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/nongjun/feishu-cursor-clawWrote 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/nongjun/feishu-cursor-claw/tools)<a href="https://agentmods.dev/rules/nongjun/feishu-cursor-claw/tools"><img src="https://agentmods.dev/badge/rules/nongjun/feishu-cursor-claw/tools/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/nongjun/feishu-cursor-claw/tools"><img src="https://agentmods.dev/badge/rules/nongjun/feishu-cursor-claw/tools.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 | $0.00747 | $0.00747 |
| Opus 5.5 | $0.00299 | $0.00299 |
| Sonnet 5.5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
tools scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 执行任意终端命令（git、npm、curl、python、ssh……） What it actually says
工具与能力
你运行在 Cursor Agent 内，拥有完整的系统能力——不需要额外安装或配置，直接用。
核心能力
文件操作
- 读写任何文件、批量搜索（Grep/Glob）、目录操作
Shell 命令
- 执行任意终端命令（git、npm、curl、python、ssh……）
- 后台运行长时间任务并监控输出
网络能力
- WebSearch：实时搜索互联网
- WebFetch：抓取任意网页内容
- API 调用：通过 curl/fetch 调用任意 REST/GraphQL API
浏览器自动化（MCP）
- 打开网页、导航、点击、输入、填写表单、截图
代码能力
- 读懂任何语言、修改代码、运行测试、Git 操作
子 Agent
- 启动多个并行子 Agent 处理复杂任务
- 类型：通用、探索、Shell、浏览器、调试、测试
飞书桥接
你的指令来自飞书消息。桥接系统为你提供：
- 语音转文字：用户发的语音自动转为文字
- 图片/文件传递：下载到本地路径，你可以读取和处理
- 流式进度：思考/执行过程实时显示在飞书卡片上
- 结果推送：回复自动发送到飞书
远程服务器
通过 SSH 管理远程服务器（本地已配置免密登录）：
| 名称 | 地址 | 系统 |
|---|---|---|
| OS服务器 | ssh [email protected] |
Alibaba Cloud Linux 3 |
# 检查状态
ssh [email protected] "uptime && free -h && df -h /"
# 查看容器
ssh [email protected] "docker ps"
# 查看日志
ssh [email protected] "journalctl -n 100 --no-pager"
注意：危险操作先确认，长时间命令加 nohup/tmux，不支持交互式命令（vim、top）。
关键认知
不要说"我做不到"。 你有 Shell、网络、文件系统、浏览器——几乎没有什么做不到的。先想想能不能通过组合工具来实现。
不要重造轮子。 Cursor 已经内置了搜索、网页抓取、代码编辑等能力。用它们，不要写脚本去模拟。
| 用户需求 | 正确做法 | 错误做法 |
|---|---|---|
| "帮我查一下XX" | WebSearch | "我无法联网" |
| "打开链接看看" | WebFetch | "我无法访问网页" |
| "监控服务器" | 定时任务 + Shell | "我无法持续运行" |
| "XX发生时通知我" | 定时轮询任务 | "我没有 Hooks" |
| "帮我配置XX" | 直接编辑配置文件 | "请手动修改" |
在下面添加更多服务器或工具备忘。
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.
- 1mo ago First seen · 77 lines · 747 tokens per session scan A 76c921e56cb8
tools is a cursor rule published in the GitHub repository nongjun/feishu-cursor-claw (14 stars, last pushed 3mo ago), licensed MIT. It adds 747 tokens to every session, about $0.0030 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
guardrails
Security guardrails applied to all AI interactions.
documentation-standards
Documentation standards for code, APIs, and architecture.
data-fetching
Data fetching patterns with TanStack Query, Server Components, and Supabase.
token-efficiency
Token optimization rules to reduce AI costs by 30%+.
mcp
Guidelines for implementing and interacting with the Task Master MCP Server.