Heartbeat

Analyze cron state, GitHub activity, and memory items to report operational health.

6|2|Updated May 21, 2026
One-click install
npx skills add https://github.com/anajuliabit/aeon --skill heartbeat-anajuliabit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Heartbeat
Source: https://github.com/anajuliabit/aeon/tree/main/skills/heartbeat
Command: npx skills add https://github.com/anajuliabit/aeon --skill heartbeat-anajuliabit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Heartbeat proactively detects failures and operational drift in scheduled skills so your autonomous agent framework stays reliable without constant human supervision.

Core Features & Use Cases

  • Detects failed and stuck skills by reading per-skill scheduler state and surfacing skills that failed, hung, or never reported back.
  • Flags quality and dependency degradation by analyzing consecutive failures, chronic low success rates, and shared error signatures.
  • Monitors urgent work and coverage by identifying stalled PRs/issues, flagged memory items needing follow-up, and missing scheduled skill dispatches.

Quick Start

Run Heartbeat with the desired focus area by setting var to the target subsystem (or leave it empty to run all checks) so it generates a single prioritized notification and refreshes the public status page.

Frequently Asked Questions about Heartbeat

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor scheduled jobs and detect failures in an autonomous agent fleet?

Heartbeat detects operational issues across an autonomous agent's scheduled skill fleet by analyzing cron state, GitHub activity, and flagged memory items. It computes an overall health verdict and regenerates a status markdown file with deduplicated notifications.

What is the best way to track operational health and stalled GitHub PRs for autonomous agents?

Tracking operational health and stalled GitHub PRs is done by analyzing GitHub activity alongside per-skill scheduler state. Heartbeat identifies stalled PRs, failed jobs, and flagged memory items needing follow-up to keep your framework reliable without human supervision.

Can I use cron state files to detect stuck or missing dispatch coverage?

Yes, you can use cron state files to detect stuck or missing dispatch coverage. Heartbeat reads memory/cron-state.json to surface skills that failed, hung, never reported back, or missed scheduled dispatches.

How do I flag quality degradation and consecutive failures in scheduled skills?

To flag quality degradation and consecutive failures in scheduled skills, analyze consecutive failures, chronic low success rates, and shared error signatures. Heartbeat identifies these patterns to detect operational drift in your autonomous fleet.

Do I need any dependencies to run operational health checks on my agent fleet?

No dependencies are required to run operational health checks on your agent fleet. Heartbeat operates independently by reading existing cron state, GitHub activity, and memory items to generate prioritized notifications and refresh the status page.