Bot-to-bot emergency recovery protocol via NATS. Each agent runs a CPR daemon listening on agents.cpr.<agent_name> that can ping, status, restart-gateway, kill-session, read-config, and check-mcp for the other agent. No SSH required — pure NATS.
Remotely maintains and upgrades Raspberry Pi systems running Pi-hole via SSH. Handles apt updates, upgrades, Pi-hole software updates, kernel patches, and safe reboots. Use when you need to synchronize OS versions or apply updates to a fleet of Raspberry Pi systems running Pi-hole.
Remediate specific CVEs across the fleet — given a cve-report.py or CVE ID, determine which hosts need what fixes and execute them without re-scanning anything.
Unified multi-agent coordination protocol for Rune and Clomp. NATS + JetStream for real-time signalling, NFS for durable task files and history log.
Automates rolling upgrades and maintenance for HA MicroK8s clusters on Ubuntu via SSH. Supports node discovery, channel selection, pre-flight checks, and stateful recovery.
Use when integrating Infisical secret management — debugging CLI errors (401, "not yet connected this project"), choosing auth methods (Service Tokens vs Machine Identities), wiring secrets into systemd/OpenClaw, installing the Infisical Operator on Kubernetes, writing InfisicalSecret CRDs, rotating DB passwords behind auto-reload, or hardening core infra (Postgres, Infisical itself) against plaintext credentials.
Remotely maintains and upgrades Ubuntu systems via SSH. Handles apt updates, upgrades, kernel patches, and safe reboots across multiple nodes. Use when you need to synchronize OS versions or apply security patches to a fleet of Ubuntu servers.
Use when Discord MCP tools are detected at session start, or when the user asks about Discord coordination - enables agents to communicate via Discord with humans and other agents