RIP Reverse Engineer Anything! 이 8 KB 스킬이 REA를 능가합니다 (38% 더 빠름)
AICodeKing가 8 KB 스킬 파일인 LeanREA를 REA(Reverse Engineer Anything)와 벤치마킹하고, REA의 내부를 설명하며, 36회 실행에서 속도, 비용, 정확성을 비교합니다.
이 사례에 대하여
이 채널에 가입하여 혜택을 받으세요: https://www.youtube.com/channel/@aicodeking/join
LeanREA에 스타를 눌러주세요: https://github.com/aicodeking/leanrea
이 비디오에서는 MCP 서버나 추가 도구 없이 REA(Reverse Engineer Anything)와 동일한 작업을 수행하기 위해 제가 만든 단일 8 KB 스킬 파일인 LeanREA를 보여드립니다. REA의 내부 작동 방식을 설명한 다음, 스킬 내부에 있는 내용을 살펴봅니다: 규칙, 각 대상 유형을 가장 빠른 명령에 매핑하는 라우터 테이블, 바로 실행할 수 있는 첫 번째 동작. 그런 다음 Claude Code에서 Sonnet 5.5를 사용한 36회 실행 벤치마크를 보여드립니다. LeanREA는 동일한 정확도에서 REA보다 38% 빠르고 35% 저렴했습니다. 또한 컨텍스트 테스트와 도구별 속도 테스트도 있습니다. 벤치마크의 한계, 제 스킬에서 발견한 두 가지 버그, 하나의 npx skills 명령으로 설치하는 방법도 이야기합니다.
설정
설치 방법은 원본 출처를 확인하세요.
원문 / 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.
