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 cost-and-capacitygit 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/cost-and-capacity)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/cost-and-capacity"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/cost-and-capacity/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/cost-and-capacity"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/cost-and-capacity.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 | $0.00066 | $0.01236 |
| Opus 5.5 | $0.00026 | $0.00494 |
| Sonnet 5.5 | $0.00013 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
azure-mcp-cost-and-capacity 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 2mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Cost & Capacity
This skill covers the cost, capacity, and inventory side of the azure-mcp connector: the pricing, quota, subscription, and group namespaces. All four are read-only — they answer "what would this cost", "do we have headroom", and "what exists", never "provision this".
Tool names follow the Azure MCP Server's namespace convention (azmcp / azure_mcp prefixes, grouped under pricing, quota, subscription, group). Invoke them by capability.
Anti-triggers
- What the customer was actually billed —
pricingreturns public retail rates, never invoiced consumption. CSP invoices and margin sit inpax8orsherweb. - Where the money is being wasted — cost optimisation findings
come from Azure Advisor; use
azure-mcp-observability. - M365 seat counts and licence costs — use
cipp-licenses.
Namespace surface
subscription — subscription inventory
Lists the Azure subscriptions the connected service principal can see, with their IDs, display names, and state (Enabled, Disabled, Warned). This is almost always the first call in any workflow — nearly every other namespace needs a subscription ID for scope.
group — resource-group inventory
Lists and inspects resource groups within a subscription: name, location, tags, and provisioning state. Use it to map the shape of an environment, find resources by tag, or pick the right scope for a pricing or quota question.
pricing — Azure retail pricing
Looks up Azure retail prices from the public Azure Retail Prices API — meter rates by service, SKU, region, and currency. This gives list pricing, not the customer's negotiated or EA/CSP pricing, and not actual billed consumption. Treat its output as an estimate baseline.
quota — quota & usage limits
Reports subscription quotas and current usage for a resource provider and region — e.g. vCPU quota for a VM family, public IP count, network interface count. Each entry shows the limit, current usage, and therefore the remaining headroom.
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.
- 2mo ago First seen · 89 lines · 66 tokens per session scan A dff0b30ed7a7
azure-mcp-cost-and-capacity is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (52 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,236 once invoked, about $0.0003 per session on Opus 5.5. 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.
azure-mcp-cost-and-capacity compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| azure-mcp-cost-and-capacityWYRE-AI/msp-claude-plugins | Skill | 52 | today | Apache-2.0 | A | 66 | Claude Code |
| aws-cost-operationssickn33/agentic-awesome-skills | Skill | 49k | today | MIT | A | 44 | Claude Code |
| azure-costmicrosoft/skills | Skill | 3.2k | today | MIT | A | 94 | Claude Code |
| cost-estimationmicrosoft/skills | Skill | 3.2k | today | MIT | A | 97 | Claude Code |
| finance-financial-statementsmodu-ai/moai-cowork | Skill | 315 | 1mo ago | Apache-2.0 | A | 86 | Claude Code |
| pwn-aws-budgets0dayInc/pwn | Skill | 86 | today | MIT | A | 21 | Claude Code |
| alibabacloud-opc-advisoraliyun/alibabacloud-agent-toolkit | Skill | 29 | today | Apache-2.0 | A | 305 | Claude Code |