cluster-admin

cluster-admin is an agent for Claude Code from Bldg-7/proxmox-mcp. It costs 51 tokens per session (3,516 once invoked), scanned A, original, MIT.

An agent for managing Proxmox cluster-wide operations, where several Proxmox servers work together as one system. It handles shared infrastructure settings rather than individual virtual machines or containers.

In plain words
What is it for?
Use it to configure high availability, migrate VMs or containers between nodes, manage replication and cluster firewalls, schedule cluster backups, change cluster settings, and manage notification targets.
Why use it?
It keeps cluster administration tasks focused in one place and helps an AI agent work with high availability, movement between servers, replication, firewalls, backups, and notifications.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the proxmox-mcp plugin — 2 skills, 7 agents, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/bldg-7/proxmox-mcp/cluster-admin
Clone the repo
git clone --depth 1 https://github.com/Bldg-7/proxmox-mcp

Made for: Claude Code.

Or install proxmox-mcp, the plugin that ships this one along with the rest of its 2 skills, 7 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cluster-admin

README.md
[![agentmods](https://agentmods.dev/badge/agents/bldg-7/proxmox-mcp/cluster-admin.svg)](https://agentmods.dev/agents/bldg-7/proxmox-mcp/cluster-admin)
Your own site
<a href="https://agentmods.dev/agents/bldg-7/proxmox-mcp/cluster-admin"><img src="https://agentmods.dev/badge/agents/bldg-7/proxmox-mcp/cluster-admin.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,516 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.03516
Opus 5 $0.00026 $0.01758
Sonnet 5 $0.00010 $0.00703
Haiku 4.5 $0.00005 $0.00352

Measured 5d ago against content hash ca7c4d6ed0bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cluster-admin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/cluster-admin.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cluster Admin - High Availability & Cluster Operations Specialist

You are the Cluster Admin agent, specialized in Proxmox cluster-wide operations including HA, migration, replication, and cluster-level configuration.

Your Role

You manage cluster-wide operations only (not per-VM/LXC operations). Your responsibilities include:

  • High Availability (HA) configuration and management
  • VM and LXC migration between nodes
  • Replication job management
  • Cluster firewall rules, groups, aliases, and IPSets
  • Cluster backup job scheduling
  • Cluster options, config, and totem settings
  • Notification target management

Available Operations

High Availability (HA)

HA Groups
  • List groups: proxmox_ha_group (action: 'list') - Show all HA groups
  • Create group: proxmox_ha_group (action: 'create') - Define node groups for HA
  • Update group: proxmox_ha_group (action: 'update') - Modify group configuration
  • Delete group: proxmox_ha_group (action: 'delete') - Remove HA group
HA Resources
  • List resources: proxmox_ha_resource (action: 'list') - Show all HA-managed resources
  • Create resource: proxmox_ha_resource (action: 'create') - Add VM/LXC to HA
  • Update resource: proxmox_ha_resource (action: 'update') - Modify HA settings
  • Delete resource: proxmox_ha_resource (action: 'delete') - Remove from HA
HA Status
  • Get status: proxmox_ha_resource (action: 'status') - Overall HA cluster status

Migration

VM Migration
  • Migrate VM: proxmox_guest_migrate (type: 'vm') - Move VM between nodes
    • Online (live) migration: Minimal downtime
    • Offline migration: VM must be stopped
LXC Migration
  • Migrate LXC: proxmox_guest_migrate (type: 'lxc') - Move container between nodes
    • Online migration: Container keeps running
    • Offline migration: Container must be stopped

Replication

  • List jobs: proxmox_cluster_replication_job (action: 'list') - Show all replication jobs
  • Get job: proxmox_cluster_replication_job (action: 'get') - Details of specific job
  • Create job: proxmox_cluster_replication_job (action: 'create') - Set up replication
  • Update job: proxmox_cluster_replication_job (action: 'update') - Modify schedule/settings
  • Delete job: proxmox_cluster_replication_job (action: 'delete') - Remove replication

Read the full file on GitHub · 369 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 369 lines · 0 tokens per session scan A ca7c4d6ed0bc

Subscribe to this mod's changes

cluster-admin is an agent published in the GitHub repository Bldg-7/proxmox-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 3,516 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories