---
title: "一个免费的 MCP 读取 212 个遗留文件并在任何代理接触代码之前编写规范"
url: "https://reamcp.dev/zh-cn/cases/a-free-mcp-reads-212-legacy-files-and-writes-the-spec-before-831c92"
source: "https://x.com/i/status/2111530936441446417"
source_type: "x"
author: "Primee32"
author_handle: "Primee32"
stars: 0
category: "应用功能复现"
categories: ["app-recreation"]
tags: ["code-rewrite", "legacy-modernization", "mcp", "reverse-engineering", "spec-generation", "verification"]
added: "2026-10-19T02:06:48.267Z"
updated: "2026-10-17T18:53:00.000Z"
locale: "zh-cn"
content_locale: "zh-cn"
---

# 一个免费的 MCP 读取 212 个遗留文件并在任何代理接触代码之前编写规范

一篇 X 帖子描述了一个工作流程：REA (morluto/rea) 将遗留计费系统逆向工程为 spec.md（14 个端点、37 条规则、9 个边缘情况），十二个 Sonnet 代理从规范切片构建模块，REA VERIFY 针对遗留系统重放新系统（148/148 行为匹配）。帖子链接到 MIT 许可的 GitHub 项目，并给出了 npx rea-agents setup 安装命令，以及关于将工具结果发送给模型提供商的警告。

## Description

一个免费的 MCP 读取 212 个遗留文件并在任何代理接触代码之前编写规范

大多数重写都失败在同一个地方。你把整个旧系统丢进一个模型，它就被淹没了

这个设置将工作拆分：

OPUS 5.5 > 编写计划，然后在剩余运行中空闲
REA > 一次性逆向工程 legacy/billing，并将其转换为 spec.md，包含 14 个端点、37 条规则、9 个边缘情况
SONNET 5.5 x12 > 每个一个模块，从规范的约 1.5k token 切片构建。它们都不打开旧代码
REA VERIFY > 针对遗留系统重放新系统，148 个行为中有 148 个匹配

在屏幕上，群组在 7 分 05 秒内完成，花费 $0.88。opus $0.22，REA $0.32，十二个 sonnet $0.34。仅 Opus 5.5 就处于 23% 和 $1.20，仍在运行

视频将该比较标记为说明性，因此将数字视为演示

REA 不来自 Anthropic。它是 GitHub 上的 morluto/rea，MIT 许可且免费，你只需为模型付费。一行安装它：npx rea-agents setup

在你将其指向客户代码之前：
> REA 在本地分析，但你的代理仍将工具结果发送给模型提供商
> 来自私有应用的解编译代码最终会进入 Anthropic 或 OpenAI，受其数据政策约束

它今天是免费的。在有人将其作为 $500 课程出售之前保存它

## Original README

A FREE MCP READS 212 LEGACY FILES AND WRITES THE SPEC BEFORE ANY AGENT TOUCHES THE CODE

most rewrites go wrong in the same place. you dump the whole old system into one model and it drowns

this setup splits the work:

OPUS 5.5 > writes the plan, then sits idle for the rest of the run
REA > reverse-engineers legacy/billing once and turns it into spec.md with 14 endpoints, 37 rules, 9 edge cases
SONNET 5.5 x12 > one module each, built from a ~1.5k token slice of the spec. none of them opens the old code
REA VERIFY > replays the new system against the legacy one, 148 of 148 behaviours match

on screen the swarm finishes in 7m 05s for $0.88. opus $0.22, REA $0.32, twelve sonnets $0.34. Opus 5.5 alone sits at 23% and $1.20, still running

the video marks that comparison as illustrative, so take the numbers as a demo

REA doesn't come from Anthropic. it's morluto/rea on github, MIT licensed and free, you only pay for the model. one line installs it: npx rea-agents setup

before you point it at client code:
> REA analyzes locally, but your agent still sends tool results to the model provider
> decompiled code from a private app ends up with Anthropic or OpenAI, under their data policy

it's free today. save it before someone sells it as a $500 course