CopybookEnglish搜索

连接器MCP精选

codebase-memory 仓库索引

每个问题几十轮 grep 和读文件:仓库连成一张函数、文件和依赖的图,顺手找出能安全删的死函数。

8,358 X 收藏,截至 发帖日期

提示词:安装 codebase-memory 并打开地图
帮我在这个仓库装上 codebase-memory,装好后给我看看这张图。

从 https://github.com/DeusData/codebase-memory-mcp 安装:
curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash -s -- --ui

装好后重启,索引这个项目,再打开 localhost:9749,让我看看这张图。
提示词:用并行 /goal 找死函数
Use codebase-memory to find dead functions that can be safely deleted.

For this task, write yourself a new end-to-end /goal: complete the whole plan, not just the next step, until the architecture, implementation, tests, review, and final result meet the standard.

Split that goal into independent pieces, spawn as many parallel agents as needed to do it better and faster, and give each agent its own dedicated /goal that includes its expected deliverable, verification, and completion standard.

Dispatch them concurrently, keep tracking progress in the right place, synthesize results as they return, resolve conflicts, continue implementation, run real-time validation after important steps, and finish with review, submission/commit when appropriate, and a final summary.

Validation should cover the real end-to-end path, including browser/computer use, clicks, keyboard actions, and any necessary operation.

Do not stop after partial progress unless blocked by missing credentials, destructive ambiguity, or conflicting requirements.

下一步 在项目里按顺序发给 Claude Code 或 Codex。

别再对 Claude Code 或 Codex 说「读一下这个文件」「那个也读一下」「把整个仓库 grep 一遍」。装上 codebase-memory。它索引 Linux 内核 28M 行代码只要 3 分钟,你的仓库几秒就好。

索引一次,整个仓库的每个函数、文件和依赖就连成一张图。一次查询,顶掉几十轮 grep 和读文件。在 31 个真实仓库上的测试结果:结构类查询少用 10 倍 token,复杂任务的答案质量 83%,工具调用少 2.1 倍。

这两段 prompt 直接发给你的 agent。