cron-mastery
Master OpenClaw's timing systems. Use for scheduling reliable reminders, setting up periodic maintenance (janitor jobs), and understanding when to use Cron vs Heartbeat for time-sensitive tasks.
Best use case
cron-mastery is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Master OpenClaw's timing systems. Use for scheduling reliable reminders, setting up periodic maintenance (janitor jobs), and understanding when to use Cron vs Heartbeat for time-sensitive tasks.
Teams using cron-mastery should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cron-mastery/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cron-mastery Compares
| Feature / Agent | cron-mastery | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Master OpenClaw's timing systems. Use for scheduling reliable reminders, setting up periodic maintenance (janitor jobs), and understanding when to use Cron vs Heartbeat for time-sensitive tasks.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Cron Mastery
**Rule #1: Heartbeats drift. Cron is precise.**
This skill provides the definitive guide for managing time in OpenClaw. It solves the "I missed my reminder" problem by enforcing a strict separation between casual checks (heartbeat) and hard schedules (cron).
## The Core Principle
| System | Behavior | Best For | Risk |
| :--- | :--- | :--- | :--- |
| **Heartbeat** | "I'll check in when I can" (e.g., every 30-60m) | Email checks, casual news summaries, low-priority polling. | **Drift:** A "remind me in 10m" task will fail if the heartbeat is 30m. |
| **Cron** | "I will run at exactly X time" | Reminders ("in 5 mins"), daily reports, system maintenance. | **Clutter:** Creates one-off jobs that need cleanup. |
## 1. Setting Reliable Reminders
**Never** use `act:wait` or internal loops for long delays (>1 min). Use `cron:add` with a one-shot `at` schedule.
### Standard Reminder Pattern (JSON)
Use this payload structure for "remind me in X minutes" tasks:
```json
{
"name": "Remind: Drink Water",
"schedule": {
"kind": "at",
"atMs": <CURRENT_MS + DELAY_MS>
},
"payload": {
"kind": "agentTurn",
"message": "⏰ Reminder: Drink water!",
"deliver": true
},
"sessionTarget": "isolated",
"wakeMode": "next-heartbeat"
}
```
*Note: Even with `wakeMode: "next-heartbeat"`, the cron system forces an event injection at `atMs`. Use `mode: "now"` in the `cron:wake` tool if you need to force an immediate wake outside of a job payload.*
## 2. The Janitor (Auto-Cleanup)
One-shot cron jobs (kind: `at`) disable themselves after running but stay in the list as "ghosts" (`enabled: false`, `lastStatus: ok`). To prevent clutter, install the **Daily Janitor**.
### Setup Instructions
1. **Check current jobs:** `cron:list` (includeDisabled: true)
2. **Create the Janitor:**
* **Name:** `Daily Cron Cleanup`
* **Schedule:** Every 24 hours (`everyMs: 86400000`)
* **Payload:** An agent turn that runs a specific prompt.
### The Janitor Prompt (Agent Turn)
> "Time for the 24-hour cron sweep. List all cron jobs including disabled ones. If you find any jobs that are `enabled: false` and have `lastStatus: ok` (finished one-shots), delete them to keep the list clean. Do not delete active recurring jobs. Log what you deleted."
## 3. Reference: Timezone Lock
For cron to work, the agent **must** know its time.
* **Action:** Add the user's timezone to `MEMORY.md`.
* **Example:** `Timezone: Cairo (GMT+2)`
* **Validation:** If a user says "remind me at 9 PM," confirm: "9 PM Cairo time?" before scheduling.
## 4. The Self-Wake Rule (Behavioral)
**Problem:** If you say "I'll wait 30 seconds" and end your turn, you go to sleep. You cannot wake up without an event.
**Solution:** If you need to "wait" across turns, you **MUST** schedule a Cron job.
* **Wait < 1 minute (interactive):** Only allowed if you keep the tool loop open (using `act:wait`).
* **Wait > 1 minute (async):** Use Cron with `wakeMode: "now"`.
**Example Payload for "Checking back in 30s":**
```json
{
"schedule": { "kind": "at", "atMs": <NOW + 30000> },
"payload": { "kind": "agentTurn", "message": "⏱️ 30s check-in. Report status." },
"wakeMode": "now"
}
```
## Troubleshooting
* **"My reminder didn't fire":** Check `cron:list`. If the job exists but didn't fire, check the system clock vs `atMs`.
* **"I have 50 old jobs":** Run the Janitor manually immediately.Related Skills
ez-cronjob
Fix common cron job failures in Clawdbot/Moltbot - message delivery issues, tool timeouts, timezone bugs, and model fallback problems.
cron-writer
Convert natural language to cron expressions. Use when you need to schedule tasks.
cron-gen
Generate cron expressions from natural language
cron-creator
Create Clawdbot cron jobs from natural language. Use when: users want to schedule recurring messages, reminders, or check-ins without using terminal commands. Examples: 'Create a daily reminder at 8am', 'Set up a weekly check-in on Mondays', 'Remind me to drink water every 2 hours'.
portfolio-watcher
Monitor stock/crypto holdings, get price alerts, track portfolio performance
portainer
Control Docker containers and stacks via Portainer API. List containers, start/stop/restart, view logs, and redeploy stacks from git.
portable-tools
Build cross-device tools without hardcoding paths or account names
polymarket
Trade prediction markets on Polymarket. Analyze odds, place bets, track positions, automate alerts, and maximize returns from event outcomes. Covers sports, politics, entertainment, and more.
polymarket-traiding-bot
No description provided.
polymarket-analysis
Analyze Polymarket prediction markets for trading edges. Pair Cost arbitrage, whale tracking, sentiment analysis, momentum signals, user profile tracking. No execution.
polymarket-agent
Autonomous prediction market agent - analyzes markets, researches news, and identifies trading opportunities
polymarket-5
Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data.