---
title: "RIP Reverse Engineer Anything！這個 8 KB 技能超越 REA（快 38%）"
url: "https://reamcp.dev/zh-tw/cases/rip-reverse-engineer-anything-this-8-kb-skill-outperforms-re-cbdb17"
source: "https://www.youtube.com/watch?v=0Otn8QGGtRw"
source_type: "resource"
author: "AICodeKing"
author_handle: "aicodeking"
stars: 0
category: "工具與整合"
categories: ["tools-integrations"]
tags: ["benchmark", "claude-code", "cli-tools", "mcp", "reverse-engineering"]
added: "2026-10-18T02:14:15.565Z"
updated: "2026-10-17T09:16:41.000Z"
locale: "zh-tw"
content_locale: "zh-tw"
---

# RIP Reverse Engineer Anything！這個 8 KB 技能超越 REA（快 38%）

AICodeKing 對 LeanREA（一個 8 KB 的技能檔案）與 REA（Reverse Engineer Anything）進行基準測試，解釋 REA 的內部機制，並在 36 次執行中比較速度、成本和準確性。

## Description

加入此頻道以獲得福利：
https://www.youtube.com/channel/@aicodeking/join

在此處給 LeanREA 加星：https://github.com/aicodeking/leanrea

在本影片中，我將展示 LeanREA，一個 8 KB 的技能檔案，我建置它來完成與 REA（Reverse Engineer Anything）相同的工作，而無需 MCP 伺服器或任何額外工具。我解釋了 REA 的內部原理，然後介紹了該技能的內容：規則、將每種目標類型對應到其最快指令的路由表，以及即用型的第一步。然後我展示了我在 Claude Code 中使用 Sonnet 5.5 進行的基準測試，共 36 次執行，其中 LeanREA 在相同準確性下比 REA 快 38% 且便宜 35%，還有上下文測試和逐工具速度測試。我還談到了基準測試的局限性、我在自己的技能中發現的兩個錯誤，以及如何透過一個 npx skills 指令安裝它。

## Original README

RIP Reverse Engineer Anything! This 8 KB Skill Outperforms REA (38% Faster)

Join this channel to get access to perks:
https://www.youtube.com/channel/@aicodeking/join

Star LeanREA here: https://github.com/aicodeking/leanrea

In this video, I'll show you LeanREA, a single 8 KB skill file that I built to do the same job as REA (Reverse Engineer Anything) without an MCP server or any extra tools. I explain what REA is under the hood, then go through what is inside the skill: the rules, the router table that maps each target type to its fastest command, and the ready-to-run first moves. Then I show my benchmark in Claude Code with Sonnet 5.5 across 36 runs, where LeanREA was 38% faster and 35% cheaper than REA at the same accuracy, plus the context test and a tool-by-tool speed test. I also talk about the limits of the benchmark, two bugs I found in my own skill, and how to install it with one npx skills command.

--
Key Takeaways:

📦 LeanREA is one 8 KB skill file with no MCP server and no extra tools; the agent runs the real tools in its normal shell.
🔀 REA is an MCP server plus a CLI that adds 207 tools, and under the hood it mostly calls tools you already have, like asar, otool, nm and jadx.
🧠 The skill has a short list of rules, a router table for 15 target types, and first moves that do many checks in one shell call.
📊 In 36 graded runs, LeanREA took 388 seconds, no skill took 479 seconds and REA took 627 seconds.
💸 LeanREA cost $2.17 against $3.36 for REA, with 56% fewer turns and 60% fewer tokens, and scored 74/75 against REA's 75/75.
⚠️ With tool search turned off, one "reply with OK" message with REA used about 400k tokens and cost $1.60.
⚡ On the same file, REA's Go build info took about half a second, and plain go version -m took 0.06 seconds.
👍 The plain model with no skill was already very good, so the big win is against REA, not against the model alone.
🔍 Two bugs I found in my own skill: ripgrep skips hidden folders like .webpack (use -uu), and zsh breaks echo with two equal signs.
✅ My verdict: if you are a programmer, use the small skill, because it is faster, cheaper, and you can read all of it in two minutes.