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/scheduler-protocolgit 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/scheduler-protocol)<a href="https://agentmods.dev/rules/nongjun/feishu-cursor-claw/scheduler-protocol"><img src="https://agentmods.dev/badge/rules/nongjun/feishu-cursor-claw/scheduler-protocol.svg" alt="Measured on agentmods" 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 | $0.00825 | $0.00825 |
| Opus 5 | $0.00413 | $0.00413 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
scheduler-protocol 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 4d 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
定时任务协议
重要：你拥有定时任务能力
你可以创建定时任务。系统后台运行着一个调度器（Scheduler），它会：
- 监听工作区根目录的
cron-jobs.json文件 - 到达指定时间后自动启动一个新的 Cursor Agent 会话来执行任务
- 将执行结果自动通过飞书推送给用户
所以当用户要求"每天XX点做某事"、"定时提醒"、"周期性检查"时，你应该直接创建任务，不要说"做不到"。
如何创建任务
通过编辑工作区根目录的 cron-jobs.json 来创建任务。如果文件不存在，直接创建它。
cron-jobs.json 结构
{
"version": 1,
"jobs": [
{
"id": "uuid-v4",
"name": "任务描述名",
"enabled": true,
"deleteAfterRun": false,
"schedule": { "kind": "every", "everyMs": 3600000 },
"message": "触发时发送给 Cursor Agent 的 prompt",
"createdAt": "ISO-8601 时间戳",
"updatedAt": "ISO-8601 时间戳",
"state": {}
}
]
}
调度类型
at — 一次性定时
在指定时间执行一次：
{ "kind": "at", "at": "2026-03-01T09:00:00+08:00" }
every — 固定间隔
按毫秒间隔重复执行：
{ "kind": "every", "everyMs": 86400000 }
常用间隔：1小时 = 3600000，6小时 = 21600000，12小时 = 43200000，24小时 = 86400000
cron — Cron 表达式
标准 5 段 cron 表达式，必须指定时区：
{ "kind": "cron", "expr": "0 9 * * 1-5", "tz": "Asia/Shanghai" }
操作规则
- 先读后改 — 编辑前必须先读取
cron-jobs.json，保留所有现有任务 - UUID v4 — 新任务 ID 使用 UUID v4 格式
- message 字段 — 写入触发时要执行的完整 prompt（系统会把它发送给 Cursor Agent）
- 一次性任务 — 设置
deleteAfterRun: true，执行后系统自动删除 - state 字段 — 系统内部管理，不要手动修改
- 时区 — cron 表达式必须包含
tz，默认Asia/Shanghai - 时间戳 —
createdAt和updatedAt使用 ISO-8601 格式（带时区偏移）
常见场景
| 用户说 | 调度方式 | 配置 |
|---|---|---|
| "每天早上9点检查邮件" | cron | "0 9 * * *" |
| "每小时检查服务器状态" | every | 3600000 |
| "明天下午3点提醒我开会" | at | 具体 ISO 时间戳 + deleteAfterRun: true |
| "工作日早上9点汇报" | cron | "0 9 * * 1-5" |
| "每6小时备份一次" | every | 21600000 |
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.
- 4d ago First seen · 90 lines · 825 tokens per session scan A 606dff718eb0
scheduler-protocol is a cursor rule published in the GitHub repository nongjun/feishu-cursor-claw (14 stars, last pushed 1mo ago), licensed MIT. It adds 825 tokens to every session, about $0.0041 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.
mcp
Guidelines for implementing and interacting with the Task Master MCP Server.
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.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.