Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Create and manage OpenClaw cron jobs following our conventions. Use when setting up periodic tasks, reminders, automated checks, or any scheduled work.
Create and manage OpenClaw cron jobs following our conventions. Use when setting up periodic tasks, reminders, automated checks, or any scheduled work.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Our conventions for creating cron jobs in OpenClaw.
SettingDefaultWhyModelanthropic/claude-sonnet-4-5Reliable tool calls, works with any Anthropic Max plan โ no OpenRouter neededSessionisolatedCron jobs run in their own session, not the main chatDelivery"mode": "none"Job handles its own output (posts to Discord, etc.)Timeout120-180sMost jobs should finish fast
Default to Sonnet (anthropic/claude-sonnet-4-5). Reliable, portable (no OpenRouter API key needed). DeepSeek is unreliable for tool calls โ don't use it for cron jobs. Use Opus (anthropic/claude-opus-4-6) only as a last resort โ expensive for scheduled tasks. Model ID format: Use anthropic/claude-sonnet-4-5 not the full dated version (anthropic/claude-sonnet-4-20250514).
{ "name": "descriptive-kebab-case-name", "schedule": { "kind": "cron", "expr": "*/30 * * * *", "tz": "America/New_York" }, "sessionTarget": "isolated", "payload": { "kind": "agentTurn", "message": "TASK INSTRUCTIONS HERE", "model": "openrouter/deepseek/deepseek-v3.2", "timeoutSeconds": 120 }, "delivery": { "mode": "none" } }
PatternCron ExpressionNotesEvery 30 min*/30 * * * *Good for inbox checks, monitoringEvery hour0 * * * *Self-reflection, status checksDaily at 4 AM0 4 * * *Cleanup, backups (during quiet hours)Daily at 6 AM0 6 * * *Morning digests, daily summariesWeekly Monday 2 PM0 14 * * 1Weekly outreach, reviewsOne-shotUse "kind": "at" insteadReminders, one-time tasks
Be explicit with commands โ Give the cron agent exact bash commands to run. It doesn't have our context. Include skip conditions โ If there's nothing to do, the agent should reply SKIP to avoid wasting tokens. Handle its own output โ The job should post results to Telegram (or wherever) using the message tool directly. Don't rely on delivery mode for formatted output. Include error handling โ What should happen if a command fails? Keep instructions self-contained โ The cron agent wakes up with no context. Everything it needs should be in the task message.
ModeWhen to Use"mode": "none"Job posts its own output to Telegram (most common)"mode": "announce"OpenClaw auto-delivers the agent's final message to a channel. Use when output IS the message (e.g., daily digest). Set "channel": "telegram" and "to": "-1003856094222:TOPIC_ID"
โ Don't use Opus for cron jobs unless the task genuinely needs it. Most cron tasks are simple checks. โ Don't use heartbeat for things that can be a cron job. Heartbeat runs in the main session (Opus) and costs way more. โ Don't create cron jobs that loop/poll โ each run should be a single check. If you need polling, use a background exec script instead. โ Don't set delivery mode to "announce" and also have the job post to Telegram โ you'll get duplicate messages.
Check current jobs anytime with the cron list tool. As of setup: workspace-activity-feed โ Every 30 min, commits workspace changes, posts to activity feed agentmail-inbox-check โ Every 30 min, checks for new emails, responds to agents sub-agent-monitor โ Every 15 min, checks on stalled sub-agents self-reflection โ Hourly, reviews recent sessions for lessons learned daily-workspace-commit โ Daily 4 AM, git commits workspace changes system-watchdog โ Daily 4 AM, checks system resources OpenClaw Daily News Digest โ Daily 6 AM, generates news digest sticker-sales-loop โ Weekly Monday 2 PM, agent outreach for sticker store
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.