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 skills add EthanChan050430/Saki-AI --skill qqbot-crongit clone --depth 1 https://github.com/EthanChan050430/Saki-AIWrote 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/skills/ethanchan050430/saki-ai/qqbot-cron)<a href="https://agentmods.dev/skills/ethanchan050430/saki-ai/qqbot-cron"><img src="https://agentmods.dev/badge/skills/ethanchan050430/saki-ai/qqbot-cron/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/skills/ethanchan050430/saki-ai/qqbot-cron"><img src="https://agentmods.dev/badge/skills/ethanchan050430/saki-ai/qqbot-cron.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 | $0.00043 | $0.04802 |
| Opus 5 | $0.00022 | $0.02401 |
| Sonnet 5 | $0.00009 | $0.00960 |
| Haiku 4.5 | $0.00004 | $0.00480 |
Grade A, and why
qqbot-cron 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 9d 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 — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QQ Bot 智能提醒
让 AI 帮用户设置、管理定时提醒,支持私聊和群聊。
⛔ 最重要的一条规则(读三遍)
调用 cron 工具时,payload.kind 必须是
"agentTurn"。绝对不能用"systemEvent"!
systemEvent只会在 AI 会话里插入一条文本,用户根本收不到 QQ 消息。 只有agentTurn+deliver: true+channel: "qqbot"+to才能真正把消息发到 QQ。
🤖 AI 决策指南
时间确认规则
设置提醒前,先确认当前系统时间(查看上下文中的时间信息,或执行
date)。 纯相对时间("5分钟后"、"1小时后")可以跳过确认,直接算Date.now() + 延迟毫秒。
用户意图识别
| 用户说法 | 意图 | cron 工具 action |
|---|---|---|
| "5分钟后提醒我喝水" | 创建一次性提醒 | add(schedule.kind=at) |
| "每天8点提醒我打卡" | 创建周期提醒 | add(schedule.kind=cron) |
| "我有哪些提醒" | 查询 | list |
| "取消喝水提醒" | 删除 | remove |
| "修改提醒时间" | 删除+重建 | remove → add |
| "提醒我" (无时间) | 需追问 | 询问具体时间 |
必须追问的情况
- 没有时间:"提醒我喝水" → "请问什么时候提醒你?"
- 时间模糊:"晚点提醒我" → "具体几点呢?"
- 周期不明:"定期提醒我" → "多久一次?每天?每周?"
📋 创建提醒(最重要)
🚨🚨🚨 工具调用参数模板(AI 必须严格遵循)
AI 调用 cron 工具时,传的是 JSON 参数,不是 CLI 命令。以下是唯一正确的 JSON 格式:
一次性提醒(N 分钟后):
{
"action": "add",
"job": {
"name": "{任务名}",
"schedule": {
"kind": "at",
"atMs": {当前时间戳毫秒 + N分钟*60000}
},
"sessionTarget": "isolated",
"wakeMode": "now",
"deleteAfterRun": true,
"payload": {
"kind": "agentTurn",
"message": "你是一个暖心的提醒助手。请用温暖、有趣的方式提醒用户:{提醒内容}。要求:(1) 不要回复HEARTBEAT_OK (2) 不要解释你是谁 (3) 直接输出一条暖心的提醒消息 (4) 可以加一句简短的鸡汤或关怀的话 (5) 控制在2-3句话以内 (6) 用emoji点缀",
"deliver": true,
"channel": "qqbot",
"to": "{openid}"
}
}
}
周期提醒(每天/每周):
{
"action": "add",
"job": {
"name": "{任务名}",
"schedule": {
"kind": "cron",
"expr": "0 8 * * *",
"tz": "Asia/Shanghai"
},
"sessionTarget": "isolated",
"wakeMode": "now",
"payload": {
"kind": "agentTurn",
"message": "你是一个暖心的提醒助手。请用温暖、有趣的方式提醒用户:{提醒内容}。要求:(1) 不要回复HEARTBEAT_OK (2) 不要解释你是谁 (3) 直接输出一条暖心的提醒消息 (4) 可以加一句简短的鸡汤或关怀的话 (5) 控制在2-3句话以内 (6) 用emoji点缀",
"deliver": true,
"channel": "qqbot",
"to": "{openid}"
}
}
}
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.
- 9d ago First seen · 513 lines · 43 tokens per session scan A a57bcdb129bf
qqbot-cron is a skill published in the GitHub repository EthanChan050430/Saki-AI (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 4,802 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
omh-automation-blueprint
This is a Hermes-native automation-blueprint workflow skill.
omh-morning-brief
This is a Hermes-native morning-brief workflow skill.
omh-deliverable-package
This is a Hermes-native deliverable-package workflow skill.
omh-voice-input
This is a Hermes-native voice-operator workflow skill.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
obsidian
Read, search, create, or edit notes in an authorized Obsidian vault while preserving frontmatter, wikilinks, and unrelated notes.