Cost Analysis — Agent Skill by Microsoft

From the author

Analyze actual Azure spend, bill changes, and AKS or AI costs. WHEN: "Azure cost breakdown", "most expensive resources", "why did my bill increase", "cost spike", "unexpected charge", "Cosmos DB charges", "Foundry model costs", "AKS cluster cost", "namespace cost", "enable AKS cost analysis", "idle AKS capacity". DO NOT USE FOR: forecasts, pricing estimates, rightsizing, commitments, or budgets.

— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The cost-analysis skill provides a structured approach to investigating historical Azure billing data. It focuses on identifying cost drivers, explaining anomalies, and breaking down expenditures for specific services like Azure Kubernetes Service (AKS) and AI models. The skill emphasizes using official billing dimensions and resource graphs to provide evidence-based reports while strictly avoiding speculative tasks like forecasting, pricing estimates, or rightsizing recommendations.

What it does

Queries historical Azure spend by scope, period, and currency.
Investigates cost spikes and unexpected charges using billing dimensions.
Analyzes AKS cluster and namespace cost allocation.
Breaks down AI service and model-related costs.
Correlates billing data with operational evidence from Resource Graph.
Distinguishes between measured costs and inferred causes.

When to use it

When you need a breakdown of your current Azure bill.
When investigating a sudden cost spike or unexpected charge.
When analyzing the cost distribution across AKS namespaces.
When identifying the most expensive resources in your subscription.
When correlating AI service spend with specific resource usage.

Advantages

Provides evidence-based analysis using official billing data.
Maintains clear separation between measured costs and inferred contributors.
Standardizes the investigation process for AKS and AI service costs.
Prevents speculative errors by excluding forecasting and rightsizing.

Usage examples

“Why did my Azure bill increase last month?”: The agent will query historical cost data for the specified period, identify the primary service or resource contributors to the increase, and report the findings.
“Show me the cost breakdown for my AKS namespaces.”: The agent will use the AKS cost analysis workflow to retrieve and present the cost allocation per namespace, including idle or unallocated charges.
“What are the most expensive resources in my subscription?”: The agent will perform a cost query grouped by resource to identify and list the top contributors to your current Azure spend.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/microsoft/cost-analysis/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip cost-analysis.zip -d .agents/skills

Documentation by Microsoft

Azure Cost Analysis

Quick Reference

Intent	Workflow	Primary tools
Query historical spend	Cost query	`query_costs`
Explain a spike	Cost investigation	`query_costs`, Resource Graph
Analyze AKS spend	AKS cost analysis	`query_aks_costs`, Resource Graph
Analyze AI service spend	AI cost analysis	`query_costs`

When to Use This Skill

Use for spend, anomalies, and AKS or AI allocation.

MCP Tools

Use cost tools and Resource Graph first. If an operation is unavailable, follow fallback and safety.

Workflow

Confirm scope, period, currency, and breakdown.
Load only the matching workflow above.
Never transform MCP results in a shell or interpreter; request tool-side totals, grouping, sorting, or bounded follow-up queries.
Respect row limits and label incomplete data.
Separate measured cost from inferred causes and recommendations.

Error Handling

Error	Action
Access denied	Name the required scope and role.
Empty result	Distinguish no data from unavailable data.
Multiple currencies	Report each currency separately.
Server error	Retry once; then stop with the trace ID.

Files

ATTRIBUTION.mdAdded by AutoGineer965 B
LICENSELicence file added by AutoGineer1.1 KiB
SKILL.md1.9 KiB
references/ai-cost-analysis.md2.1 KiB
references/aks-anomaly.md4.5 KiB
references/aks-cost-analysis.md1.5 KiB
references/aks-enablement.md1.4 KiB
references/cost-investigation.md3.2 KiB
references/cost-query/dimensions-by-scope.md1.5 KiB
references/cost-query/error-handling.md1.5 KiB
references/cost-query/examples.md1.2 KiB
references/cost-query/guardrails.md1.7 KiB
references/cost-query/request-body-schema.md1.4 KiB
references/cost-query/workflow.md2.6 KiB
references/tools-and-safety.md2.2 KiB

references/tools-and-safety.md

Cost Tool and Safety Guidance

Tool preference

Use Azure Resource Manager MCP (ARM MCP) first. For Resource Graph, use the generate, validate, execute sequence.

If a required operation is unavailable, name the fallback API and use an already authenticated Azure CLI, Azure PowerShell, or direct REST client. Prefer a native command when it exposes the required fields; otherwise use az rest, Invoke-AzRestMethod, or authenticated REST. Do not fall back for invalid input, denied access, throttling, or empty data.

Workflow	Fallback API
Historical or AI cost	Cost Management Query API
AKS cost	Cost Management Query API for Kubernetes cost data
Resource inventory or changes	Azure Resource Graph Resources API
AKS utilization	Azure Monitor Metrics API
Enable AKS cost analysis	AKS Managed Clusters API

Preserve the MCP workflow's scope, period, row limits, pagination, currency, and evidence labels. State which fallback was used. Never expose access tokens. Require explicit approval before a fallback write or configuration change. Do not invoke Bash, PowerShell, Python, or another local interpreter merely to parse or aggregate an MCP response. Request server-side grouping or sorting, or issue smaller bounded MCP queries. Use shell clients only for an approved API fallback when the required MCP operation is unavailable.

Evidence labels

Label	Meaning
Actual cost	Returned by Cost Management for the selected scope and period.
Actual metric	Returned by Azure Monitor or Kubernetes metrics.
Retail price	Returned by official Azure retail pricing.
Negotiated price	Returned from the user's pricesheet.
Estimate	Calculated from stated assumptions.

Follow Resource Graph skipToken pages. For cost tools without continuation input, increase top within the tool limit or narrow scope and label incomplete results. Preserve currencies and reporting periods. Do not turn missing data into zero, combine currencies, or present retail comparisons as realized savings.

Require explicit approval before writes, purchases, tier changes, stops, resizes, or deletes. Budget creation additionally requires confirmed scope, name, amount, period, thresholds, and recipients.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Modal
K-Dense· Community
A serverless cloud platform for deploying and scaling Python applications, AI models, and GPU-accelerated workloads.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Low riskGitHub stars of the source repository56.4k
Cloud Infrastructure Network Engineer
Seth Hobson· Community
An expert network engineer persona specializing in cloud architecture, security, and performance optimization.
Cloud and DevOpsClaude Code
MITGitHub stars of the source repository42.3k
Deployment Validation Cloud Architect
Seth Hobson· Community
Expert cloud architect for multi-cloud infrastructure, cost optimization, and resilient system design.
Cloud and DevOpsClaude Code
MITGitHub stars of the source repository42.3k
Airflow Dag Patterns
Seth Hobson· Community
Best practices and design patterns for building and maintaining production-ready Apache Airflow DAGs.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Cost Optimization
Seth Hobson· Community
A comprehensive framework for reducing cloud infrastructure costs across AWS, Azure, GCP, and OCI.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Hybrid Cloud Networking
Seth Hobson· Community
A guide to configuring secure, high-performance network connectivity between on-premises infrastructure and major cloud providers.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download cost-analysis.zip