agentleFS
lukemurraynzlukemurraynz/hve-agent-skills/skills/azure-sre-agent/SKILL.md

azure-sre-agent

Skill2 starsChanged 3 months agoMITView on GitHub

Design, configure, review, and operate production-grade Azure SRE Agent capabilities: response plans, scheduled tasks, HTTP triggers, custom agents, autonomous and review workflows, approval guardrails, AMBA observability, source RCA, connectors, MCP, governance hooks, WAF reviews, AI Foundry posture, Digital Native governance, postmortem generation, and KT discipline.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for new Azure projects that need Azure SRE Agent designed, reviewed, or productionized.

    line 19
  2. Distinctive:

    Stop and require human review when rollback is unclear, run mode or ownership is unknown, the design spans multi-subscription or …

    line 81
  3. Distinctive:

    Before producing output, identify the workload, owner, environment, incident source, and blast radius.

    line 85
  4. Distinctive:

    Trigger: before writing YAML, API payloads, hook settings, trigger auth guidance, AAU pricing guidance, or region-sensitive deployment …

    line 89
  5. Very specific:

    Verification methods: verify current Azure SRE Agent schema, run modes, connector behavior, pricing, and supported regions against …

    line 91
  6. Very specific:

    Forbidden shortcuts: do not guess azuresre.ai schema fields, hook shapes, token audiences, operation names, pricing tiers, region lists, or …

    line 93
  7. Very specific:

    Safe degraded output: if a field, endpoint, auth audience, or behavior cannot be verified, mark it [VERIFY], point to the source to check, …

    line 95
  8. Distinctive:

    Create specialist custom agents by concern: diagnostics, source RCA, remediation review, notification, workload specialist, and knowledge …

    line 141
  9. Very specific:

    Create response plans and HTTP triggers in Review.

    line 142
  10. Distinctive:

    Add source code and IaC context where deployment correlation matters, then add knowledge lifecycle tasks only after first useful …

    line 143
  11. Very specific:

    Test new response plans and HTTP triggers in Review long enough to capture Intent Met, false positives, approval outcomes, and AAU cost …

    line 144

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Azure SRE Agent Skill

Use this skill for new Azure projects that need Azure SRE Agent designed, reviewed, or productionized. Route broad Azure incident diagnosis to sibling troubleshooting skills unless the work is explicitly about SRE Agent capabilities, workflows, or governance.

Overview

This skill helps you design and review production-grade Azure SRE Agent capabilities: response plans, scheduled tasks, HTTP triggers, custom agents, connectors, source-aware RCA, governance hooks, and AMBA-aligned observability. It assumes greenfield or newly structured deployments, not legacy preservation.

SLI-to-incident flow: Azure SRE Agent consumes SLI breaches as incident triggers. For SLI/SLO design, Azure Monitor baselines, and target-setting, use the observability-monitoring skill; this skill owns response and remediation execution.

Use when

Request patternUse this skill?Route or output
Design a new Azure SRE Agent capability, response plan, trigger, or custom agentYesBundle selection, workflow, governance, rollout plan
Map Azure Monitor or AMBA alerts into SRE Agent workflowsYesAMBA baseline, alert routing, autonomy posture
Add source RCA, PR remediation, or GitHub and Azure DevOps integration to SRE AgentYesSource-aware investigation design
Review connector security, approval hooks, or SRE Agent RBACYesLeast-privilege and governance review
Diagnose an Azure outage with no SRE Agent in scopeNoUse ../azure-troubleshooting/SKILL.md
Design or operate Azure Monitor Health Models (state rollup, health-state alerts)NoUse ../azure-health-models/SKILL.md
General observability architecture without SRE Agent workflowsNoUse ../observability-monitoring/SKILL.md
Generic product-agnostic autonomous-agent loop outside the SRE Agent surfaceNoUse ../autonomous-agent-loops/SKILL.md

Production defaults

Decision areaDefaultAvoid
Run modeStart in ReadOnly when scope/ownership is unclear, otherwise Review; promote one workflow at a time. Both surfaces use Autonomous; the data-plane response-plan value is autonomous (automatic is rejected everywhere). Note: the platform's own default for new response plans and scheduled tasks is Autonomous — this package deliberately overrides that to Review for production hardeningDefaulting new production automation to autonomous
Access levelStart agent accessLevel at Low; raise to High only with explicit blast-radius, RBAC, and rollback decisionsProvisioning High access by default
Model tierDefault General Purpose per workflow; reserve higher tiers for deep RCA where AAU cost is acceptedA single global high-cost tier for all triggers/tasks
Alerting baselineStart from AMBA, then tune to SLOs and alert-noise evidenceCopying baseline alerts unchanged into production
Connector scopeEnable only required operations, tools, repos, and RBAC scopes; stay within the 80-tool/agent budgetCatch-all agents and broad write-capable connectors
KT depthFull SA -> PA -> DA -> PPA for P1/P2; lightweight KT for lower severity; minimum DA + PPA for write actionsForcing full KT for low-risk read-only tasks
Cost postureBudget for 4 AAUs per agent-hour fixed cost plus model-dependent active-flow AAUsTreating AAU cost as fixed only

Autonomy Progression Model

Promote workflows through levels based on demonstrated success, not configuration changes alone. Gate each transition on evaluation data, not intent.

LevelRun ModeGate CriteriaHuman Role
L0 - ManualReadOnlyInitial onboarding or untrusted scopeInvestigates, approves, actuates all actions
L1 - AssistedReadOnlyAgent provides investigation insights; human actuatesReviews agent findings, executes mitigations
L2 - ReviewReviewAgent proposes mitigations; human approves eachApproves or rejects agent-proposed actions
L3 - Autonomous (bounded)ARM Autonomous + plan autonomousSustained high success rate against Gold evaluation data for a specific, narrow workflowMonitors, handles novel situations
L4 - Autonomous (multi-step)ARM Autonomous + plan autonomousAgent handles end-to-end incident lifecycle for well-defined scenarios; adapts strategy based on outcomesArchitectural governance, safety guardrail design

Progression rules: promote one workflow at a time; L2→L3 requires demonstrated success against Gold-quality evaluation data (references/knowledge-lifecycle.md); L3→L4 requires multi-step resolution (diagnose → mitigate → verify → adapt); demote on any sustained increase in false positives or missed detections.

Autonomy safety rules (live-verified)

Each rule below was reproduced against a live deployment; full evidence, error messages, and worked examples in references/live-verified-operations.md. Read that file before promoting any workflow or writing guardrails.

  1. Plan-level review does NOT restrain an agent-level Autonomous. ARM actionConfiguration.mode is the governing control; supervised operation means ARM mode: Review, whatever plans say.
  2. Per-plan promotion works directly — an earlier "raise ARM first" reading misread an invalid-enum rejection. automatic is invalid everywhere; set agentMode: autonomous directly, and enumerate every plan's mode explicitly before changing the agent-level default.
  3. Graduated autonomy needs two agents with two identities (supervised + autonomous), never shared identities, a custom no-delete AKS role for the autonomous one, and no self-administration. Watch the two custom-role deploy-blockers (AssignableScopeMismatch, InvalidDataActionOrNotDataAction); neither fails at compile time.
  4. An agent without incidentManagementConfiguration deploys Succeeded then rejects every plan create with a bare 405; repair via redeploy, not az resource update (redacted connection string breaks the round-trip).
  5. Audit autonomous actions via the kube-audit-admin Log Analytics category, not Activity Log (data-plane writes are invisible there) and not IncidentActivitySnapshot (proves investigation, not action, and misattributes the acting identity).
  6. Read every hook's actual prompt before trusting its name — a hook named for approval shipped as a self-judged gate that approved everything plausible. Match hooks to PascalCase tool names including Terminal/RunInTerminal.
  7. Incident titles are Prometheus rule-GROUP names, so titleContainsAny routing misfires; overlapping plans silently suppress investigation (zero tool calls). One rule group per routing intent; verify outcomes via ResponsePlanId.
  8. Control stack order is hooks → tool access policies → connector Ask → run mode — and a user-defined hook returning allow overrides even a global policy deny. Use global deny policies for coarse blocks and toolGlob(argGlob) argument patterns for boundaries RBAC can't express; audit every hook-allow override (references/hooks-governance.md).

Stop conditions

Stop and require human review when rollback is unclear, run mode or ownership is unknown, the design spans multi-subscription or multi-tenant write scope without explicit isolation, or schema and auth behavior cannot be verified from current docs.

Model-output reset

Before producing output, identify the workload, owner, environment, incident source, and blast radius; prefer evidence, guardrails, and rollout steps over slogans; keep AMBA, connectors, hooks, and KT proportional to the use case; and mark freshness gaps instead of smoothing them away.

Anti-hallucination rule

Trigger: before writing YAML, API payloads, hook settings, trigger auth guidance, AAU pricing guidance, or region-sensitive deployment advice.

Verification methods: verify current Azure SRE Agent schema, run modes, connector behavior, pricing, and supported regions against references/source-map.md, Microsoft Learn, and official microsoft/sre-agent artifacts.

Forbidden shortcuts: do not guess azuresre.ai schema fields, hook shapes, token audiences, operation names, pricing tiers, region lists, or plugin catalog behavior.

Safe degraded output: if a field, endpoint, auth audience, or behavior cannot be verified, mark it [VERIFY], point to the source to check, and stop at a reviewable seam. Do not invent a fallback workflow or fake-safe production path.

Live-verified operations

Load references/live-verified-operations.md when promoting to autonomous, writing/auditing hooks, debugging engagement, verifying incident routing, auditing autonomous writes, or working with the data-plane API. It carries the verified loop shape, hook matcher mechanics, RBAC-vs-ingestion gaps, the kube-audit-admin audit path, and the data-plane path table (audience https://azuresre.dev; PUT creates / POST updates).

Bundle Routing

Open only the bundle and reference files needed for the current task. When populating @@PLACEHOLDER@@ values in bundle templates, use parameters.example.yaml as the substitution checklist.

User intentLoad
Minimal production baselinebundles/base-core/, references/production-blueprints.md
AMBA, Azure Monitor, alert baselines, alert tuningbundles/observability-amba/, references/observability-amba.md
HTTP/event-driven invocation from CI/CD or alertsbundles/http-triggers-production/, references/http-triggers-production.md
HTTP trigger auth bridge via Functions, Logic Apps, or APIMbundles/http-trigger-auth-bridges/, references/http-trigger-auth-bridges.md
Source-code RCA, deployment regression, PR remediationbundles/source-rca-remediation/, references/source-rca-remediation.md
Knowledge, memory, runbook lifecyclebundles/knowledge-lifecycle/, references/knowledge-lifecycle.md
Identity, RBAC, OBO fallback, private networkbundles/security-identity/, references/security-identity-rbac.md
Value tracking, autonomy promotion, AAU governancebundles/operational-metrics/, references/value-promotion-scorecard.md
Common Azure workload response-plan seedsbundles/azure-workload-production/, references/workload-bundle-seeding.md
AKS incidents or health checksbundles/aks-production/, references/aks-containerapps-production.md
Container Apps incidents or revisionsbundles/containerapps-production/, references/aks-containerapps-production.md
Drasi on AKSbundles/drasi-aks-production/, references/drasi-aks-playbook.md
Run mode, access level, model tier, upgrade channel, tool budgetreferences/run-posture-and-operational-levers.md
Live-verified run modes, hooks, routing, data-plane APIreferences/live-verified-operations.md
KT, approval, audit, write-action governancebundles/governance-kt/, references/kt-methodology.md, references/hooks-governance.md
Observability or incident connectorsbundles/connectors-observability/, references/connectors-and-mcp.md, references/connector-token-security.md
Teams/GitHub handoffbundles/connectors-collab-handoff/, references/connectors-and-mcp.md
Bundle maintenancebundles/catalog.yaml, bundles/README.md, references/bundles-operations.md, references/capability-matrix.md
Audit diagnostics or 2am investigationreferences/audit-diagnostics-2am.md
Source verificationreferences/source-map.md
Output shaping/examplesreferences/output-examples.md
Project/resource isolation and placementreferences/project-boundary-resource-placement.md
First deployment (Quickstart)references/quickstart-first-deployment.md
IaC deployment, recipes, backends, day-2 export/clone/diff/verifyreferences/production-patterns-guide.md#multi-backend-deployment-patterns
HTTP trigger auth troubleshooting (token audience conflict)references/http-triggers-production.md#authentication

Workflow

For new production projects, build capabilities in this order:

  1. Establish owner, region, incident platform, identity model, baseline connectors, AAU limit, and governance hooks.
  2. Verify the current deployment region. Supported regions last verified 2026-08-25 (18): Australia East, Canada Central, Central US, East Asia, East US 2, France Central, Italy North, Japan East, Korea Central, North Central US, South Africa North, Southeast Asia, Spain Central, Sweden Central, UK South, West Central US, West US 2, West US 3. An agent's region is fixed at creation and cannot be changed; it can still manage resources elsewhere where its identity has permissions. Confirm subscription-specific availability before cutover.
  3. Deploy AMBA-aligned monitoring or map existing alerts to AMBA categories before creating response plans.
  4. Classify alerts as investigate, notify, digest, tune, or candidate-for-autonomy before routing them to agents.
  5. Create specialist custom agents by concern: diagnostics, source RCA, remediation review, notification, workload specialist, and knowledge capture. Six generic subagents ship built in (Explore, Plan, CodeReview, Bash, Verification, GeneralPurpose) alongside your custom ones.
  6. Create response plans and HTTP triggers in Review; apply cooldown and noise controls before any high-volume trigger goes live.
  7. Add source code and IaC context where deployment correlation matters, then add knowledge lifecycle tasks only after first useful investigations.
  8. Test new response plans and HTTP triggers in Review long enough to capture Intent Met, false positives, approval outcomes, and AAU cost before autonomy promotion.
  9. Promote only narrow, repeatedly validated, low-blast-radius workflows to Autonomous.

Recipe Design Framework

Production SRE Agent capabilities are shaped by five intersecting dimensions:

DimensionOptions / ExamplesDecision driver
PlatformAzMonitor, PagerDuty, Dynatrace, ServiceNow, GitHub Actions, Azure DevOps, GrafanaWhere incidents originate; native webhook support
ConnectorsAppInsights, LAW (Log Analytics), Kusto, MCP integrations, GitHub, Azure DevOps APIsWhich observability/CI/CD systems feed investigation
SkillsInvestigation playbooks by workload: VM, CosmosDB, AKS, Container Apps, HTTP errorsThe target system or error class you need to automate
KnowledgeRunbooks, incident templates, RCA patterns, troubleshooting guides, approval checklistsContext and procedures the agent needs to reach conclusion
ResponseSeverity-based routing, agentMode (Autonomous/Review), customInstructions, max attemptsHow the agent behaves and when it escalates or acts

Design in this order: platform → connectors → skills → knowledge → response mode. Test each layer independently before combining. Name recipes <platform>-<key-connectors>[-workload-variant] (good: pagerduty-law-vmcosmos; avoid: agent-automation).

See Production Patterns Guide for recipe patterns, multi-backend deployment, connector auth orchestration, export→clone→verify workflows, and post-deployment verification checklists.

Resource Boundary Defaults

Last reviewed: 2026-08-25. The Microsoft.App/agents resource has no diagnostic-settings or private-endpoint support; audit via the agent's own Application Insights customEvents, and reach private workloads via VNet integration (preview, vnetConfiguration.subnetResourceId); see references/security-identity-rbac.md and references/run-posture-and-operational-levers.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.