Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/zhourong12/cursor-bridgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/zhourong12/cursor-bridge/services)<a href="https://agentmods.dev/rules/zhourong12/cursor-bridge/services"><img src="https://agentmods.dev/badge/rules/zhourong12/cursor-bridge/services/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/zhourong12/cursor-bridge/services"><img src="https://agentmods.dev/badge/rules/zhourong12/cursor-bridge/services.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01389 | $0.01389 |
| Opus 5.5 | $0.00556 | $0.00556 |
| Sonnet 5.5 | $0.00278 | $0.00278 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
services scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
三类服务（必须区分，禁止混为一谈）
本仓库有 三个独立服务。它们职责、进程、端口、启动入口 各不相同。
回答用户「怎么启动」「为什么两个窗口」「连了几个 bot」时，先判断用户指的是哪一类。
1. Bridge Bot 运行时（飞书 ↔ Agent）
| 项 | 说明 |
|---|---|
| 是什么 | 真正连飞书、跑 Cursor/Claude Agent、处理 /schedule 的 Bot 进程 |
| 不是什么 | 不是管理网页；没有给用户点的 Console 窗口；不占 3928 管理端口 |
| 进程 | 每个 Profile 一个 node（lark-channel-bridge run 或后台 daemon） |
| 数据 | ~/.lark-channel/、fleet.json、registry/processes.json |
启动方式（二选一或并存多个 profile）
| 模式 | 适用 | 入口 |
|---|---|---|
| 单 Bot 前台 | 开发调试、只跑 active profile | start.bat → npm run lark-bridge:cursor |
| 单 Bot 重启 | 改 src/ 后 |
restart.bat → npm run lark-bridge:restart |
| Fleet 多 Bot | 多个 Profile 同时在线 | fleet-restart.bat → npm run lark-bridge:fleet-restart |
Fleet 说明：
- 配置在
~/.lark-channel/fleet.json（autoStart、bots） fleet start按 profile 拉起多个 Bot 进程，不是 多开端口、也不是多开 Console- 启动后终端应看到各 Bot 连接信息；汇总：
lark-channel-bridge fleet status --all
与 Console 关系：Bot 可单独跑；Console 只是管理 Bot/Fleet，不会代替 fleet start 或 lark-bridge:cursor 自动起 Bot。
2. Bridge Console · Electron（桌面管理壳）
| 项 | 说明 |
|---|---|
| 是什么 | 本地 管理界面：概览、Bot 绑定、Fleet、进程、定时任务、日志 |
| 不是什么 | 不是飞书 Bot；打开它 不会 自动连接飞书 |
| 端口 | 内嵌 HTTP 3928（仅本机） |
| 窗口 | 1 个 Electron 窗口 |
启动
.\run-console.cmd
# 或 npm run console:run
# 开发：npm run console（electron desktop/electron-main.cjs）
打包：npm run pack:console → release/win-unpacked/Bridge Console.exe
3. Bridge Console · Web（浏览器管理）
| 项 | 说明 |
|---|---|
| 是什么 | 与 Electron 同一套 Admin API + 静态页，用 浏览器 打开 |
| 不是什么 | 不是第三个 Bot；不是「多开一个飞书连接」 |
| 端口 | HTTP 3928（与 Electron Console 共用，同时只能有一个监听） |
| 窗口 | 1 个 浏览器标签/窗口（脚本 --open 自动打开） |
启动
.\console-web.bat
# 或 npm run console:web:build
登录：http://127.0.0.1:3928/?token=<admin-token>（token 在 ~/.lark-channel/admin-token）
互斥与常见误区
| 误区 | 正确说法 |
|---|---|
| 「开了 Console = Bot 已上线」 | 错误。Console 只是管理 UI；Bot 需 Bot 运行时 或 Fleet 单独启动 |
| 「3928 / 3930 各开一个 = 两个 Bot」 | 错误。那是 Console 管理端口；多端口 = 多个 Console 实例，不是多个 Bot |
| 「Electron + 浏览器 = 两个 Bot」 | 错误。是 Console Electron + Console Web 各一个界面；应 二选一 |
| 「Fleet 多 Bot = 多个 Console」 | 错误。Fleet = 多个 Bot 进程；Console 仍然只需 一个（Electron 或 Web） |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 119 lines · 1,389 tokens per session scan A f33cc7b32095
services is a cursor rule published in the GitHub repository zhourong12/cursor-bridge (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,389 tokens to every session, about $0.0056 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.