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.
npx skills add pwdev-solucoes/pwdev-claude-marketplace --skill proxmox-engineergit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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.
[](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/proxmox-engineer)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/proxmox-engineer"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/proxmox-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/proxmox-engineer"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/proxmox-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.00812 |
| Opus 5 | $0.00048 | $0.00406 |
| Sonnet 5 | $0.00019 | $0.00162 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
proxmox-engineer 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proxmox Engineer
Você opera infraestrutura própria. Erro de quorum ou de Ceph tira o cluster inteiro do ar.
Como este plugin acessa
Não há MCP nem CLI local. Os caminhos são:
- SSH no nó —
pvesh,pct,qm,ceph(mais direto) - API REST —
https://host:8006/api2/jsoncom token
Sem acesso configurado: modo consultivo — entrega o comando, o usuário roda.
Portão de segurança
pvesh get, qm list, ceph status rodam livres.
qm start|stop, pct, migração, alteração de storage exigem confirmação.
Remover VM, container ou OSD é destrutivo.
Cluster e quorum
pvecm status # quorum é a primeira coisa a olhar
pvecm nodes
systemctl status corosync
Cluster sem quorum entra em read-only. Com 3 nós, perder 2 mata o quorum. Nunca reinicie um segundo nó antes de o primeiro voltar — é assim que se transforma manutenção em incidente.
Quorum perdido não se resolve com pressa. Restaure o nó faltante; forçar quorum
(pvecm expected 1) é último recurso e pode causar split-brain.
Ceph
ceph status
ceph osd tree
ceph health detail
ceph df
| Estado | Significa |
|---|---|
HEALTH_OK |
ok |
HEALTH_WARN + backfill |
rebalanceando — espere, não intervenha |
HEALTH_ERR |
perda de dado possível — pare e avalie |
PG inactive |
dado indisponível |
Nunca remova um OSD durante rebalanceamento. Espere HEALTH_OK.
Remover OSD com PG degradada é a forma mais rápida de perder dado.
Ceph precisa de espaço livre para rebalancear: acima de 85% de uso, o cluster entra em risco. Trate 80% como alerta.
VM e LXC
qm list ; qm config VMID ; qm status VMID
pct list ; pct config CTID
| Sintoma | Verificar |
|---|---|
| VM não inicia | storage disponível, RAM livre, disco existe |
| Migração falha | storage compartilhado, versão dos nós, rede |
| LXC sem rede | bridge, VLAN, firewall do nó |
| Disco cheio no host | /var/log, snapshot antigo, backup local |
Backup — PBS
- Verifique retenção e verificação de integridade (
verify) - Backup nunca restaurado não é backup — ver
backup-dr - Backup no mesmo storage do dado não protege contra falha de storage
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.
- 7d ago First seen · 92 lines · 95 tokens per session scan A 47003d982aeb
proxmox-engineer is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 812 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
together-kueue
Install and use the Kueue job-queueing controller on a Together AI Kubernetes GPU cluster to gate jobs on quota. Covers installing Kueue, defining ResourceFlavor, ClusterQueue, and LocalQueue quota, submitting jobs to a queue, and watching quota admit or suspend them. Reach for it when a Together cluster's GPU pool…
edge-computing-expert
Design and implement production-grade edge computing solutions including CDN optimization, fog computing architectures, and distributed edge workloads. Use when the user mentions edge computing, CDN or edge caching, fog computing, MEC, IoT edge workloads, or latency-sensitive distributed deployments.
Infrastructure Development
Enterprise infrastructure patterns for AWS VPC, ECS, and PrivateLink deployments.
live-demo
Add temporary, isolated hosted sessions to a tested robotics application.
mk8s-byok
Runs workloads on your own hardware and provisions managed Kubernetes (mk8s) clusters on Control Plane. Use when the user asks about bare metal, on-prem, data centers, their own servers, mk8s, BYOK, or node pools.
graviton-migration
Execute a workload migration from x86 (amd64) to AWS Graviton (arm64) — set up the Arm migration MCP server for code, dependency, and container arm64-readiness scanning, then run the migration — pre-migration scanning, Karpenter arm64 node cutover, and multi-arch CI pipelines. Use when someone says "migrate to…