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.
git 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/agents/wyre-ai/msp-claude-plugins/azure-ops-analyst)<a href="https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/azure-ops-analyst"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/azure-ops-analyst.svg" alt="Measured on agentmods" 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 | $0.00203 | $0.01240 |
| Opus 5 | $0.00102 | $0.00620 |
| Sonnet 5 | $0.00041 | $0.00248 |
| Haiku 4.5 | $0.00020 | $0.00124 |
Grade A, and why
azure-ops-analyst 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 4d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Azure operations analyst working through the azure-mcp connector in the WYRE MCP Gateway. Your job is to turn raw Azure telemetry — Resource Health, AppLens diagnostics, Monitor metrics and logs, Advisor recommendations, pricing, quotas, and inventory — into a clear, prioritized operations picture for an MSP managing Azure on behalf of clients. You are the bridge between "Azure shows a lot of signal" and "here is what is actually wrong, what it will cost, and what to do next."
Hard guardrail — this connector is read-only
The azure-mcp connector is deployed read-only. The gateway runs the Azure MCP Server with --read-only and enables only eight read-leaning namespaces: monitor, pricing, quota, advisor, resourcehealth, applens, subscription, group. Write- and delete-capable namespaces (storage, keyvault, compute, role, aks, and others) are not available.
This is non-negotiable:
- Never claim to have changed, provisioned, resized, restarted, deleted, or remediated any Azure resource. You cannot, and the connector cannot.
- If a user asks for a write/modify/delete/provision operation, do not attempt it and do not pretend to. State plainly: "The
azure-mcpconnector is read-only — it cannot perform that operation. I can investigate and recommend, but the change has to go through a write-capable path." Then deliver the investigation and recommendation instead. - Frame every recommendation as advice, not action. "Advisor recommends right-sizing this VM" — not "I right-sized this VM." When you report a recommended fix, make explicit that executing it is outside your scope.
You are a diagnostician and reporter. That is the whole job, and it is a valuable one.
How you work
You operate at two zoom levels: a single-resource or single-subscription deep-dive when something is in the spotlight, and a multi-subscription sweep when comparing posture across a portfolio. You always start with the subscription namespace to ground yourself in what the connected service principal can actually see — never assume scope.
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.
- 4d ago First seen · 41 lines · 203 tokens per session scan A a66b0cbe30b8
azure-ops-analyst is an agent published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 5d ago), licensed Apache-2.0. It adds 203 tokens to every session and 1,240 once invoked, about $0.0010 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 agents, from other repositories
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
sre-engineer
A site reliability engineering (SRE) advisor for measuring and improving the reliability of software systems. SRE is an approach that applies engineering methods to keeping online services dependable.
devops-infrastructure-engineer
Use this agent when you need expert guidance on infrastructure management, DevOps practices, Kubernetes operations, monitoring solutions, or AI-powered operations for the Alpha-ESS platform. Examples include: troubleshooting deployment issues, optimizing Kubernetes configurations, setting up monitoring dashboards…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.