
Azure Cost Optimizer
Finds Azure cost savings in your infrastructure code and live resources, then files GitHub issues for them.
- Repository
- github/awesome-copilot
- Stars
- 40,703
- Licence
- MIT
- Files
- 1 file
What it does
When installed, the agent follows a multi-step workflow to review an Azure app's infrastructure-as-code files (such as Bicep or Terraform) and the Azure resources actually running in a resource group. It pulls usage metrics, estimates monthly costs, and suggests cheaper configurations such as right-sizing, switching pricing tiers, or adding storage lifecycle policies. After you approve a summary, it creates one GitHub issue per optimization plus an EPIC issue to track the work.
Great for
- Developers maintaining an Azure app who want a structured review of spending
- Teams that already use Azure MCP and GitHub MCP servers and want cost work tracked as GitHub issues
Skip it if
- Projects without IaC files: the skill says to stop and report if none are found, so it cannot run its analysis.
- Anyone who wants savings applied automatically: it recommends and files issues, and changes to live resources or pricing estimates still need human review, since the skill itself notes that savings calculations must be validated.
Try asking
- “Analyze the Azure resources in my resource group rg-prod and suggest cost savings as GitHub issues.”
- “Review our Bicep files for oversized App Service plans and Cosmos DB throughput settings.”
- “Find unused or redundant storage accounts in this app's infrastructure and create an EPIC issue to track cleanup.”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
az-cost-optimize.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip az-cost-optimize.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip az-cost-optimize.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Point the agent at a specific resource group and IaC folder so the analysis stays scoped to the app you care about.
- Check the pricing and savings figures yourself before approving issues, because the skill relies on estimates and asks the agent to look up current Azure pricing.
- Review the proposed issues at the confirmation step; the skill is designed to pause for your approval before creating any GitHub issues.
What's inside
- SKILL.md
Redistributed unmodified from github/awesome-copilot under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.