REA MCP
☰
ZH-CN
● — 人在线 · 浏览 — 次
赞助提交案例
教程资源 · 发布者 AICodeKing

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

AICodeKing 对 LeanREA(一个 8 KB 的技能文件)与 REA(Reverse Engineer Anything)进行基准测试,解释 REA 的内部机制,并在 36 次运行中比较速度、成本和准确性。

已翻译

关于这个案例

加入此频道以获取福利: https://www.youtube.com/channel/@aicodeking/join

在此处给 LeanREA 加星:https://github.com/aicodeking/leanrea

在本视频中,我将展示 LeanREA,一个 8 KB 的技能文件,我构建它来完成与 REA(Reverse Engineer Anything)相同的工作,而无需 MCP 服务器或任何额外工具。我解释了 REA 的内部原理,然后介绍了该技能的内容:规则、将每种目标类型映射到其最快命令的路由表,以及即用型的第一步。然后我展示了我在 Claude Code 中使用 Sonnet 5.5 进行的基准测试,共 36 次运行,其中 LeanREA 在相同准确性下比 REA 快 38% 且便宜 35%,还有上下文测试和逐工具速度测试。我还谈到了基准测试的局限性、我在自己的技能中发现的两个错误,以及如何通过一个 npx skills 命令安装它。

安装配置

安装方法请查看原始来源。

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.

更多类似作品