Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsScheduled Agent Task Designer: Safe Unattended Prompts
Review, draft and lint prompts for scheduled agent tasks before they run without a human, and check cron next-run times.
$5
Scheduled Agent Task Designer: Safe Unattended Prompts
Example session with this skill installed
Review my nightly cleanup task prompt in task.md before I schedule it, and show me the next five run times for "0 2 * * 1-5".
- Read your context and instructions
- Compiled the scheduled agent task
What happened
The two-line prompt was missing all ten sections an unattended task needs, so the linter failed it. The cron helper then listed the next run times. Real output from the bundled scripts:
$ python scripts/task_lint.py task.md # a two-line "nightly cleanup" prompt
Section checklist:
Trigger MISSING · Read order MISSING · Gate MISSING · Lock MISSING · Stop conditions MISSING
Caps MISSING · Output MISSING · Notifications MISSING · Error handling MISSING · Never MISSING
RESULT: FAIL — 10 missing section(s) (exit 1)
$ python scripts/cron_explain.py --next 5 "0 2 * * 1-5"
1 2026-10-23 02:00 UTC
2 2026-10-26 02:00 UTC
3 2026-10-27 02:00 UTC
4 2026-10-28 02:00 UTC
5 2026-10-29 02:00 UTC
Note: semantics follow Vixie cron (Debian crontab(5)). AWS EventBridge, Quartz, systemd, and Google Cloud Scheduler may differ.
Next steps
- Ask the skill to draft the ten sections for this task.
- Re-run the linter on the draft until it passes.
- Check the next run times against your own scheduler before you deploy.
Connects securely to your tools. The creator never sees your data.
About this skill
Use when you have a prompt for a scheduled or cron-triggered agent task and want a structured review before it runs unattended. The linter checks ten sections (trigger, read order, gate, lock, stop conditions, caps, output, notifications, error handling, never-list) and the cron helper explains an expression and lists the next run times.
Do not use when the task runs interactively with a human in the loop. Do not use when you want to schedule arbitrary shell scripts; this reviews agent task prompts, not shell commands.
Requires: Python 3.9 or later (standard library only).
Limits: Does not connect to any scheduler API or write cron entries. Verify next run times against your own scheduler before deploying.
Does not connect to any scheduler API or write cron entries. Verify next run times against your own scheduler before deploying.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 8 days ago
Requires
Python