microsoft/sre-agent is the community repository for Azure SRE Agent, an AI assistant for diagnosing and resolving production problems and reducing routine operations work. It is for teams working on service reliability and includes documentation, discussions, videos, and hands-on labs for using the product. The catalogue skills relate to the agent's official plugins and resources.
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 microsoft/sre-agent --skill onboarding-labgit clone --depth 1 https://github.com/microsoft/sre-agentWrote 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/microsoft/sre-agent/onboarding-lab)<a href="https://agentmods.dev/skills/microsoft/sre-agent/onboarding-lab"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/onboarding-lab/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/microsoft/sre-agent/onboarding-lab"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/onboarding-lab.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 | $0.00047 | $0.00760 |
| Opus 5.5 | $0.00019 | $0.00304 |
| Sonnet 5.5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
onboarding-lab 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help with the onboarding lab
Read the lab's README.md from labs/onboardinglab. Work from that directory
so relative paths and its local instructions resolve correctly.
Find the learner's starting point
- For an assigned agent, ask for its portal link or exact resource ID. Inspect only that environment. Do not deploy or overwrite it.
- For an existing local setup, read
azd env listand the selected environment's values fromticketingapp-source. Check the subscription and resource group before executing any stage. - For a new environment, explain which resources are billable, confirm the target and responsible owner, and run the documented preflight before deployment.
- If access, quota or prerequisites are missing, name the failed check and its remedy. Offer the facilitator's assigned environment when one is available. Never invent an assigned environment or grant yourself access.
Prepare and resume
Use the documented setup scripts and azd lifecycle. Inspect their help and parameters before calling them. Do not turn README examples into a separate collection of unverified REST writes.
Run prerequisite checks before installing anything. Obtain approval for missing tools, Azure resources and role assignments. Reuse existing sign-ins; let the learner complete an expired sign-in through the provider's normal UI.
The standard lab includes GitHub and Outlook. Obtain the approved repository
and email recipients during preparation. Let the learner complete OAuth in the
connection UI, then run setup's Connect stage. Do not ask for credentials in
chat or treat consent as permission to create an issue or send email.
Use -CoreOnly only when explicitly choosing the reduced fallback.
After a failure, inspect the named deployment and the stage's read-back output. Reconcile an unknown write result before retrying. Preserve the existing app, agent, skills, knowledge and existing connections. Do not use a force flag to silence unexpected drift.
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.
- 1mo ago First seen · 76 lines · 47 tokens per session scan A 71bf384c906c
onboarding-lab is a skill published in the GitHub repository microsoft/sre-agent (179 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 760 once invoked, about $0.0002 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 2026-09-19.
Other skills, from other repositories
cloud-build-basics
Teaches the fundamentals of Cloud Build on Google Cloud. Covers core concepts, API enablement, console navigation to the Build History page, and the end-to-end workflow for creating and manually running a basic build trigger. Do not use for managing private pools or complex pipeline architectures.
mirrord-quickstart
Guide users from zero to their first working mirrord session — check system requirements, install mirrord via CLI, VS Code, or IntelliJ, run a first session against a Kubernetes target, and verify the connection. Use when a user is new to mirrord, wants to install it, needs help running their first session, or wants…
hr-devops
Help HR managers, recruiters, and talent acquisition teams understand DevOps, Platform Engineering, Site Reliability Engineering (SRE), cloud infrastructure, CI/CD, and modern software delivery workflows. Use when asked to explain DevOps, screen DevOps candidates, understand CI/CD, compare DevOps and SRE, evaluate…
azure-lab-services
Expert knowledge for Azure Lab Services development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring lab plans, VM templates/schedules, VNet-integrated labs…
wa-builder
"Learn then Build" — help developers understand AWS Well-Architected best practices for their specific workload, then produce actionable visual artifacts (architecture diagrams with WA annotations, decision trees, improvement roadmaps) they can commit and use. Adapts explanations for beginners and generates artifacts…
bdbsaastraining
Use when onboarding or training staff on the BDB SaaS Host Engine. Guides trainees via interactive workloads (WordPress, mail, agents) through SSH 2FA, Incus, and FastMCP guardrails, culminating in a PDF certificate.