@raishin/vanguard-frontier-agentic 2.8.0 → 2.10.0

package/skills/azure/azure-live-cost-budget-action-guard/SKILL.md

@@ -4,8 +4,8 @@ description: Gate Azure budget action changes and GPU/HPC SKU provisioning again
 allowed-tools: Read Grep Glob WebFetch
 metadata:
   author: "github: Raishin"
-  version: "0.1.0"
-  updated: "2026-05-05"
+  version: 0.1.7
+  updated: "2026-06-05"
   category: finops
 ---
 
@@ -25,7 +25,7 @@ Use this skill when:
 
 ## Lean operating rules
 
-- Prefer Azure CLI (`az`) official documentation when available; fall back to Microsoft Learn docs and sanitized user evidence.
+- Prefer Microsoft Learn documentation through the user's configured documentation MCP; use sampled read-only Azure evidence when available, then sanitized user evidence.
 - Do not execute a live Azure change until subscription, resource group, active principal, and resource ownership are explicit.
 - Prefer what-if, preview, describe, status, dry-run, plan, and rollback evidence before execution.
 - If the request skips preview or rollback design, push back.
@@ -36,9 +36,13 @@ Use this skill when:
 
 Load these only when needed:
 
+- [Azure Cost Budget and Quota Operations](references/budget-quota-operations.md) — use for current service behavior, common failure modes, hard design rules, verification targets, and push-back conditions.
 - [Preflight commands](references/preflight-commands.md) — CLI commands to run before any mutation.
 - [Rollback playbook](references/rollback-playbook.md) — concrete rollback steps for this service.
 - [Permission model](references/permission-model.md) — RBAC role definitions and PIM guidance.
+- [MCP and evidence path](references/mcp-and-evidence.md) — use when choosing documentation-based evidence, sampled read-only evidence, or sanitized user evidence.
+- [Safety checklist](references/safety-checklist.md) — use for evidence labels, budget thresholds, action groups, data latency, quota/spend approval, and runaway-cost rollback limits.
+- [Workflow and output contract](references/workflow-and-output.md) — execution flow and final response contract.
 - [Official sources](references/official-sources.md) — authoritative Azure documentation links.
 
 ## Response minimum

package/skills/azure/azure-live-cost-budget-action-guard/metadata.json

@@ -11,17 +11,19 @@
     "kiro",
     "other"
   ],
-  "summary": "Gate Azure budget action changes and GPU/HPC SKU provisioning against approved spend limits, with quota audits and emergency spend-stop playbooks.",
+  "summary": "Gate Azure budget action changes, cost-alert automation, and quota-sensitive GPU/HPC provisioning against approved spend limits, cost data latency, action-group behavior, and emergency spend-stop playbooks.",
   "source_type": "original",
   "official_docs": [
-    "https://learn.microsoft.com/en-us/azure/cost-management-billing/costs/tutorial-acm-create-budgets",
-    "https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/azure-subscription-service-limits",
-    "https://learn.microsoft.com/en-us/azure/quotas/quickstart-increase-quota-portal",
-    "https://learn.microsoft.com/en-us/azure/cost-management-billing/finops/overview-finops"
+    "https://learn.microsoft.com/azure/cost-management-billing/costs/tutorial-acm-create-budgets",
+    "https://learn.microsoft.com/azure/cost-management-billing/costs/cost-mgt-alerts-monitor-usage-spending",
+    "https://learn.microsoft.com/azure/cost-management-billing/costs/cost-mgt-best-practices",
+    "https://learn.microsoft.com/cloud-computing/finops/framework/quantify/budgeting",
+    "https://learn.microsoft.com/azure/quotas/quickstart-increase-quota-portal",
+    "https://learn.microsoft.com/azure/azure-resource-manager/management/azure-subscription-service-limits"
   ],
-  "security_notes": "GPU/HPC SKUs (NDv5, H100, A100) can generate $50K+ daily costs. Never approve quota increases or budget threshold raises without explicit spend-approval sign-off from a financial authority.",
-  "last_verified": "2026-04-30",
+  "security_notes": "Never approve quota increases, budget threshold raises, automated cost actions, or high-cost SKU provisioning without explicit financial owner approval, cost data latency caveat, rollback or stop action, and scope confirmation.",
+  "last_verified": "2026-06-05",
   "path": "skills/azure/azure-live-cost-budget-action-guard",
   "author": "github: Raishin",
-  "version": "0.1.0"
+  "version": "0.1.7"
 }

package/skills/azure/azure-live-cost-budget-action-guard/references/budget-quota-operations.md

@@ -0,0 +1,68 @@
+# Azure Cost Budget and Quota Operations
+
+Use this reference for current, source-grounded service behavior and the hard live-operation gates that the lean `SKILL.md` intentionally does not carry.
+
+## What people get wrong
+
+- Assuming a budget alert stops Azure spend.
+- Approving GPU/HPC quota because current spend is low, while ignoring delayed cost data.
+- Creating action groups with no owner or runbook.
+- Raising budget thresholds without financial authority and expiry.
+- Using quota increase as capacity planning rather than explicit spend-risk acceptance.
+
+## Officially grounded service shape
+
+Microsoft Learn evidence says Cost Management budgets monitor spending and trigger notifications or action groups, but budget alerts do not stop resources or consumption. Cost and usage data is typically delayed, and budgets are evaluated on a schedule. Budgeting guidance recommends alerts, anomaly detection, stakeholder ownership, and automation only with clear accountable response paths.
+
+- Budgets can be scoped and filtered, and can alert on actual or forecast cost.
+- Budget alerts notify stakeholders and can integrate action groups at supported scopes.
+- Cost data is not real time; budget evaluations lag consumption.
+- Quota controls capacity but is not a budget by itself.
+- Emergency spend-stop actions can be disruptive and need owner approval and rollback criteria.
+
+## Non-negotiable design rules
+
+- Confirm billing/subscription/resource-group scope and financial owner before changes.
+- State that budgets do not stop consumption unless paired with separate approved automation.
+- Review actual, forecast, data freshness, threshold, recipients, action groups, and anomaly coverage.
+- Treat GPU/HPC quota and high-cost scale-up as high-risk financial mutations.
+- Prefer lower-risk alerts and temporary quotas before permanent threshold increases.
+
+## Minimal safe implementation flow
+
+- Scope cost owner, subscription/resource group, workload, SKU, quota, and budget action.
+- Collect current budget definitions, alert thresholds, action groups, current/forecast costs, data freshness, and quota state.
+- Classify proposed change as alert-only, automation, quota increase, deallocation, or spend-stop.
+- Gate mutation on explicit financial approval and rollback/restore plan.
+- Verify alert/action configuration and document residual spend risk.
+
+## High-risk assumptions to kill
+
+- A budget alert is not a spending stop. Microsoft Learn states resources are not affected and consumption is not stopped when thresholds are exceeded.
+- Cost evidence is delayed; budget decisions based on current totals can be wrong because cost and usage data is typically available hours later and evaluated on a schedule.
+- Action groups can trigger automation, but automation without an owner, runbook, and rollback path is an outage mechanism, not FinOps control.
+- Quota increases authorize capacity to spend faster; they are financial-risk approvals even when no resource is created immediately.
+- Forecast alerts are predictions, not guarantees; they must be labeled separately from actual-cost evidence.
+
+## Safe command/code verification targets
+
+- Verify budget scope, filters, reset period, amount, expiration, actual thresholds, forecast thresholds, recipients, and action groups.
+- Confirm cost-data freshness and label actual versus forecast evidence in the final verdict.
+- Inspect action-group receivers and automation targets without exposing secrets or customer data.
+- Require business owner, duration, and spend ceiling for high-cost quota or budget-threshold increases.
+- Verify post-change budget/action configuration and document that residual consumption can continue after alerting.
+
+## Safe verification targets
+
+- Budget thresholds and recipients match accountable stakeholders.
+- Action group behavior and automation runbooks are tested and reversible where possible.
+- Cost data freshness and forecast uncertainty are explicitly stated.
+- Quota increase request has business justification, expiry/review, and spend ceiling.
+- Emergency deallocation or quota reduction has owner approval and service-impact assessment.
+
+## When to push back
+
+- The user treats budget alerting as a hard spending stop.
+- Financial approval is missing or vague.
+- High-cost quota request lacks workload, duration, and maximum-spend boundary.
+- Automation could deallocate production without an incident commander and rollback plan.

package/skills/azure/azure-live-cost-budget-action-guard/references/mcp-and-evidence.md

@@ -0,0 +1,26 @@
+# Documentation and Evidence Path
+
+## Preferred evidence order
+
+1. Microsoft Learn documentation through the user's configured documentation MCP for documented Azure behavior.
+2. Sampled read-only Azure evidence, when safely available, for current configured-environment observations.
+3. Sanitized user-provided evidence.
+4. Clearly labeled inference.
+
+## What each evidence type can prove
+
+- Microsoft Learn documentation can prove documented service behavior, supported concepts, limitations, and recommended patterns.
+- Sampled read-only evidence can prove the sampled configured state at the time observed.
+- Sanitized user evidence can prove only what the snippet shows.
+- None of these alone prove broad regional availability, future success, full account posture, or production readiness.
+
+## Safe usage pattern
+
+- State whether each claim is documentation-based, sampled-current-state, user-provided, or inference.
+- Use read-only queries before recommending changes.
+- Do not include sensitive internal identifiers, tenant identifiers, subscription identifiers, or secrets in committed docs or final findings.
+- If no sampled evidence is available, say the review is documentation-based and list the exact evidence still needed.
+
+## Live-operation rule
+
+For live operations, documentation is never enough. Require target confirmation, current-state evidence, explicit approval, rollback constraints, and post-action verification.

package/skills/azure/azure-live-cost-budget-action-guard/references/official-sources.md

@@ -1,17 +1,27 @@
-# Official Sources: Azure Live Cost Budget Action Guard
+# Official Sources
 
-## Azure Cost Management budgets
+Use these sources to ground the skill. Microsoft Learn documentation proves documented Azure behavior; it does not prove the user's tenant, subscription, RBAC, quota, deployed resources, current cost, vault state, app health, or production readiness.
 
-- https://learn.microsoft.com/en-us/azure/cost-management-billing/costs/tutorial-acm-create-budgets
-- https://learn.microsoft.com/en-us/azure/cost-management-billing/costs/manage-automation
-- https://learn.microsoft.com/en-us/azure/cost-management-billing/costs/cost-analysis-common-uses
+## Primary Microsoft Learn sources
 
-## Azure Quotas and limits
+- https://learn.microsoft.com/azure/cost-management-billing/costs/tutorial-acm-create-budgets
+- https://learn.microsoft.com/azure/cost-management-billing/costs/cost-mgt-alerts-monitor-usage-spending
+- https://learn.microsoft.com/azure/cost-management-billing/costs/cost-mgt-best-practices
+- https://learn.microsoft.com/cloud-computing/finops/framework/quantify/budgeting
+- https://learn.microsoft.com/azure/quotas/quickstart-increase-quota-portal
+- https://learn.microsoft.com/azure/azure-resource-manager/management/azure-subscription-service-limits
 
-- https://learn.microsoft.com/en-us/azure/quotas/quotas-overview
-- https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/azure-subscription-service-limits
+## Grounding notes
 
-## Source-grounding rule
+- Documentation-based claim: Microsoft Learn evidence says Cost Management budgets monitor spending and trigger notifications or action groups, but budget alerts do not stop resources or consumption. Cost and usage data is typically delayed, and budgets are evaluated on a schedule. Budgeting guidance recommends alerts, anomaly detection, stakeholder ownership, and automation only with clear accountable response paths.
+- Current-state claim: requires sampled read-only Azure evidence or sanitized user-provided evidence.
+- Live-operation claim: requires target, principal, approval, preflight evidence, rollback constraints, and post-action verification.
+- Inference: allowed only when labeled and tied to observed fields or documented behavior.
+- Do not include sensitive internal identifiers or secret material in findings.
 
-Use official Microsoft Learn documentation as the source of truth.
-Budget and quota behavior changes with service versions — verify current API behavior against docs.
+## Source use rules
+
+- Prefer Microsoft Learn documentation through the user's configured documentation MCP for current Azure service behavior.
+- Use sampled read-only Azure evidence only to validate current configured-environment observations.
+- If documentation and sampled evidence appear to conflict, report both and stop short of a production-ready verdict.
+- Re-check official sources before changing high-risk guidance, because cloud behavior and feature availability can change.

package/skills/azure/azure-live-cost-budget-action-guard/references/permission-model.md

@@ -26,7 +26,7 @@
     "Microsoft.CostManagement/budgets/delete"
   ],
   "AssignableScopes": [
-    "/subscriptions/<SUBSCRIPTION_ID>"
+    "$APPROVED_AZURE_SCOPE"
   ]
 }
 ```
@@ -64,3 +64,5 @@ Deny GPU VM SKU provisioning without an approved budget tag:
 - `Cost Management Contributor` at management-group scope
 - `Billing Account Contributor`
 - `Microsoft.Compute/virtualMachines/write` to this role
+
+Use exact resource scopes from approved change records; do not paste raw subscription identifiers into chat.

package/skills/azure/azure-live-cost-budget-action-guard/references/preflight-commands.md

@@ -29,7 +29,7 @@ az costmanagement query \
   --type ActualCost \
   --dataset-aggregation '{"totalCost":{"name":"PreTaxCost","function":"Sum"}}' \
   --timeframe MonthToDate \
-  --scope "/subscriptions/<SUBSCRIPTION_ID>"
+  --scope "$APPROVED_AZURE_SCOPE"
 ```
 
 ## 5. Check compute quota usage before action

package/skills/azure/azure-live-cost-budget-action-guard/references/rollback-playbook.md

@@ -1,21 +1,23 @@
 # Rollback Playbook: Azure Live Cost Budget Action Guard
 
-## Revert a budget modification
+## Evidence-variable convention
+
+Shell variables in examples are local operator placeholders from an approved change record or already configured shell context. Do not commit real values, and redact them from shared evidence unless disclosure is explicitly approved.
+
+## Budget update rollback
 
 ```bash
 # Inspect current state before revert
 az consumption budget show -n <BUDGET_NAME>
 
-# Delete and recreate with original values
-az consumption budget delete -n <BUDGET_NAME>
-
+# Re-apply the original budget values without deleting the budget when possible
 az consumption budget create \
   -n <BUDGET_NAME> \
   --amount <ORIGINAL_AMOUNT> \
   --time-grain <Monthly|Quarterly|Annually> \
   --start-date <YYYY-MM-01> \
   --end-date <YYYY-MM-01> \
-  --notification <KEY=VALUE pairs from original>
+  --notification $ORIGINAL_NOTIFICATION_FIELDS_JSON
 ```
 
 ## Remove a runaway action group from a budget
@@ -38,3 +40,8 @@ az consumption budget create -n <BUDGET_NAME> \
 - Spend that already occurred before the budget alert triggered cannot be reversed.
 - Deleting a budget does NOT stop any VMs or resources — it only removes the alerting rule.
 - Quota increases, once approved by Microsoft, cannot be reduced below the original limit.
+
+
+## Cost-data latency caveat
+
+Microsoft Learn documents that cost and usage data is typically available within 8-24 hours and budget evaluation runs every 24 hours. A rollback or threshold reduction does not undo spend that already occurred and might not immediately reflect current consumption.

package/skills/azure/azure-live-cost-budget-action-guard/references/safety-checklist.md

@@ -0,0 +1,29 @@
+# Safety Checklist
+
+## Evidence labels
+
+- `documentation-based`: grounded in Microsoft Learn or listed official documentation.
+- `sampled-current-state`: grounded in read-only Azure or Kubernetes observations from the user's configured tools.
+- `user-provided`: grounded in sanitized snippets supplied by the user.
+- `inference`: reasoned from evidence but not directly proven.
+
+## Mutation boundary
+
+- Default to read-only review.
+- Do not perform create, update, delete, rotate, purge, recover, apply, swap, reset, complete, deploy, assign, revoke, deallocate, quota, budget, or policy changes unless the user explicitly asks and approval is clear.
+- Prefer preview, what-if, dry-run, status, describe, list, show, diff, activity-log, and policy evaluation evidence before any mutation.
+
+## Credential and data boundary
+
+- Never ask users to paste credentials, tokens, tenant IDs, subscription IDs, customer data, private keys, kubeconfig contents, CA requester credentials, secret values, connection strings, or raw environment dumps.
+- Summarize sensitive evidence by field presence, control state, and risk; do not reproduce secret material.
+
+## Risk gates
+
+- Stop on ambiguous target, ambiguous principal, missing approval, missing rollback, missing financial owner, or missing asset owner for high-impact assets.
+- Treat broad permissions, permanent privileged access, public exposure, purge authority, destructive deployment behavior, quota increases, budget automation, and production slot swaps as high-risk.
+- Separate documented product behavior from sampled configured-environment evidence.
+
+## Asset-specific hard line
+
+Never approve quota increases, budget threshold raises, automated cost actions, or high-cost SKU provisioning without explicit financial owner approval, cost data latency caveat, rollback or stop action, and scope confirmation.

package/skills/azure/azure-live-cost-budget-action-guard/references/workflow-and-output.md

@@ -0,0 +1,33 @@
+# Workflow and Output Contract
+
+## Execution flow
+
+1. Scope the exact target, environment boundary, owner, requested operation, approval state, and rollback owner.
+2. Load `official-sources.md`, then the component operations guide for service behavior and risk gates.
+3. Gather sampled read-only evidence only when available and safe.
+4. Compare observed posture against documented behavior, least-privilege expectations, and live-operation safety rules.
+5. Refuse or defer mutation if target, approval, rollback, or evidence is incomplete.
+6. Return a verdict with evidence level, blockers, safe next actions, and open questions.
+
+## Required output
+
+- `verdict`: pass, warn, fail, or blocked.
+- `evidence_level`: documentation-based, sampled-current-state, user-provided, inference, or mixed.
+- `scope`: what was reviewed and what was not reviewed.
+- `approval_status`: explicit approval, missing approval, or not applicable for read-only review.
+- `blockers`: issues that prevent a safe or production-ready conclusion.
+- `findings`: severity-labeled risks with source labels.
+- `rollback_posture`: exact rollback path or explicit non-reversibility caveat.
+- `safe_next_actions`: reversible actions first; mutation only with explicit approval.
+- `open_questions`: missing facts that would change the verdict.
+
+## Stress checks
+
+- What assumption would make this recommendation unsafe?
+- Which role, policy, budget, quota, deployment, swap, or purge action has the largest blast radius?
+- What evidence would disprove the claimed readiness?
+- Is the answer accidentally treating documentation as environment-specific proof?
+
+## Response discipline
+
+Use Microsoft Learn documentation through the user's configured documentation MCP for documented Azure behavior. Use sampled read-only Azure evidence only for current configured-environment observations and label it as sampled evidence.

package/skills/azure/azure-live-entra-role-assignment-guard/SKILL.md

@@ -4,8 +4,8 @@ description: Guard live permanent Microsoft Entra ID and Azure RBAC role assignm
 allowed-tools: Read Grep Glob WebFetch
 metadata:
   author: "github: Raishin"
-  version: "0.1.0"
-  updated: "2026-05-05"
+  version: 0.1.7
+  updated: "2026-06-05"
   category: security
 ---
 
@@ -25,7 +25,7 @@ Use this skill when:
 
 ## Lean operating rules
 
-- Prefer Azure CLI (`az`) and Microsoft Learn docs when available; fall back to sanitized user evidence.
+- Prefer Microsoft Learn documentation through the user's configured documentation MCP; use sampled read-only Azure evidence when available, then sanitized user evidence.
 - Do not create or delete any role assignment until subscription or tenant, active principal, target scope, role, and assignee identity are all explicit.
 - Prefer read-only inspection (`az role assignment list`, `az ad user show`) before any write.
 - Flag the following as high-severity and require explicit justification with business case before proceeding:
@@ -41,10 +41,14 @@ Use this skill when:
 
 Load these only when needed:
 
-- [Preflight commands](references/preflight-commands.md) — Azure CLI commands to inspect current assignments, identity, and scope before any write.
-- [Rollback playbook](references/rollback-playbook.md) — how to remove an assignment and verify access is revoked.
-- [Permission model](references/permission-model.md) — least-privilege role alternatives, dangerous role IDs, and PIM vs permanent guidance.
-- [Official sources](references/official-sources.md) — authoritative Microsoft documentation links.
+- [Azure Entra and RBAC Role Assignment Operations](references/role-assignment-operations.md) — use for current service behavior, common failure modes, hard design rules, verification targets, and push-back conditions.
+- [Preflight commands](references/preflight-commands.md) — CLI commands to run before any mutation.
+- [Rollback playbook](references/rollback-playbook.md) — concrete rollback steps for this service.
+- [Permission model](references/permission-model.md) — RBAC role definitions and PIM guidance.
+- [MCP and evidence path](references/mcp-and-evidence.md) — use when choosing documentation-based evidence, sampled read-only evidence, or sanitized user evidence.
+- [Safety checklist](references/safety-checklist.md) — use for evidence labels, permanent assignment blast radius, PIM eligibility, guest/service-principal risk, propagation delay, and rollback limits.
+- [Workflow and output contract](references/workflow-and-output.md) — execution flow and final response contract.
+- [Official sources](references/official-sources.md) — authoritative Azure documentation links.
 
 ## Response minimum
 

package/skills/azure/azure-live-entra-role-assignment-guard/metadata.json

@@ -11,18 +11,19 @@
     "kiro",
     "other"
   ],
-  "summary": "Guard live permanent Microsoft Entra ID and Azure RBAC role assignments with scope audit, principal-type risk classification, dangerous-role detection, and explicit approval gates before write.",
+  "summary": "Guard live permanent Microsoft Entra ID and Azure RBAC role assignments with scope audit, principal-type risk classification, dangerous-role detection, PIM preference, propagation caveats, and explicit approval gates before write.",
   "source_type": "original",
   "official_docs": [
-    "https://learn.microsoft.com/en-us/azure/role-based-access-control/overview",
-    "https://learn.microsoft.com/en-us/azure/role-based-access-control/best-practices",
-    "https://learn.microsoft.com/en-us/azure/role-based-access-control/built-in-roles",
-    "https://learn.microsoft.com/en-us/azure/role-based-access-control/role-assignments-alert",
-    "https://learn.microsoft.com/en-us/entra/id-governance/privileged-identity-management/pim-configure"
+    "https://learn.microsoft.com/azure/role-based-access-control/overview",
+    "https://learn.microsoft.com/azure/role-based-access-control/best-practices",
+    "https://learn.microsoft.com/azure/role-based-access-control/role-assignments-steps",
+    "https://learn.microsoft.com/azure/role-based-access-control/role-assignments-alert",
+    "https://learn.microsoft.com/azure/role-based-access-control/troubleshooting#azure-role-assignments",
+    "https://learn.microsoft.com/entra/id-governance/privileged-identity-management/pim-deployment-plan"
   ],
-  "security_notes": "Never create Owner, Contributor, or User Access Administrator assignments at subscription or management-group scope without explicit CISO-level justification. Always prefer PIM eligible assignment over permanent. Block any assignment to Guest principals without Director-level sign-off. Token caching means deletion may take up to 5 minutes to propagate.",
-  "last_verified": "2026-05-01",
+  "security_notes": "Never create or delete privileged role assignments without confirmed tenant/scope, assignee identity, principal type, role definition, existing assignment evidence, PIM alternative review, explicit approval, propagation caveat, and rollback command.",
+  "last_verified": "2026-06-05",
   "path": "skills/azure/azure-live-entra-role-assignment-guard",
   "author": "github: Raishin",
-  "version": "0.1.0"
+  "version": "0.1.7"
 }

package/skills/azure/azure-live-entra-role-assignment-guard/references/mcp-and-evidence.md

@@ -0,0 +1,26 @@
+# Documentation and Evidence Path
+
+## Preferred evidence order
+
+1. Microsoft Learn documentation through the user's configured documentation MCP for documented Azure behavior.
+2. Sampled read-only Azure evidence, when safely available, for current configured-environment observations.
+3. Sanitized user-provided evidence.
+4. Clearly labeled inference.
+
+## What each evidence type can prove
+
+- Microsoft Learn documentation can prove documented service behavior, supported concepts, limitations, and recommended patterns.
+- Sampled read-only evidence can prove the sampled configured state at the time observed.
+- Sanitized user evidence can prove only what the snippet shows.
+- None of these alone prove broad regional availability, future success, full account posture, or production readiness.
+
+## Safe usage pattern
+
+- State whether each claim is documentation-based, sampled-current-state, user-provided, or inference.
+- Use read-only queries before recommending changes.
+- Do not include sensitive internal identifiers, tenant identifiers, subscription identifiers, or secrets in committed docs or final findings.
+- If no sampled evidence is available, say the review is documentation-based and list the exact evidence still needed.
+
+## Live-operation rule
+
+For live operations, documentation is never enough. Require target confirmation, current-state evidence, explicit approval, rollback constraints, and post-action verification.

package/skills/azure/azure-live-entra-role-assignment-guard/references/official-sources.md

@@ -1,21 +1,35 @@
 # Official Sources
 
-Load these only when needed:
-
-- [Azure RBAC overview](https://learn.microsoft.com/en-us/azure/role-based-access-control/overview) — use for role assignment model, scope hierarchy (management group → subscription → resource group → resource), and security principal types.
-- [Best practices for Azure RBAC](https://learn.microsoft.com/en-us/azure/role-based-access-control/best-practices) — use for least privilege, group-based assignment, PIM preference, limiting Owner and UAA, and stable role ID usage.
-- [Azure built-in roles](https://learn.microsoft.com/en-us/azure/role-based-access-control/built-in-roles) — use when checking whether a narrow built-in role satisfies the requirement before recommending Contributor or Owner.
-- [Alert on privileged role assignments](https://learn.microsoft.com/en-us/azure/role-based-access-control/role-assignments-alert) — use for the Kusto query pattern to detect Owner / Contributor / UAA assignment events in Activity Log.
-- [Entra ID PIM overview](https://learn.microsoft.com/en-us/entra/id-governance/privileged-identity-management/pim-configure) — use when the permanent assignment request should instead use PIM eligible assignment with JIT activation.
-- [az role assignment CLI reference](https://learn.microsoft.com/en-us/cli/azure/role/assignment) — use for exact `az role assignment create`, `list`, `delete` syntax and parameter options.
-- [Understand role assignments](https://learn.microsoft.com/en-us/azure/role-based-access-control/role-assignments) — use for role assignment object structure (name, roleDefinitionId, principalId, principalType, scope, condition).
-
-## Grounded insights worth carrying into the skill
-
-- The Azure RBAC API version for role assignments is `2022-04-01` (`Microsoft.Authorization/roleAssignments`).
-- Dangerous role definition IDs (stable — never rename): Owner `8e3af657-a8ff-443c-a75c-2fe8c4bcb635`, Contributor `b24988ac-6180-42a0-ab88-20f7382dd24c`, User Access Administrator `18d7d88d-d35e-4fb5-a5c3-7773c20a72d9`.
-- A permanent role assignment at subscription scope granted to a Guest user is one of the most common post-breach persistence techniques in Azure tenants — always block without explicit CISO-level sign-off.
-- Azure AD token caching means a deleted assignment may still be honored for up to 5 minutes after deletion; do not declare rollback complete immediately.
-- `Microsoft.Authorization/roleAssignments/write` at subscription scope is the permission that enables all downstream privilege escalation — any principal with it can assign themselves Owner.
-- Prefer `az role assignment list --include-inherited` to find assignments at parent scopes that affect the target resource.
-- Microsoft recommends group-based role assignment over direct user assignment to simplify access reviews and offboarding.
+Use these sources to ground the skill. Microsoft Learn documentation proves documented Azure behavior; it does not prove the user's tenant, subscription, RBAC, quota, deployed resources, current cost, vault state, app health, or production readiness.
+
+## Primary Microsoft Learn sources
+
+- https://learn.microsoft.com/azure/role-based-access-control/overview
+- https://learn.microsoft.com/azure/role-based-access-control/best-practices
+- https://learn.microsoft.com/azure/role-based-access-control/role-assignments-steps
+- https://learn.microsoft.com/azure/role-based-access-control/role-assignments-alert
+- https://learn.microsoft.com/azure/role-based-access-control/troubleshooting#azure-role-assignments
+- https://learn.microsoft.com/entra/id-governance/privileged-identity-management/pim-deployment-plan
+
+## Grounding notes
+
+- Documentation-based claim: Microsoft Learn evidence says Azure RBAC grants who can access Azure resources, what they can do, and where. Best practices require least privilege, narrow scope, limiting privileged administrator roles, assigning to groups where manageable, and using PIM for just-in-time access. Privileged role assignments such as Owner, Contributor, and User Access Administrator are powerful and can be monitored with alerts; role assignment changes can take time to propagate.
+- Current-state claim: requires sampled read-only Azure evidence or sanitized user-provided evidence.
+- Live-operation claim: requires target, principal, approval, preflight evidence, rollback constraints, and post-action verification.
+- Inference: allowed only when labeled and tied to observed fields or documented behavior.
+- Do not include sensitive internal identifiers or secret material in findings.
+
+## Source use rules
+
+- Prefer Microsoft Learn documentation through the user's configured documentation MCP for current Azure service behavior.
+- Use sampled read-only Azure evidence only to validate current configured-environment observations.
+- If documentation and sampled evidence appear to conflict, report both and stop short of a production-ready verdict.
+- Re-check official sources before changing high-risk guidance, because cloud behavior and feature availability can change.
+
+## Current Microsoft Learn deltas checked on 2026-06-05
+
+- Azure RBAC and Microsoft Entra directory roles are different assignment systems with different scopes and tooling.
+- Eligible, time-bound PIM assignment for Azure RBAC is not equivalent for users, service principals, applications, and managed identities; verify supported principal type before recommending PIM as the answer.
+- Built-in Microsoft Entra roles assigned to guests can grant the same role permissions as member users; do not downplay guest-admin blast radius.
+- Administrative-unit-scoped assignments can still need tenant-scope read permissions for some principal types to function.
+

package/skills/azure/azure-live-entra-role-assignment-guard/references/permission-model.md

@@ -1,5 +1,9 @@
 # Permission Model: Azure Live Entra Role Assignment Guard
 
+## Evidence-variable convention
+
+Shell variables in examples are local operator placeholders from an approved change record or already configured shell context. Do not commit real values, and redact them from shared evidence unless disclosure is explicitly approved.
+
 ## Risk classification by role
 
 | Role | Risk | Reason |
@@ -55,7 +59,7 @@
     "Microsoft.Authorization/roleDefinitions/read"
   ],
   "AssignableScopes": [
-    "/subscriptions/<SUBSCRIPTION_ID>"
+    "$APPROVED_AZURE_SCOPE"
   ]
 }
 ```
@@ -68,3 +72,5 @@ Restrict `AssignableScopes` to resource-group scope for operators who should not
 - User Access Administrator at subscription scope (allows re-elevating to Owner)
 - Any Entra directory role (Global Admin, Privileged Role Admin) assigned outside of PIM
 - Service principal with Owner and no owner/contact defined in application registration
+
+Use exact resource scopes from approved change records; do not paste raw subscription identifiers into chat.

package/skills/azure/azure-live-entra-role-assignment-guard/references/preflight-commands.md

@@ -14,19 +14,19 @@ az ad signed-in-user show --query "{displayName:displayName, id:id, userPrincipa
 ```bash
 # Subscription scope
 az role assignment list \
-  --scope "/subscriptions/<SUBSCRIPTION_ID>" \
+  --scope "$APPROVED_AZURE_SCOPE" \
   --include-inherited \
   --query "[].{role:roleDefinitionName, principal:principalName, principalType:principalType, scope:scope}"
 
 # Management group scope
 az role assignment list \
-  --scope "/providers/Microsoft.Management/managementGroups/<MG_ID>" \
+  --scope "$APPROVED_MANAGEMENT_GROUP_SCOPE" \
   --include-inherited \
   --query "[].{role:roleDefinitionName, principal:principalName, principalType:principalType, scope:scope}"
 
 # Resource group scope
 az role assignment list \
-  --resource-group <RESOURCE_GROUP> \
+  --resource-group $AZURE_RESOURCE_GROUP_NAME \
   --include-inherited \
   --query "[].{role:roleDefinitionName, principal:principalName, principalType:principalType, scope:scope}"
 ```
@@ -35,17 +35,17 @@ az role assignment list \
 
 ```bash
 # For a user
-az ad user show --id <UPN_OR_OBJECT_ID> \
+az ad user show --id $ASSIGNEE_LOOKUP_VALUE \
   --query "{displayName:displayName, userPrincipalName:userPrincipalName, userType:userType, accountEnabled:accountEnabled}"
 
 # userType: "Guest" = external account, elevated risk. Always flag.
 
 # For a service principal
-az ad sp show --id <APP_ID_OR_OBJECT_ID> \
+az ad sp show --id $SERVICE_PRINCIPAL_LOOKUP_VALUE \
   --query "{displayName:displayName, appId:appId, servicePrincipalType:servicePrincipalType}"
 
 # For a managed identity
-az identity show --name <IDENTITY_NAME> --resource-group <RG> \
+az identity show --name $MANAGED_IDENTITY_NAME --resource-group $AZURE_RESOURCE_GROUP_NAME \
   --query "{name:name, principalId:principalId, tenantId:tenantId}"
 ```
 
@@ -54,7 +54,7 @@ az identity show --name <IDENTITY_NAME> --resource-group <RG> \
 ```bash
 # Find Owner and UAA at subscription scope (Kusto alternative via activity log)
 az role assignment list \
-  --scope "/subscriptions/<SUBSCRIPTION_ID>" \
+  --scope "$APPROVED_AZURE_SCOPE" \
   --query "[?roleDefinitionName=='Owner' || roleDefinitionName=='User Access Administrator'].{role:roleDefinitionName, principal:principalName, principalType:principalType}"
 ```
 
@@ -62,8 +62,8 @@ az role assignment list \
 
 ```bash
 az role eligibility-schedule list \
-  --scope "/subscriptions/<SUBSCRIPTION_ID>" \
-  --query "[?principalId=='<PRINCIPAL_OBJECT_ID>'].{role:roleDefinitionDisplayName, endDateTime:endDateTime, status:status}"
+  --scope "$APPROVED_AZURE_SCOPE" \
+  --query "[?principalId=='$ASSIGNEE_OBJECT_ID'].{role:roleDefinitionDisplayName, endDateTime:endDateTime, status:status}"
 ```
 
 If an eligible assignment already exists, the correct action is PIM activation, not a new permanent assignment.