Quick Reminders
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A background process remains active until the reminder fires or is canceled, and reminders will not survive a machine reboot.
The skill intentionally leaves a local process running after the initial request so the reminder can fire later; this is disclosed and purpose-aligned.
Each reminder spawns **one detached `nohup` process** that sleeps for the specified duration, then calls `openclaw message send` and self-removes from `reminders.json`.
Use this for short reminders only, and use the provided list/remove commands to review or cancel pending reminders.
If the channel or target is wrong, the reminder message could be sent to the wrong chat or contact.
The reminder is delivered using the user's already configured OpenClaw messaging authority.
openclaw message send --channel "$channel" --target "$target" --message "$(cat "$msg_file")"
Verify the channel and target in TOOLS.md or in the command before relying on the skill.
Reminder text and chat or phone identifiers may remain in local files until the reminder is fired, canceled, or cleaned up.
The skill persists delivery target information and active reminder text/metadata in local files so future reminders can be sent correctly.
`TOOLS.md` | Read (always), write (once, if delivery target missing) ... `./reminders.json` | Read/write | Tracks active reminders
Avoid putting highly sensitive content in reminder text, and review or delete TOOLS.md entries and reminders.json if needed.