---
title: "Claude Code 正在做什么的实时地图"
url: "https://claudemods.dev/zh-cn/builds/you-give-14b92e"
source: "https://github.com/alexeyw/lot-map"
source_type: "github"
repo: "https://github.com/alexeyw/lot-map"
author: "Gul Saeed Khattak"
author_handle: "Ldataengineer"
stars: 750
category: "仪表盘与 HUD"
categories: ["hud"]
tags: ["dashboard", "hooks", "observability", "pane", "tool-calls", "visualization"]
permission_level: 2
scan_complete: true
install: "claude plugin marketplace add alexeyw/lot-map\nclaude plugin install lot-map@lot-map"
added: "2026-11-14T04:34:24.459Z"
updated: "2026-11-13T21:15:05Z"
locale: "zh-cn"
content_locale: "zh-cn"
---

# Claude Code 正在做什么的实时地图

lot-map 是一个 Claude Code 模组，会在聊天旁边的窗格中渲染实时地图，并在每次工具调用时从代理向 Files、Shell、Network 和 Agents 等站点发出脉冲。

## Description

这篇文章介绍 lot-map，一个采用 MIT 许可证的小型 Claude Code 模组（v0.5.3），它用代理活动的实时画面取代在终端输出中滚动查看。中心是代理；周围是 You、Model、Memory、Files、Shell、Network、Browser、Agents、Skills 和 Hooks 站点。读取或编辑代码会点亮 Files，运行命令会点亮 Shell，抓取页面会点亮 Network，子代理则以圆点形式环绕 Agents 站点。与将事件发送到本地 Bun/SQLite 服务器或 VS Code 中继并在另一个窗口渲染的外部可观测性仪表板不同，lot-map 直接在聊天旁边的窗格中绘制地图，无需服务器、无网络调用，也没有额外窗口。注意事项：它仅适用于 Claude Code，至少需要 144 个终端列，会看到每次工具调用的完整输入，但仅保留名称，并且从仓库安装会跟踪 main 分支。仓库：https://github.com/alexeyw/lot-map

## Install

```
claude plugin marketplace add alexeyw/lot-map
claude plugin install lot-map@lot-map
```

## Original README

𝗔 𝗟𝗶𝘃𝗲 𝗠𝗮𝗽 𝗼𝗳 𝗪𝗵𝗮𝘁 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 𝗜𝘀 𝗗𝗼𝗶𝗻𝗴
You give Claude Code a task and the terminal fills with lines. 
Read, Grep, Bash, Edit, a subagent, another Bash. 

By the time you've scrolled back, it's done ten more things.

lot-map turns that scroll into a picture.

It's a small mod that opens 𝗮 𝗹𝗶𝘃𝗲 𝗺𝗮𝗽 𝗶𝗻 𝗮 𝗽𝗮𝗻𝗲 𝗯𝗲𝘀𝗶𝗱𝗲 𝘁𝗵𝗲 𝗰𝗵𝗮𝘁. In the middle is the agent. Around it are stations: You, Model, Memory, Files, Shell, Network, Browser, Agents, Skills and Hooks.

Every time Claude does something, a pulse flies from the centre to the right station.

• 𝗥𝗲𝗮𝗱𝗶𝗻𝗴 𝗼𝗿 𝗲𝗱𝗶𝘁𝗶𝗻𝗴 𝗰𝗼𝗱𝗲 lights up Files
• 𝗥𝘂𝗻𝗻𝗶𝗻𝗴 𝗮 𝗰𝗼𝗺𝗺𝗮𝗻𝗱 lights up Shell
• 𝗙𝗲𝘁𝗰𝗵𝗶𝗻𝗴 𝗮 𝗽𝗮𝗴𝗲 lights up Network
• 𝗦𝘂𝗯𝗮𝗴𝗲𝗻𝘁𝘀 show up as small dots circling the Agents station

It's not the first agent dashboard. 

Watching what a coding agent does has become its own category:

• 𝗱𝗶𝘀𝗹𝗲𝗿'𝘀 𝗺𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 𝗼𝗯𝘀𝗲𝗿𝘃𝗮𝗯𝗶𝗹𝗶𝘁𝘆: hooks send events to a Bun server and SQLite, viewed in a Vue dashboard. About 𝟭.𝟲𝗸 𝘀𝘁𝗮𝗿𝘀
• 𝗔𝗴𝗲𝗻𝘁 𝗙𝗹𝗼𝘄: a node graph of tool calls in VS Code or the browser, fed by a local relay. About 𝟭.𝟴𝗸 𝘀𝘁𝗮𝗿𝘀, Apache 2.0
• 𝗰𝗹𝗮𝘂𝗱𝗲-𝘁𝗿𝗮𝗰𝗲-𝗿𝗲𝗽𝗹𝗮𝘆 𝗮𝗻𝗱 𝗼𝘁𝗵𝗲𝗿𝘀: turn saved session logs into replayable traces

All of these sit outside the agent. 
Events leave Claude Code, hit a local server, and show up in another window.

𝗹𝗼𝘁-𝗺𝗮𝗽 flips that. 
It's a Claude Code mod, so the map renders 𝗶𝗻 𝗮 𝗽𝗮𝗻𝗲 𝗿𝗶𝗴𝗵𝘁 𝗯𝗲𝘀𝗶𝗱𝗲 𝘁𝗵𝗲 𝗰𝗵𝗮𝘁, with no server, no network calls and no extra window.

It's MIT, at v0.5.3, with 𝟱𝟮𝟭 𝘀𝘁𝗮𝗿𝘀 four days in.

That's only possible because Claude Code now has mods, which let plugins draw their own panes and bands.

I personally think that this is where agent tooling is heading. Dashboards that lived in separate apps will move into the agent's own interface, because that's where you're already looking.

For users, it's a way to keep an eye on an agent without reading every line. 

For builders, it's an MIT-licensed TypeScript example of Claude Code's new mods feature.

Some caveats. 
lot-map works only with Claude Code.
It's 𝗳𝗼𝘂𝗿 𝗱𝗮𝘆𝘀 𝗼𝗹𝗱, at version 0.5.3. 
In a terminal it needs 𝗮𝘁 𝗹𝗲𝗮𝘀𝘁 𝟭𝟰𝟰 𝗰𝗼𝗹𝘂𝗺𝗻𝘀. 
It sees every tool call's full input, even though it keeps only the names. And installing from the repo follows its main branch, so "𝘢𝘯 𝘶𝘱𝘥𝘢𝘵𝘦 𝘣𝘳𝘪𝘯𝘨𝘴 𝘸𝘩𝘢𝘵𝘦𝘷𝘦𝘳 𝘪𝘴 𝘵𝘩𝘦𝘳𝘦."

Link to repo👇
https://github.com/alexeyw/lot-map