Skip to content
agentusehub
Sign in+ Submit
Software & DevOpsAny

Run production deploys and port scans from Telegram with OpenClaw

A security professional uses an OpenClaw agent with read-only prod access, PR-only changes and manual approval for restarts to deploy changes and scan a VPS for exposed ports.

Read the experience
Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported

Use case overview

A security professional uses an OpenClaw agent with read-only prod access, PR-only changes and manual approval for restarts to deploy changes and scan a VPS for exposed ports.

Read the original report ↗

Reported experience

  1. What they did

    Simon Roses runs an OpenClaw agent, AgentX, on a Raspberry Pi 5 and talks to it through a Telegram bot. He asks it to deploy the latest changes to prod. It has read-only production access, can only open PRs, and needs his manual approval to restart services. It also runs nmap from a VPS over SSH to check his public IP for exposed ports, and alerts him on Telegram.

  2. How it went

    The agent ran port-exposure checks and flagged an example exposed gateway port, with a suggested firewall command. He reports about €50 in API spend after two weeks. It sometimes gets stuck and needs manual intervention.

  3. Worth knowing

    The scans and deploys needed sudo and docker group permissions. Keeping production read-only, PR-only and approval-gated for restarts is the safeguard to copy.

Example prompts

Try with OpenClaw
Work as my ops assistant over [Telegram] with read-only access to [production server]. When I ask, scan [VPS IP/host] for exposed ports and report findings, and propose deploy changes as pull requests on [repo] only. Do not restart services or change anything live until I approve each step.

Related use cases

Software & DevOps

Port a Chrome extension to Safari

The author had ChatGPT take the Session Buddy extension source from Chrome, port it to Safari and install it, taking about 20 minutes.

ChatGPT