/heart — Ops Health Monitor

Sibling to /pp (Peak Performance machine audit). Where /pp watches the machine's capacity (RAM, CPU, disk), /heart watches the machine's substrate processes — the daemons that make the cockpit work.

When to invoke

• Before starting a focused work session
• When voice operator feels slow or unresponsive
• When the audit tab shows no events (suspect bus is down)
• When dashboard at :3007 won't load
• Pre-flight before arc <project> if a previous session crashed

What to check (Six Gate scoring)

Score: 6/6 = green. 4-5/6 = yellow (note degraded surface but proceed). <4 = red (stop, fix substrate first).

Implementation (PowerShell)

# Run the shared heart-check script
& "$PSScriptRoot/../../../scripts/heart-check.ps1"

What to do per state

• GREEN — proceed; report 6/6 and move on
• YELLOW — note in response but proceed; user can choose to fix later
• RED on any gate — stop session work; show user how to remediate
  • Memory Bus down: pwsh scripts/start-memory-bus-watcher.ps1
  • Dashboard down: cd private/local-command-center/apps/dashboard && npm run dev
  • Indexer task missing: pwsh scripts/register-cross-repo-indexer-task.ps1

Output format

When /heart is invoked, respond with a compact score card:

/heart — Ops health: 5/6 (YELLOW)

  ✓ Memory Bus
  ✓ brain_watchdog
  ✓ Voice Operator
  ✗ Dashboard (no response :3007 — run: cd private/local-command-center/apps/dashboard && npm run dev)
  ✓ Audit log (12m old)
  ✓ Scheduled tasks (3/3 Ready)

Built on SIP — operational-tier · machine substrate skill