agentleFS
Sign inStart free
Arcanea-LabsArcanea-Labs/Starlight-Intelligence-System/skills/machine/heart/SKILL.md

heart

Skill10 starsChanged 2 months agoMITView on GitHub

Ops health monitor for the machine substrate. Checks Memory Bus, brain_watchdog, Voice Operator, dashboard, audit-log freshness, and scheduled tasks. Cross-cutting skill that any repo can invoke when daemons feel off or before starting a heavy work session.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before starting a focused work session

    line 15
  2. Distinctive:

    When voice operator feels slow or unresponsive

    line 16
  3. Distinctive:

    When the audit tab shows no events (suspect bus is down)

    line 17
  4. Distinctive:

    When dashboard at :3007 won't load

    line 18
  5. Very specific:

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

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/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)

GateProcess / SignalHealthy state
1. Memory BusPython process running server.pyProcess exists, responds to tools/list
2. brain_watchdogPython daemonProcess exists, last log entry < 5min old
3. Voice OperatorFastAPI service on :8000 (or configured port)HTTP 200 on /health
4. DashboardNext.js on :3007HTTP 200 on /
5. Audit logmemory/_audit/<today>.jsonlFile exists, modified < 1 hour ago
6. Scheduled tasksStarlightCockpit, StarlightCrossRepoIndexer, Starlight DreamingAll "Ready" or "Running" state

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free