🧪 Community ✓ Claude Code ✓ Claude Desktop Standalone • Cloudops-pack
Cloudops Pack
Cloud & Network Infrastructure — cross-vendor network and cloud infrastructure operations: device/network health, capacity planning, and cost management across whatever network monitoring and cloud platforms you have connected.
Installation
Install this plugin individually:
/plugin marketplace add wyre-technology/msp-claude-plugins --plugin cloudops-pack Or install all MSP plugins at once:
/plugin marketplace add wyre-technology/msp-claude-plugins Features
- Cloud Capacity Planning
- Cloud Cost Management
- Network Health Sweep
Skills
This plugin provides 3 skills that teach Claude about Cloudops Pack:
| Skill | Description |
|---|---|
cloud-capacity-planning | Right-sizing and capacity forecasting for cloud resources on whatever platforms (Azure, DigitalOcean) are connected: the per-platform over-provisioned and under-provisioned signals, growth-trend-based forecasting toward a projected exhaustion window, and the discipline that separates a genuine capacity risk from normal variance — require a trend not a spike, distinguish burst-tolerant from sustained-critical resources, and always state the observation window behind a forecast. |
cloud-cost-management | Cloud spend anomaly detection and reclaimable-spend hunting on whatever platforms (Azure, DigitalOcean) are connected: the signals that make a spend increase an anomaly rather than expected cost, the per-platform orphaned/idle resource catalog (unattached storage, idle load balancers, stopped-but-not-deallocated compute, idle managed databases, orphaned network resources), and how to build a monthly cost trend view — or a clearly labeled inventory-and-list-pricing estimate when a platform exposes no billing data. |
network-health-sweep | A normalized device and network health sweep across whatever network-monitoring tools (Auvik, Meraki, Domotz) are connected: each vendor family's data model and native status fields mapped into one Down/Degraded/Unknown/Healthy taxonomy, default interface error and utilization thresholds, topology-change detection, and why an offline Domotz collector renders its devices "unknown" rather than "down". |
Agents
This plugin provides 3 agents for autonomous task execution:
| Agent | Description |
|---|---|
capacity-forecaster | Use this agent when an MSP needs to know whether current cloud resource capacity will hold up under growth, or which resources are already over- or under-provisioned. |
cost-anomaly-detector | Use this agent when an MSP needs to investigate unexpected cloud spend or hunt for orphaned/idle cloud resources that are still costing money. |
network-health-auditor | Use this agent when an MSP needs a portfolio-wide or single-client sweep of network device and link health across whatever network-monitoring tools are connected. |
Commands
Available slash commands:
| Command | Description |
|---|---|
/capacity-check | Capacity forecast for cloud resources, scoped to a resource type or covering everything connected |
/cost-report | Cloud cost anomaly and reclaimable-spend report for a given window |
/network-sweep | Full network health sweep across all connected network-monitoring tools — devices down, degraded links, and topology changes |
API Reference
| Base URL | |
| Authentication | |
| Rate Limit | |
| Documentation |
Example Usage
Capacity forecast for cloud resources, scoped to a resource type or covering everything connected
/capacity-checkCloud cost anomaly and reclaimable-spend report for a given window
/cost-reportFull network health sweep across all connected network-monitoring tools — devices down, degraded links, and topology changes
/network-sweepUsing Skills
/skill cloudops-pack:cloud-capacity-planning
Right-sizing and capacity forecasting for cloud resources on whatever platforms (Azure, DigitalOcean) are connected: the per-platform over-provisioned and under-provisioned signals, growth-trend-based forecasting toward a projected exhaustion window, and the discipline that separates a genuine capacity risk from normal variance — require a trend not a spike, distinguish burst-tolerant from sustained-critical resources, and always state the observation window behind a forecast.