cost-governance
Govern Azure costs with budgets, alerts, tags, and policy restrictions. WHEN: "Azure budget health", "configured budget overrun", "list Azure budgets", "create Azure budget", "budget alerts", "budget coverage", "missing CostCenter tags", "allowed VM SKUs", "allowed Azure regions", "would this SKU be denied", "cost guardrails". DO NOT USE FOR: planning-target forecasts, bill investigations, pricing, rightsizing, or commitments.
73
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Cost Governance
Quick Reference
| Intent | Workflow | Primary tools |
|---|---|---|
| Check budget status | Budget health | list_budgets, forecast_costs, query_costs, list_alerts |
| Configure a budget | Budget setup | Cost tools, create_budget |
| Review guardrails | Guardrails | Resource Graph, list_budgets |
When to Use This Skill
Use for budgets, alerts, tags, and policy.
MCP Tools
Use cost tools for budgets; Resource Graph for guardrails. Writes need confirmed scope, amount, thresholds, and recipients. Fallback: API mappings.
Workflow
- Confirm scope and load the matching workflow.
- Never transform MCP results in a shell or interpreter; request tool-side filtering or bounded follow-up queries.
- Distinguish access failures from empty results.
- Report gaps without implying budgets cap spend.
Error Handling
| Error | Action |
|---|---|
| Access denied | Name missing permission. |
| No budget or forecast | Report unavailable data, not zero. |
| Multiple currencies | Never sum or compare across currencies. |
| Write conflict | Preserve the budget. |
| Server error | Retry once; then stop with the trace ID. |
- Repository
- microsoft/GitHub-Copilot-for-Azure
- Commit
fcf2f3b
- Last updated
- First committed
Also appears in
since Sep 26, 2026
since Sep 25, 2026
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.