擁有或獲授權檢查的軟體。僅推薦官方儲存庫（github.com/morluto/rea）。

## 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