recipe-persistent-monitor

Run a long-running monitoring agent with heartbeats, cron reports, and webhook events.

21|4|Updated Feb 19, 2026

Search Tags:#monitoring #agent #observability #webhook #cron #heartbeat #cost-control

Ready to run

npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill recipe-persistent-monitor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: recipe-persistent-monitor
Source: https://github.com/tylerjrbuell/reactive-agents-ts/tree/main/apps/docs/skills/recipe-persistent-monitor
Command: npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill recipe-persistent-monitor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a production-grade long-running monitoring agent that automates periodic health checks, daily reporting, webhook-driven triggers, and enforces cost and token budgets to prevent runaway usage and missed incidents.

Core Features & Use Cases

Adaptive Heartbeats: Periodic heartbeats with adaptive skipping to avoid unnecessary runs while guaranteeing wake-ups after configurable skip limits.
Scheduled Reporting: Cron-based daily reports with timezone-aware schedules for weekday operational summaries.
Webhook Integration & Policies: Secure webhook adapters with secret verification, rate limiting, daily token/cost budgets, and graceful SIGINT/SIGTERM shutdown for safe operations.
Use Case: Run an ops monitor that checks service status every 30 minutes, accepts GitHub webhook events, generates a 9am weekday report, and stops automatically when daily budgets are exceeded.

Quick Start

Start the persistent monitoring agent to run an immediate heartbeat and generate today's operations report.

Frequently Asked Questions about recipe-persistent-monitor

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

FAQPage Schema

How do I build a long-running monitoring agent with cost control and webhook support?▼

A long-running monitoring agent automates periodic health checks, cron-based reporting, and webhook triggers while enforcing daily token and cost budgets. You configure adaptive heartbeats, timezone-aware schedules, and rate limiting to maintain production operations safely.

How do I enforce daily token and cost budgets for an automated operations agent?▼

To enforce daily token and cost budgets, the monitoring agent applies rate and token policy enforcement alongside cost tracking. It automatically stops operations when daily budgets are exceeded, preventing runaway usage and unexpected charges.

Can I schedule cron-based daily reports with timezone awareness for production monitoring?▼

Yes, you can schedule cron-based daily reports with timezone-aware schedules for weekday operational summaries. This allows the monitoring agent to generate reports at specified times, such as a 9am weekday report, aligned with your operational timezone.

How do webhook adapters with secret verification work for production monitoring agents?▼

Webhook adapters with secret verification secure external event triggers by validating incoming payloads against a configured secret. This ensures only authenticated events, such as GitHub webhook triggers, are processed by the monitoring agent.

How do I handle graceful SIGINT and SIGTERM shutdown in a persistent monitoring agent?▼

Graceful SIGINT and SIGTERM shutdown handling ensures the persistent monitoring agent stops safely without losing data or leaving operations hanging. It intercepts termination signals to cleanly exit heartbeat loops and cron schedules.

What is adaptive heartbeat scheduling and when do I need it for health checks?▼

Adaptive heartbeat scheduling skips unnecessary periodic health checks while guaranteeing wake-ups after configurable skip limits. You need it for production monitoring to reduce redundant operations and conserve token budgets without missing critical status checks.