ssh-docker-debug

SSH Docker Debugging

Discover and tail logs for Docker containers on a remote VM over SSH.

Arguments

/ssh-docker-debug <ssh-host> [container-name ...]

• ssh-host (required) — SSH host name as configured in ~/.ssh/config
• container-name (optional, repeatable) — One or more container names or IDs to tail. If omitted, run the discovery phase and ask the user which containers to tail.

IMPORTANT

This skill is strictly read-only on the remote VM. NEVER run docker exec, docker build, docker compose up/down, docker run, docker rm, docker stop, docker restart, or any command that modifies container or host state. Only the following are allowed:

• docker ps (and variants with --format, -a, --filter)
• docker logs (with --tail, --since, -f)
• docker inspect (read-only metadata)
• ssh -G for host resolution
• curl for connectivity checks against services the user explicitly asks about

If the user asks for anything that would mutate state, refuse and explain that this skill is read-only.

Step 1: Resolve the VM IP (optional, for curl checks)

ssh -G <ssh-host> | grep "^hostname "

Use the resolved IP for any curl commands later in the session.

Step 2: Discovery Phase

Run when no container names were supplied, or when the user explicitly asks "what's running" / "list containers" / similar.

List running containers with a clean, parseable format:

ssh <ssh-host> "docker ps --format 'table {{.Names}}\t{{.Image}}\t{{.Status}}\t{{.Ports}}'"

To include stopped containers as well, add -a:

ssh <ssh-host> "docker ps -a --format 'table {{.Names}}\t{{.Image}}\t{{.Status}}'"

Present the list to the user and ask which containers they'd like to tail. If there are obvious candidates based on the user's stated goal (e.g. they mentioned a service name that matches a container), suggest those by name.

Step 3: Tail Logs

For each container the user selected (or supplied as arguments), start a background log stream. Launch all streams in parallel: