# MCP and evidence path

Use this reference when deciding how to ground `azure-subscription-resource-organization` guidance.

## Evidence order

1. Microsoft Learn documentation through the user's configured documentation MCP for documented Azure behavior.
2. Sampled read-only Azure evidence when the user has configured it and current-state confirmation is necessary.
3. Sanitized user-provided evidence when no read-only evidence path is available.
4. Clearly labeled inference when evidence is incomplete.

## Boundaries

- Documentation evidence does not prove the user's tenant, subscription, RBAC, quotas, deployed resources, billing state, security posture, reliability state, or production readiness.
- Sampled read-only evidence proves only the sampled configured environment and time window.
- User-provided evidence can be incomplete or stale; preserve uncertainty.
- Never ask for credentials, tokens, secrets, tenant IDs, subscription IDs, resource IDs, customer data, private keys, or raw incident payloads.

## Required phrasing

Use generic phrasing such as "Microsoft Learn documentation through the user's configured documentation MCP". Do not expose internal tool names, profile names, environment names, or local identifiers in committed docs.

# Official sources

Use this reference when grounding current Azure behavior for `azure-subscription-resource-organization`.

## Microsoft Learn sources

- https://learn.microsoft.com/azure/cloud-adoption-framework/ready/landing-zone/design-area/resource-org
- https://learn.microsoft.com/azure/cloud-adoption-framework/ready/landing-zone/design-area/resource-org-management-groups
- https://learn.microsoft.com/azure/cloud-adoption-framework/ready/landing-zone/design-area/resource-org-subscriptions
- https://learn.microsoft.com/azure/cloud-adoption-framework/ready/azure-setup-guide/organize-resources
- https://learn.microsoft.com/azure/cloud-adoption-framework/ready/landing-zone/design-area/management-application-environments
- https://learn.microsoft.com/azure/cloud-adoption-framework/ready/landing-zone/design-area/governance
- https://learn.microsoft.com/training/modules/design-governance/
- https://learn.microsoft.com/azure/governance/management-groups/overview
- https://learn.microsoft.com/azure/cloud-adoption-framework/ready/azure-best-practices/resource-tagging
- https://learn.microsoft.com/azure/azure-resource-manager/management/tag-policies

## Current documentation refresh (2026-06-05)

- Microsoft Learn documentation through the user's configured documentation MCP is the primary source for documented Azure behavior.
- Documentation evidence is not live customer-state evidence. It does not prove the user's tenant, subscription, RBAC, quotas, deployed resources, billing state, security posture, or production readiness.
- Use sampled read-only Azure evidence only when the user has configured it and the task requires current-state confirmation. Label it as sampled evidence, not broad proof.

## Grounding rule

Docs explain service behavior. Current-state claims require sampled read-only evidence or sanitized user-provided evidence. If current state was not queried or shown, say so.

# Safety checklist

Use before recommending production Azure changes, access grants, security remediation, hierarchy moves, cost actions, reliability changes, or readiness conclusions for `azure-subscription-resource-organization`.

## Non-negotiables

- Do not ask for or print credentials, client secrets, certificates, private keys, access tokens, tenant IDs, subscription IDs, resource IDs, customer data, raw incident payloads, or environment-specific identifiers.
- Prefer Microsoft Learn documentation through the user's configured documentation MCP for documented Azure behavior.
- Use sampled read-only Azure evidence only for current-state claims and label it as sampled evidence.
- Require explicit approval before recommending live mutation, broad access, destructive remediation, billing changes, commitment purchases, hierarchy moves, failover, failback, or alert suppression.
- Keep recommendations least-privilege, reversible where possible, and scoped to the named resource or workload.
- Separate documentation-based claims, sampled evidence, user-provided evidence, and inference.

## Component risks

- **Identity and roles:** broad privileged roles, direct user grants, wildcard custom roles, missing PIM/time-bound controls, inherited scope surprises.
- **Security posture:** stored secrets, public exposure, missing managed identities, weak Key Vault boundaries, no diagnostic coverage, untracked policy exemptions.
- **Resource organization:** flat hierarchy drift, fake isolation via resource groups, subscription sprawl, weak ownership, policy inheritance surprises.
- **Cost:** optimizing recommendations without workload context, deleting resources without owner confirmation, buying commitments before rightsizing, ignoring licensing and reliability cost tradeoffs.
- **Reliability:** vague SLOs, untested recovery, overengineered topology, missing health model, no dependency mapping, unvalidated chaos or failover assumptions.

## Evidence labels

Use `documentation-based`, `sampled read-only evidence`, `repo evidence`, `user-provided evidence`, or `inference`. Documentation alone never proves the user's live Azure environment.

# Azure Subscription Resource Organization Operations

> Version note: Azure service behavior and tooling change over time. Verify exact command syntax, permissions, and feature availability against Microsoft Learn documentation through the user's configured documentation MCP before production use. Do not paste secrets or sensitive identifiers into commands, files, or chat.

Use this reference for current, source-grounded service behavior and the hard review gates that the lean `SKILL.md` intentionally does not carry.

## What people get wrong

- Using resource groups as the main isolation boundary for production environments.
- Building a flat subscription estate then hoping tags fix governance later.
- Moving subscriptions without understanding inherited policy and RBAC impact.
- Mixing platform shared services and workload resources without owner boundaries.
- Ignoring quotas, regions, naming, tagging, and lifecycle when designing hierarchy.

## Officially grounded service shape

- Microsoft Learn evidence says Azure resources can be organized at management group, subscription, resource group, and resource levels.
- Resource organization decisions are foundational for naming, tagging, subscription design, and management group design.
- Management groups manage policies, access, and compliance across subscriptions at scale; subscriptions act as policy and management boundaries and scale units.
- Landing-zone guidance separates platform/management deployments from workload or application resources and recommends planning for scale, multiple regions, governance, and ownership.

Documentation evidence proves documented Azure service behavior. It does not prove the user's tenant, subscription, RBAC, quotas, deployed resources, billing state, security posture, or production readiness.

## Non-negotiable design rules

- Choose hierarchy from governance, ownership, compliance, network, cost, and scale requirements, not aesthetics.
- Use subscriptions as isolation, policy, management, and scale boundaries where environment or workload separation is needed.
- Use resource groups for shared lifecycle, not as a substitute for subscription isolation.
- Document policy/RBAC inheritance and exemption strategy before moving subscriptions.
- Require naming, tagging, budget, and owner model for every proposed boundary.

## Minimal safe implementation flow

- Scope organization goal, current hierarchy, workloads, environments, regions, owners, compliance, and platform services.
- Map management groups, subscriptions, resource groups, policies, RBAC, budgets, tags, and quotas.
- Identify weak boundaries, inheritance surprises, and migration risks.
- Propose minimal target-state changes with staged moves and rollback/communication plan.
- Return target hierarchy, rationale, blockers, verification checks, and governance debt.

## High-risk assumptions to kill

- Tags can replace hierarchy; tags help reporting and policy targeting, but they are not first-class isolation boundaries.
- Resource groups can isolate production from nonproduction; they share subscription-level policy, quota, billing, and many blast-radius concerns.
- A flat hierarchy is simpler; it usually defers governance debt until policy, RBAC, and compliance inheritance become painful.
- Subscription moves are administrative cleanup; they can change inherited policy, RBAC, budgets, compliance reporting, and operational ownership.
- A landing-zone diagram proves suitability; current quotas, regions, ownership, and workload lifecycle still need evidence.

## Safe command/code verification targets

- Inventory management groups, subscriptions, resource groups, inherited policies, role assignments, tags, budgets, and quotas with read-only queries.
- Compare proposed boundaries to workload lifecycle, owner, environment, compliance, network, and cost-accountability requirements.
- Check management-group depth, parentage, and subscription placement constraints before proposing hierarchy moves.
- Validate naming and tagging standards against Microsoft Learn guidance and existing policy enforcement.
- Label hierarchy inventory as sampled current-state evidence; documentation alone does not prove the estate is organized correctly.

## Safe verification targets

- Management group purpose and inherited controls are documented.
- Subscription placement matches workload/environment/platform boundary.
- Resource groups contain resources with shared lifecycle and ownership.
- Policy, RBAC, budget, tag, naming, and quota implications are known.
- Subscription moves or hierarchy changes have validation and rollback/communication plan.

## When to push back

- The user wants one subscription or flat hierarchy for convenience.
- A resource group is used to isolate production from non-production without policy/RBAC proof.
- The proposed move ignores inherited deny policies or RBAC.
- Ownership and cost accountability are undefined.

# Workflow and output contract

Use this reference for full execution of `azure-subscription-resource-organization`.

## Workflow

1. **Classify the request**
   - Identify service/domain, resource scope, environment, production impact, and whether mutation or billing impact is requested.
   - Identify whether the task needs documentation-only guidance, sampled read-only current-state evidence, or sanitized user evidence.

2. **Ground in current sources**
   - Prefer Microsoft Learn documentation through the user's configured documentation MCP.
   - Read the component operations guide before issuing design, safety, or readiness conclusions.
   - Treat current-state claims as unproven unless supported by sampled read-only evidence or sanitized user-provided evidence.

3. **Stress-test the plan**
   - Kill broad permissions, vague ownership, missing rollback, missing validation, and unsupported production-readiness claims.
   - Separate facts from inference.
   - State blockers before recommendations.

4. **Recommend minimal safe action**
   - Prefer read-only inspection, preview, what-if, diagnostic query, cost forecast, or staged rollout before mutation.
   - Require explicit approval for live, destructive, access, reliability, hierarchy, or billing-impacting actions.
   - Keep the recommendation scoped and reversible where possible.

5. **Validate and hand off**
   - Name verification targets and evidence gaps.
   - Provide safe next actions and escalation criteria.
   - Do not claim tenant, subscription, resource, billing, quota, or posture state that was not observed.

## Output contract

Return:

1. Scope and target
2. Evidence level: documentation-based, sampled read-only evidence, user-provided evidence, repo evidence, or inference
3. Key findings and risks
4. Blockers or missing evidence
5. Minimal safe next actions
6. Verification targets
7. Rollback, cleanup, expiry, or reversal path where applicable