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。
關於這個案例
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。
安裝設定
安裝方式請查看原始來源。
原文 / 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.
