skills.rest
bjornslib
bjornslibCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

cobuilder-heartbeat

Scan CoBuilder Heartbeat loop for actionable workflow issues and report findings.

Updated Aug 27, 2026
Search Tags:#workflow#monitoring#beads#orchestrator#heartbeat#gchat
One-click install
npx skills add https://github.com/bjornslib/cobuilder-harness --skill cobuilder-heartbeat
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cobuilder-heartbeat
Source: https://github.com/bjornslib/cobuilder-harness/tree/main/.claude/skills/cobuilder-heartbeat
Command: npx skills add https://github.com/bjornslib/cobuilder-harness --skill cobuilder-heartbeat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

CoBuilder Heartbeat provides a continuous supervisory loop inside the session-scoped team to detect actionable issues in the workflow, such as bead readiness, orchestrator health, Git staleness, stale tasks, idle orchestrators, and pending GChat replies, and report them to the Operator.

Core Features & Use Cases

  • Continuous monitoring of beads, orchestrator sessions, Git status, and GChat interactions.
  • Actionable alerting for critical conditions (P0/P1, ORCH_FAILURE) and advisory insights for other states.
  • Deduplicated reporting across up to three cycles to avoid duplicate alerts.
  • Configurable active hours and cost awareness to minimize runtime cost.

Quick Start

Start the Heartbeat loop by spawning the Haiku agent with this skill and running cycles every 600 seconds during your configured active hours.

Frequently Asked Questions about cobuilder-heartbeat

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

FAQPage Schema
How do I monitor orchestrator status and workflow readiness issues automatically?▼

Continuous heartbeat monitoring scans beads readiness, orchestrator status, Git staleness, stale tasks, idle orchestrators, and pending GChat replies every 600 seconds, reporting actionable conditions to the team lead via SendMessage.

How does workflow monitoring handle duplicate alerts for recurring orchestrator issues?▼

Workflow monitoring handles duplicate alerts by deduplicating detected events across up to three cycles, preventing repeated notifications for the same actionable conditions like Git staleness or pending GChat replies.

Can I use this heartbeat monitoring to track pending GChat replies and Git staleness?▼

Yes, heartbeat monitoring tracks pending GChat replies and Git staleness alongside beads readiness, orchestrator status, and stale tasks, reporting all actionable conditions to the Operator for remediation decisions.

Does the workflow heartbeat loop edit code or send messages to external channels?▼

No, the workflow heartbeat loop does not edit code or send messages to external channels, relying entirely on the Operator to decide and execute remediation actions for detected actionable items.

What is the best way to minimize runtime cost during continuous workflow monitoring?▼

The best way to minimize runtime cost during continuous workflow monitoring is to configure active hours and run the supervisory loop on a 600-second cycle, limiting the heartbeat to necessary operational periods.

Related Skills

Explore More Software Engineering Skills→
testdriveraitestdriverai
238

testdriver:client

Initialize the TestDriver client with an API key and connect to a sandbox.

Official
Intermediate
netdatanetdata
1

troubleshoot-kafka

Diagnose Kafka failures by mapping symptoms to Netdata operator playbook archetypes.

Official
Intermediate
LudwigAJLudwigAJ

agent-autonomy-kit

Build a proactive task queue with heartbeat loops and status tracking.

Community
Intermediate
gitgoodordietryinggitgoodordietrying
1

cron-scheduling

Automate recurring task scheduling with cron and systemd timers.

Community
Advanced