Cron

Local-first recurring schedule engine for reminders, repeated tasks, and time-based execution plans. Use whenever the user mentions recurring timing, repetit...

Security Scan

The skill's code, instructions, and declared requirements are consistent with a simple local scheduler that stores data under ~/.openclaw/workspace/memory/cron and does not access external services or unrelated credentials.

Purpose & Capability

Name/description match the included Python scripts: add/list/pause/resume/show/next-run with local JSON storage. The requirement of python3 and the lack of network/third-party credentials are proportionate to a local schedule engine.

Instruction Scope

SKILL.md runtime instructions and the scripts only read/write the declared local storage files and do not reference other system config, credentials, or external endpoints. No vague 'gather context' directives are present.

Install Mechanism

No install spec (instruction-only) and included scripts are plain Python files. Nothing is downloaded or extracted from external URLs.

Credentials

No environment variables or external credentials requested. The code uses the user's home directory (~) for storage, which is appropriate for a local-first scheduler.

Persistence & Privilege

always is false, the skill does not modify other skills or system-wide settings and only creates/updates files under its own ~/.openclaw workspace path.

Assessment

This appears to be a simple, local-only Python-based scheduler. It will create and update files under ~/.openclaw/workspace/memory/cron (jobs.json, runs.json, stats.json); review whether you’re comfortable with those files being created there. No network or external credentials are used. Notes: the code uses naive datetime objects (no timezone-aware handling), so scheduled times may not handle DST/timezone transitions precisely; the default timezone string in add_job.py is 'Asia/Tokyo' but it is only stored as metadata and not enforced. If you want to be extra cautious, inspect the scripts locally before running and run scripts/init_storage.py first to see the created files. Overall internal coherence is good and I see no signs of data exfiltration or unrelated privilege requests.

Turn recurring intentions into structured local schedules.

Core Philosophy

1. Repetition should be captured once, then trusted.
2. A schedule is not just a reminder — it is an execution contract over time.
3. The system should make recurrence visible, editable, and pausable.
4. Users should always know what runs next.

Runtime Requirements

• Python 3 must be available as python3
• No external packages required

Storage

All data is stored locally only under:

• ~/.openclaw/workspace/memory/cron/jobs.json
• ~/.openclaw/workspace/memory/cron/runs.json
• ~/.openclaw/workspace/memory/cron/stats.json

No external sync. No cloud storage. No third-party cron service.

Job Status

• active: schedule is live
• paused: temporarily disabled
• archived: no longer active, kept for history

Schedule Types

• daily
• weekly
• monthly
• interval

Key Workflows

• Capture recurring job: add_job.py
• See what runs next: next_run.py
• Pause or resume: pause_job.py, resume_job.py
• Inspect one job: show_job.py
• Review all jobs: list_jobs.py