Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aiappsgbb/awesome-gbbnpx agentmods add skills/aiappsgbb/awesome-gbb/azure-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/aiappsgbb/awesome-gbb/azure-sre-agent)<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/azure-sre-agent"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/azure-sre-agent/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/aiappsgbb/awesome-gbb/azure-sre-agent"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/azure-sre-agent.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 | $0.00248 | $0.03817 |
| Opus 5 | $0.00124 | $0.01909 |
| Sonnet 5 | $0.00050 | $0.00763 |
| Haiku 4.5 | $0.00025 | $0.00382 |
Grade A, and why
azure-sre-agent 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 10d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure SRE Agent — GBB Adoption Skill
Posture: upstream-first. Microsoft ships the full toolchain at
microsoft/sre-agentand the plugin marketplace atAzure/sre-agent-plugins. This skill does not rebuild Bicep modules, deploy scripts, or a custom-agent library — those are MIT-licensed and actively maintained there. We add only what GBB engagements need on top: 3 GBB-shaped recipes, 2 GBB-shaped plugins, a small cross-skill data-plane helper, and the pre-flight runbook the official docs assume you don't need.
1. When to use / when NOT
Use this skill when a customer wants Azure SRE Agent (sre.azure.com,
Microsoft.App/agents) deployed in a GBB engagement — typically because
they already run on Azure and want an always-on operator/responder agent
on top of App Insights + Log Analytics + their incident platform.
| Use this skill | Use a different skill |
|---|---|
| Deploy Azure SRE Agent in a customer sub | Deploy a Foundry hosted agent → foundry-hosted-agents |
| Wire SRE Agent to a Citadel-routed Foundry connection | Provision the Citadel hub itself → citadel-hub-deploy |
| Post a Threadlight incident into a customer's SRE Agent | Onboard a Foundry spoke to a Citadel hub → citadel-spoke-onboarding |
| Knowledge-base seed with GBB runbooks | In-process agent governance (policy-decision middleware) → foundry-agt |
| Author a GBB recipe upstream-shaped | OTel emit from a hosted agent → foundry-observability |
| Author a GBB plugin upstream-shaped | Host an MCP server on ACA → foundry-mcp-aca |
2. Use the official toolchain first
Before you write a single byte of Bicep, do this:
git clone https://github.com/microsoft/sre-agent.git
cd sre-agent/sreagent-templates
./bin/install-prerequisites.sh # az, jq, python3, pyyaml; --all adds Terraform + azd
# Generate config from a vendor-neutral recipe
./bin/new-agent.sh --recipe minimal --non-interactive \
--set agentName=my-sre-agent \
--set resourceGroup=rg-my-sre-agent \
--set location=swedencentral \
--set targetRGs=rg-my-workload \
-o my-agent/
./bin/deploy.sh my-agent/ # Bicep deploy, ~3 min
What ships with it
43 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 4.3 KB
- references/plugins/gbb-citadel/plugin.json 325 B
- references/plugins/gbb-citadel/README.md 2.0 KB
- references/plugins/gbb-citadel/skills/apim_throttle_expert/SKILL.md 2.1 KB
- references/plugins/gbb-citadel/skills/jwt_403_debug_expert/SKILL.md 2.5 KB
- references/plugins/gbb-foundry/plugin.json 324 B
- references/plugins/gbb-foundry/README.md 1.9 KB
- references/plugins/gbb-foundry/skills/byok_401_debug_expert/SKILL.md 2.9 KB
- references/plugins/gbb-foundry/skills/hosted_agent_deploy_expert/SKILL.md 2.8 KB
- references/plugins/gbb-foundry/skills/quota_throttle_expert/SKILL.md 2.5 KB
- references/recipes/citadel-routed/agent.json 2.2 KB
- references/recipes/citadel-routed/config/common-prompts/citadel-safety-rules.yaml 567 B
- references/recipes/citadel-routed/config/skills/citadel-gateway-debug.md 2.0 KB
- references/recipes/citadel-routed/config/skills/citadel-gateway-debug.yaml 381 B
- references/recipes/citadel-routed/config/subagents/apim-403-investigator.instructions.md 2.2 KB
- references/recipes/citadel-routed/config/subagents/apim-403-investigator.yaml 489 B
- references/recipes/citadel-routed/connectors.json 334 B
- references/recipes/citadel-routed/expected-config.json 579 B
- references/recipes/citadel-routed/README.md 3.3 KB
- references/recipes/citadel-routed/roles.yaml 756 B
- references/recipes/foundry-hosted-agents/agent.json 2.0 KB
- references/recipes/foundry-hosted-agents/config/automations/scheduled-tasks/daily-hosted-agent-health-check.yaml 1014 B
- references/recipes/foundry-hosted-agents/config/skills/hosted-agent-deploy-triage.md 2.3 KB
- references/recipes/foundry-hosted-agents/config/skills/hosted-agent-deploy-triage.yaml 397 B
- references/recipes/foundry-hosted-agents/config/subagents/byok-401-investigator.instructions.md 2.6 KB
- references/recipes/foundry-hosted-agents/config/subagents/byok-401-investigator.yaml 540 B
- references/recipes/foundry-hosted-agents/connectors.json 325 B
- references/recipes/foundry-hosted-agents/expected-config.json 680 B
- references/recipes/foundry-hosted-agents/README.md 3.0 KB
- references/recipes/foundry-hosted-agents/roles.yaml 627 B
- references/recipes/threadlight-pilot-handover/agent.json 2.2 KB
- references/recipes/threadlight-pilot-handover/config/automations/scheduled-tasks/daily-pipeline-health.yaml 1.3 KB
- references/recipes/threadlight-pilot-handover/config/skills/threadlight-incident-triage.md 2.6 KB
- references/recipes/threadlight-pilot-handover/config/skills/threadlight-incident-triage.yaml 406 B
- references/recipes/threadlight-pilot-handover/config/subagents/threadlight-runtime-investigator.instructions.md 2.5 KB
- references/recipes/threadlight-pilot-handover/config/subagents/threadlight-runtime-investigator.yaml 579 B
- references/recipes/threadlight-pilot-handover/connectors.json 305 B
- references/recipes/threadlight-pilot-handover/expected-config.json 692 B
- references/recipes/threadlight-pilot-handover/README.md 4.0 KB
- references/recipes/threadlight-pilot-handover/roles.yaml 868 B
- references/upstream-pin.md 12 KB
- scripts/data_plane.py 6.7 KB runs code
- scripts/preflight.sh 3.1 KB runs code
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.
- 10d ago First seen · 298 lines · 248 tokens per session scan A c51f27f02f74
azure-sre-agent is a skill published in the GitHub repository aiappsgbb/awesome-gbb (5 stars, last pushed 3d ago), licensed MIT. It adds 248 tokens to every session and 3,817 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…