Mission Control

Overview

Single-command health aggregator for autonomous AI infrastructure. Replaces checking 5+ separate tools by collecting agent status, resource health, cron jobs, and service state into one report.

Designed for operators running autonomous agents (OpenClaw daemons, AOMS, VPS workers) who need a fast answer to "is everything OK?"

Core Rules

• Read-only by default. Only restart mutates state and requires confirmation.
• Prefer --json output when piping to other tools or storing results.
• Do not invent OpenClaw CLI flags. Use only documented commands.
• When the user asks "what's running?" or "system status" - run mctl status for the full picture.

Commands

Full Status (default)

bash scripts/mctl.sh status

Returns: agents, resources (CPU/RAM/disk/GPU), cron jobs, services, OpenClaw status.

Agent List

bash scripts/mctl.sh agents

Detects running processes matching: openclaw daemon, openclaw gateway, and any process with "agent", "daemon", "worker", or "aoms" in its name. Shows PID and uptime.

Resource Health

bash scripts/mctl.sh health

CPU count, load average, RAM usage, disk usage, NVIDIA GPU (if present). Color-coded thresholds:

• Green: <60% usage
• Yellow: 60-80%
• Red: >80%

Cron Jobs

bash scripts/mctl.sh cron

Lists OpenClaw cron jobs via openclaw cron list.

Services

bash scripts/mctl.sh services

Checks systemd status for openclaw-gateway and openclaw-daemon. Also shows listening ports.

View Logs

bash scripts/mctl.sh logs [service-name]

Shows last 50 lines from the past hour for a systemd service. Defaults to openclaw-daemon.

Restart Service

bash scripts/mctl.sh restart <service-name>

Restarts a systemd service. Requires sudo. Always confirm with the user before running.

JSON Output

Add --json to any command for machine-readable output:

bash scripts/mctl.sh --json status

Usage Examples

Quick daily check

User: "How's the system?"
Agent: runs `mctl status` and summarizes findings

Debug a slow agent

User: "Why is my daemon slow?"
Agent: runs `mctl health` to check resources, then `mctl logs openclaw-daemon`

Pre-deployment check

User: "Is everything healthy before I deploy?"
Agent: runs `mctl --json status`, checks for red flags, gives go/no-go

Automated monitoring via cron

# Add to openclaw cron for daily checks
openclaw cron add --name "mission-control:daily" \
  --schedule "0 8 * * *" \
  --command "bash ~/.openclaw/skills/mission-control/scripts/mctl.sh --json status > /tmp/mctl-status.json"

What Gets Checked