skills.rest
wrensignal
wrensignalCOMMUNITY
Explore all skills by this author →
GitHub

heartbeat-monitor

Aggregate skill health signals and coordinate Telegram alerts and auto-remediation.

Updated Aug 27, 2026
Search Tags:#automation#monitoring#alerts#healthcheck#heartbeat#wrenos
One-click install
npx skills add https://github.com/wrensignal/wrenOS --skill heartbeat-monitor-wrensignal
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: heartbeat-monitor
Source: https://github.com/wrensignal/wrenOS/tree/main/packs/core-skills-pack/heartbeat-monitor
Command: npx skills add https://github.com/wrensignal/wrenOS --skill heartbeat-monitor-wrensignal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Heartbeat Monitor is the always-on watchdog that keeps the WrenOS agent stack healthy by continuously validating the state of all active skills, coordinating alerts, and triggering safe auto-remediation when issues arise.

Core Features & Use Cases

  • Monitors feed_health across every skill and health metrics such as strategy zoo, portfolio risk, and agent infra.
  • Sends Telegram alerts for degraded conditions and escalates to operators under safety or policy concerns.
  • Auto-remediates local issues (e.g., stale configs, missed cycles) and generates daily briefs for morning review.

Quick Start

Deploy the heartbeat-monitor to continuously surveil skill outputs, alert operators via Telegram, and auto-remediate common issues.

Frequently Asked Questions about heartbeat-monitor

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

FAQPage Schema
How do I monitor health signals across multiple active skills?▼

Monitor health signals by aggregating output states and feed_health blocks from active skills to determine overall system health. This process continuously validates skill conditions and coordinates operator alerts.

What is a heartbeat healthcheck and when do I need it for my agent stack?▼

A heartbeat healthcheck continuously validates the state of an agent stack to keep it healthy. You need it when active skills require constant surveillance, alerting, and safe auto-remediation for degraded conditions.

Can I send Telegram alerts when system health degrades?▼

Yes, you can send Telegram alerts for degraded conditions. The monitoring system escalates these alerts to operators specifically when safety or policy concerns arise within the active skill stack.

How do I auto-remediate stale configs and missed cycles locally?▼

Auto-remediate stale configs and missed cycles by enforcing safety rules that read local files while avoiding external queries. This safely resolves common local issues and generates daily health briefs.

Does the heartbeat monitoring process require external network queries?▼

No, heartbeat monitoring enforces safety by reading local files and avoiding external queries entirely. It provides clearly structured outputs for downstream skills without exposing the system to external network risks.

What's the best way to schedule daily health briefs for morning review?▼

Schedule daily health briefs by configuring the monitoring system to aggregate feed_health metrics according to your set schedules. This generates structured morning reviews covering strategy zoo, portfolio risk, and agent infra.

Related Skills

Explore More Software Engineering Skills→
baekenoughbaekenough
13

omcustom:status

Aggregate system health and agent status across components.

Community
Basic
mahmoud20138mahmoud20138
10

telegram-bot

Automate Telegram trading alerts and psychological nudges for risk management.

Community
Intermediate
liangdabiaoliangdabiao
71

video-prompt-generator

Convert natural-language video ideas into structured seven-layer prompts with JSON output.

Community
Advanced
shepard-systemshepard-system
70

obs-alerts

Retrieve active alerts, silences, and Prometheus rule states via Alertmanager and Prometheus APIs.

Official
Intermediate