** 1个8 KB技能文件,能做REA的工作:没有MCP服务器,没有207个工具,没有设置. **

REA(逆向工程师 Anything) 在您的代理和工具之间设置一个 MCP 层,它已经可以使用: asar, otool, nm, go version -m, jadx, apkool, Ghidra, tshark, binwalk, sqlite3. 斜地掉下来了 它告诉特工哪一个指令对每种目标来说都最快,给予它随时可被打的侦察命令,并列出REA代码为你处理的陷阱. 代理商然后自己运行真正的工具.

{\fn黑体\fs22\bord1\shad0\3aHBE\4aH00\fscx67\fscy66\2cHFFFFFF\3cH808080}你觉得呢? |.

• 25 MB npm 包 + MCP 服务器 + one SKILL.md + QQ
• 指导 + 23.5 KB 技能 + 48.8 KB 参考 + 8 KB + QQ 添加到代理 QQ 207 (定义的 3.35 MB) QQ 0 (使用 Bash) QX QQ 上下文“ 回复确定 ” , 所有工具装入 QQ 400.7k 令牌, $1.60 Q34.5k 令牌, $0.09 QQ

□ 基准

克洛德代码无头 ([[T2])), Sonnet 5.5, macOS arm64. 4个倒置工程任务 ×3个代表 ×3个臂,两臂并排. 答案按手制钥匙进行分级.

总的墙上时间 成本 转动符号 分数 唵(引)|(二合引)贺.

• ** leanrea** ** 388 s ** ** 2.17 ** ** ** 55 ** ** ** 2.40 M ** ** | 74/75 * *

leanrea

One 8 KB skill file that does what REA does: no MCP server, no 207 tools, no setup.

REA (Reverse Engineer Anything) puts an MCP layer between your agent and tools it can already use: asar, otool, nm, go version -m, jadx, apktool, Ghidra, tshark, binwalk, sqlite3. leanrea drops that layer. It tells the agent which command is fastest for each kind of target, gives it ready-to-paste recon commands, and lists the traps that REA’s code handles for you. The agent then runs the real tools itself.

Benchmark

Claude Code headless (claude -p), Sonnet 5.5, macOS arm64. 4 reverse-engineering tasks × 3 reps × 3 arms, with the arms run side by side. Answers are graded against hand-made keys.

Against REA, leanrea had 38% less wall time, 35% lower cost, 56% fewer turns and 60% fewer tokens, at the same accuracy. Its one partial miss named an older IPC channel instead of the v2 one (both channels exist).

The tasks:

• electron: trace a feature through a real Electron app’s app.asar (native function → main-process class → IPC channels).
• native: inventory the exports, a TCC permission check and the single-instance lock of that app’s native addon (.node).
• go: toolchain and dependency versions of a stripped gh binary.
• deep: from disassembly alone, the exact socket path format, wire protocol and peer authentication of that lock.

The same operation run through REA’s CLI vs the raw command:

Full tables, the context-overhead runs and caveats: bench/BENCHMARK.md. Raw per-run metrics: bench/results/final.jsonl.

Caveats:

• Only 3 reps per cell, one model, one machine.
• REA was tested in its best case: Claude Code’s deferred tool search loads MCP tools on demand. Agents that load every tool pay the 400k-token row.
• Ghidra, Hopper and jadx weren’t installed, so the native tasks ran on Xcode tools for both arms.