From agon
Loads project-specific compute/server notes from a server manual to select a server or verify running tasks. Activates when the project has configured compute resources.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agon:server-healthThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Placeholder for project-specific compute availability.
Placeholder for project-specific compute availability.
This release intentionally ships no private server names, accounts, paths, queues, credentials, or monitoring scripts. Projects should fill references/servers_manual.md or replace this skill with their own health collector.
${CLAUDE_PLUGIN_ROOT}/references/servers_manual.md.UNKNOWN and ask the user for server information.The server manual should define:
npx claudepluginhub autoresearch-factory/agonManages physical server infrastructure, bare metal systems, and OOB management (iDRAC/iLO/IPMI). Handles SSH connectivity audits, hardware health checks, boot time estimation, and recovery actions.
Manages Agents Observe server: start/stop/restart, view dashboard, check stats, tail logs (Docker, CLI, MCP), and diagnose issues.
Query and monitor Unraid servers via GraphQL API. Access system info, disk health, logs, Docker containers, VMs, and array status through command-line scripts.