Agent Autonomy Kit.Backup

Stop waiting for prompts. Keep working.

Security Scan

The skill's instructions, files, and requirements are coherent with its stated purpose of enabling autonomous agent work; it is instruction-only and does not request unexpected credentials or install code, but it enables frequent autonomous actions (cron, channel posts) so review operational scope before enabling.

Purpose & Capability

Name/description (make agent proactive) match the included README and SKILL.md. The skill is instruction-only and does not request unrelated binaries, env vars, or paths — everything it asks the operator to create (tasks/QUEUE.md, HEARTBEAT.md, cron jobs, optional team channels) is consistent with the stated goal.

Instruction Scope

Instructions direct the agent to read/write local markdown files (tasks/, memory/) and to post updates to team channels (Discord/Slack) and to schedule cron jobs via openclaw. Those actions are within the autonomy purpose, but they grant broad operational scope (frequent autonomous runs, network posts). The SKILL.md does not direct reading of unrelated system files, nor does it include hidden endpoints.

Install Mechanism

No install spec and no code files — lowest-risk delivery model. Nothing is downloaded or written by the skill itself.

Credentials

The registry metadata declares no required env vars or credentials, but the instructions assume existing channel/configuration (Discord/Slack, openclaw cron) which in practice require tokens/permissions. The skill itself does not request those secrets, so ensure any credentials you grant to the agent are scoped minimally and intentional.

Persistence & Privilege

always:false (normal). However, the guidance explicitly encourages scheduling frequent autonomous heartbeats and cron jobs that run without human prompts. While not a metadata privilege escalation, this amplifies the agent's runtime footprint — increasing potential impact if misconfigured or given excessive permissions.

Assessment

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.

Agent Autonomy Kit

Transform your agent from reactive to proactive.

Quick Start

1. Create tasks/QUEUE.md with Ready/In Progress/Blocked/Done sections
2. Update HEARTBEAT.md to pull from queue and do work
3. Set up cron jobs for overnight work and daily reports
4. Watch work happen without prompting

Key Concepts

• Task Queue — Always have work ready
• Proactive Heartbeat — Do work, don't just check
• Continuous Operation — Work until limits hit

See README.md for full documentation.