Mission Control

CLI-first system health aggregator for autonomous AI agents. Query all agent processes, resources, cron jobs, and services in one shot. Use when a user asks...

Security Scan

The skill's files, commands, and requirements align with a CLI system-health tool for OpenClaw agents: it reads system state and logs and can restart services (with sudo), but it does not ask for unrelated credentials or perform network exfiltration.

Purpose & Capability

Name/description match the provided files: mctl.sh inspects processes, resources, cron entries, and services (including openclaw CLI calls). No unrelated credentials, downloads, or tools are requested. package.json points to the same script as main.

Instruction Scope

Runtime instructions and the script perform broad local reads (pgrep/ps, /proc/loadavg, free, df, systemctl, journalctl, ss, and optionally openclaw and nvidia-smi). This is expected for a monitoring tool, but those operations can reveal sensitive local information (process command lines, logs). The SKILL.md clearly documents the commands and requires confirmation for restart operations.

Install Mechanism

No network install or external downloads; install is a local copy (clawhub or cp). No extract-from-URL or third-party package registries are used.

Credentials

The skill declares no required environment variables or credentials and the script does not attempt to read secrets from unrelated env vars or config paths. It sets a temporary TMPDIR internally when producing JSON.

Persistence & Privilege

always:false and user-invocable:true (normal). The skill can be invoked autonomously by the agent (disable-model-invocation:false), which is platform default; combined with the ability to read logs/process lists, autonomous runs could expose system state without interactive user review. Restart requires sudo and the script documents confirmation is required.

Assessment

This skill appears to do what it says: local monitoring of OpenClaw-related processes, resources, cron jobs, and systemd services. Before installing: 1) Review the mctl.sh script yourself (it runs journalctl, systemctl, pgrep, etc.) if you have sensitive logs or process command-lines you don't want exposed. 2) Ensure the agent will ask you before performing a restart (restart uses sudo). 3) Because the agent can invoke skills autonomously by default, consider whether you trust the agent to run this tool without interactive approval — it only accesses local state and does not call external endpoints, but it can collect potentially sensitive local information. 4) Optionally test on a non-production host first. Minor note: some JSON output paths in the script look slightly buggy (harmless but may affect machine-readable output).

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

Check	Source	Threshold
Agent processes	pgrep	Any running = green
CPU load	/proc/loadavg	>CPUs = yellow
RAM	free -m	>80% = red
Disk	df -h /	>85% = red
GPU/VRAM	nvidia-smi	Optional
Cron	openclaw cron list	Shows schedule
Services	systemctl	active/failed
Ports	ss -ltnp	Informational

Installation

No external dependencies. Requires:

• Bash 4+
• Standard Linux utilities (ps, free, df, ss)
• Optional: nvidia-smi for GPU, openclaw CLI for cron/status

# Install via ClawHub
clawhub install mission-control

# Or manually
cp -r . ~/.openclaw/skills/mission-control/
chmod +x ~/.openclaw/skills/mission-control/scripts/mctl.sh

Integration with OpenClaw

Works with the existing OpenClaw ecosystem:

• openclaw cron - Schedule periodic health checks
• openclaw status - Included in full status report
• openclaw daemon - Monitored as an agent process
• openclaw gateway - Service health checked

When to Use

• Daily health checks for autonomous systems
• Before deployments or major changes
• Debugging performance issues
• Quick "is everything running?" answer
• Automated monitoring via cron
• Post-incident verification

Differences from mission-control-dashboard

Feature	mission-control (this)	mission-control-dashboard
Interface	CLI / agent skill	Web UI (browser)
Use case	Quick status queries	Visual monitoring
Dependencies	Bash only	Python 3.8+
Real-time	On-demand	Polling dashboard
Best for	AI agent queries	Human visual monitoring

Use both together: this skill for agent-driven checks, the dashboard for visual monitoring.

Author

Built for autonomous infrastructure operations.

Price

Free on ClawHub

Tags

#monitoring #agents #health #cli #devops #automation #infrastructure #status

License

MIT