Stop waiting for prompts. Keep working.

This skill is coherent with its purpose and is instruction-only (no code installs), but it changes your agent's behavior to run frequently and to post or coordinate via channels. Before installing: 1) Confirm which agent identity/session will run cron jobs and limit its permissions (use isolated sessions). 2) Do not grant broad tokens (Discord, Slack, cloud) — give only the minimal channel permissions needed. 3) Start with conservative heartbeat frequency and strict token budgets in config to avoid uncontrolled runs or costs. 4) Review tasks/ and memory/ files for sensitive data that an autonomous agent might read or post. 5) Monitor first runs and logs closely; if you use team channels, consider dedicated channels with limited visibility. If you need higher assurance, request an explicit list of what credentials (if any) you'll need to provide and test in an isolated environment first.

Type: OpenClaw Skill Name: agent-autonomy-kit-backup Version: 1.0.0 The Agent Autonomy Kit is a productivity framework designed to make AI agents proactive by implementing a task queue system and enhanced heartbeat routines. It uses standard markdown files (QUEUE.md, HEARTBEAT.md) for state management and leverages the platform's native cron functionality for scheduling. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the instructions are consistent with the stated goal of autonomous task management.