Skip to content
Automation
Skill

/server-health

Use when you need project-specific compute/server notes to pick a server or confirm a running task, if the project has filled its server manual or monitoring hooks.

Boost this skill
@autoresearch-factoryautoresearch-factory@autoresearch-factory
From plugin
agon
485 skills12 agents4 commands2 hooks
Install
$ npx -y skills add AutoResearch-Factory/Agon --skill server-health --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/server-health

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use when you need project-specific compute/server notes to pick a server or confirm a running task, if the project has filled its server manual or monitoring hooks.

SKILL.md

server-health.SKILL.md
name: server-health
description: Use when you need project-specific compute/server notes to pick a server or confirm a running task, if the project has filled its server manual or monitoring hooks.

Server health snapshot

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.

Usage Contract

  • First read `${CLAUDE_PLUGIN_ROOT}/references/servers_manual.md`.
  • Use only project-provided server labels, paths, queues, and monitoring commands.
  • If the project has not configured compute resources, report `UNKNOWN` and ask the user for server information.
  • Do not guess private hostnames, usernames, storage roots, queues, or GPU availability.

Expected Project Notes

The server manual should define:

  • host labels and access method
  • GPU/CPU/RAM inventory
  • scheduler or launch rules
  • canonical remote project root
  • dataset/cache/checkpoint/result locations
  • how to check load, jobs, disk, and running experiments
Read it on GitHub ↗
Ships withagon

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.

Get the whole plugin
Stats
PythonHTMLBashGitGitHub
+3 tags
LaTeXAnthropicMCP
48
Stars
4
Forks
Active
Maintenance
Python
Language
MIT
License
9d ago
Last commit
2mo ago
Created

Repo: AutoResearch-Factory/Agon

In this plugin
12 agents5 skills4 commands2 hooks
See everything inside

Other skills on agon.