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.
npx agentmods add rules/nongjun/feishu-cursor-claw/cursor-capabilitiesgit clone --depth 1 https://github.com/nongjun/feishu-cursor-clawWhat 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 | $0.00541 | $0.00541 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
cursor-capabilities 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 3d 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.
What it actually says
Cursor Agent 能力引导
完整的工具清单见 .cursor/TOOLS.md。这里只列出遇到具体需求时该怎么做。
决策树
用户说"帮我查XX最新价格/新闻/信息"
→ WebSearch 搜索 → 返回结果
用户说"帮我看看这个网站/链接"
→ WebFetch 抓取内容 → 分析并回复
用户说"每天早上9点提醒我XX"
→ 编辑 cron-jobs.json 创建定时任务（详见 scheduler-protocol.mdc）
用户说"监控服务器/检查某个状态"
→ 创建定时任务，message 里写 Shell 检查命令
用户说"当XX发生时通知我"
→ 创建定时轮询任务（每N分钟检查一次条件）
用户说"帮我整理这个文件夹"
→ Glob 列出文件 → Read 读取 → Write/Shell 整理
用户说"帮我写个脚本/程序"
→ Write 创建文件 → Shell 测试运行
用户说"记住XX / 以后注意XX"
→ 写入 .cursor/memory/YYYY-MM-DD.md 或 .cursor/MEMORY.md
用户说"帮我在网页上操作/填表/点击"
→ Browser MCP（browser_navigate → browser_snapshot → browser_click/fill）
用户说"这个任务很复杂/需要同时处理多个事"
→ 启动多个子 Agent 并行处理
三条原则
- 先行动后汇报 — 不要问"要不要我帮你搜索？"，直接搜。
- 组合能力 — 复杂任务通过组合多个工具完成（Shell + 网络 + 文件 + 定时）。
- 不说做不到 — 如果看起来不可能，想想能否通过工具组合实现。
输出格式约束
回复通过飞书卡片展示，受以下限制：
- 单张卡片最多 5 个 Markdown 表格，建议不超过 4 个
- 卡片总大小 30KB（约 3500-4000 中文字符）
- 超限内容会被截断或渲染失败
应对策略：内容多时主动分次回复，少用表格多用列表，先给结论再展开。
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.
- 3d ago First seen · 59 lines · 541 tokens per session scan A c93a8c087aeb
cursor-capabilities is a cursor rule published in the GitHub repository nongjun/feishu-cursor-claw (14 stars, last pushed 1mo ago), licensed MIT. It adds 541 tokens to every session, about $0.0027 per session on Opus 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 2026-08-30.
Other cursor rules, from other repositories
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
general
You are running in Cursor IDE. The tools of the MCP server that you are developing are connected to this IDE. When you've modified the code and want to use updated functionality, you must prompt the user to reload the server first.
new_features
Guidelines for integrating new features into the Task Master CLI.
utilities
// ✅ DO: Create focused, reusable utilities /.
commands
Guidelines for implementing CLI commands using Commander.js.
architecture
Describes the high-level architecture of the Task Master CLI application.