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 WYRE-AI/msp-claude-plugins --skill cloud-capacity-planninggit clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote 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/wyre-ai/msp-claude-plugins/cloud-capacity-planning)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/cloud-capacity-planning"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/cloud-capacity-planning/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/wyre-ai/msp-claude-plugins/cloud-capacity-planning"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/cloud-capacity-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00089 | $0.01704 |
| Opus 5 | $0.00044 | $0.00852 |
| Sonnet 5 | $0.00018 | $0.00341 |
| Haiku 4.5 | $0.00009 | $0.00170 |
Grade A, and why
Cloud Capacity Planning 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 6d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Capacity Planning
Overview
Capacity planning answers two distinct questions that are easy to conflate: "is this resource sized correctly right now" (right-sizing) and "will it still be sized correctly in N weeks given its growth trend" (forecasting). This skill covers both, across whatever cloud platform(s) an org has connected, and is deliberately conservative about calling something a risk — a capacity plan that cries wolf on every metric blip gets ignored.
This is infrastructure-substrate capacity — compute, storage, database, and
cluster headroom on the platforms themselves. It is not application-level
performance or SLO tracking (see devops-pack, if connected) and it is not
spend (see the cloud-cost-management skill, a related but separate
concern: a resource can be correctly sized and still be a cost problem, or
be under-provisioned and cheap).
Anti-triggers
- A one-off quota or usage-limit lookup — "what's my quota, how much is
used" is a direct read against the connector; use
azure-mcp-cost-and-capacity. This skill turns repeated readings into a trend and a forecast. - The metric and log queries behind the utilization numbers — use
azure-mcp-observability.
Discovering available tools first
Never assume which cloud platform is connected:
- Call
conduit__search_toolswith a query like"list resources","resource group","droplet", or"quota"to discover which cloud platform connector(s) are live and their actual tool names (e.g.azure-mcp__group_resource_list,azure-mcp__quota,digitalocean__list_droplets,digitalocean__list_kubernetes_clusters,digitalocean__list_databases). - More than one cloud platform can be connected (an org running both Azure and DigitalOcean). Cover all connected platforms; don't stop at the first.
- Only call concrete tools that discovery actually returned.
Key Concepts
Right-sizing signals, per platform
| Platform | Over-provisioned signal | Under-provisioned signal |
|---|---|---|
| Azure | Resource group / subscription quota usage well below allocated quota (via azure-mcp__quota); Advisor recommendations flagging low-utilization VMs or oversized SKUs (via azure-mcp__advisor); sustained low CPU/memory/IOPS in azure-mcp__monitor metrics against an oversized SKU |
Quota usage approaching the allocated limit; Advisor or azure-mcp__resourcehealth flagging throttling, sustained high utilization, or scale-limited resources |
| DigitalOcean | A Droplet or Database sized well above its sustained CPU/memory/disk usage; a DOKS node pool with persistently low node utilization; unattached or lightly used block storage | A Droplet or Database consistently near its CPU/memory/disk ceiling; a DOKS cluster with pods pending due to insufficient node capacity; a Database approaching connection-limit or storage-limit thresholds |
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.
- 6d ago First seen · 157 lines · 89 tokens per session scan A bcb7e13bed27
Cloud Capacity Planning is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 7d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,704 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
rented-server-setup
Runs an open model in the cloud two ways, and makes the user choose with real numbers. Route A is OVHcloud AI Endpoints, an EU-owned per-token API with zero idle cost, for spiky usage and EU jurisdiction. Route B rents one single-tenant RunPod GPU pod in a region the user picks, serving the model on vLLM behind a…
allow-team
Puts a running Open WebUI or Odysseus on a shareable public URL through an ngrok tunnel, so a teammate can sign in and use the local models without installing anything. Use when the user says "share Open WebUI with my team", "share Odysseus with my team", "let my colleague use my local AI", "expose Open WebUI", "share…
gcloud-cli-health-check
Run a Google Cloud CLI (gcloud) health check — verify installation, authentication, active project, recommended region, enabled APIs (run, cloudbuild, artifactregistry, secretmanager, cloudresourcemanager, iam, plus gmail/calendar/monitoring/logging), API access token, billing, IAM bindings, service accounts, and…
dell-idrac-bmc-ops
Bring a Dell PowerEdge BMC (iDRAC) onto the network headlessly, standardize its baseline settings, stage its firmware, and drive an unattended Proxmox/Linux install through it — including generation-specific Redfish/racadm gotchas, the identity-before-power-action rule, and the phantom-drive failure mode caused by…
homelab-runbooks
Use when powering on a sleeping DR node, converging DNS records for a new ingress vhost, or bringing up OpenBao/Terrakube JWT identity — homelab operational runbooks for power management, DNS, and secrets-engine bring-up.
proxmox-cluster-ops
Operate a Proxmox VE cluster safely — read-only inspection with pvesh/pct/qm/pvecm instead of hand-editing a live guest, node-by-node package updates that respect quorum, and the shape of joining a new node to an existing cluster. Use when inspecting cluster or guest state, planning a rolling update across cluster…