Cost Check
- 3 installs
- 12 repo stars
- Updated June 8, 2026
- aws-samples/sample-claude-code-plugins-for-startups
cost-check is a Claude Code skill that analyzes and optimizes AWS costs, ranking optimizations by savings potential versus implementation effort.
About
This skill turns Claude Code into an AWS cost-optimization specialist. It pulls cost data, identifies the top cost drivers and proposes optimizations ranked by savings versus effort, using a quick-wins checklist and gotchas on data transfer, Reserved Instances, Spot and Graviton. A developer uses it to cut an AWS bill or investigate unexpected charges.
- AWS cost-optimization specialist with a quick-wins checklist
- Ranks optimizations by savings potential vs implementation effort
- Flags hidden costs like cross-AZ data transfer and NAT gateway
Cost Check by the numbers
- 3 all-time installs (skills.sh)
- Ranked #892 of 1,039 Cloud & Infrastructure skills by installs in the Skillselion catalog
- Data as of Jul 28, 2026 (Skillselion catalog sync)
cost-check capabilities & compatibility
Free skill; uses an aws-cost MCP when available to read live cost data.
- Capabilities
- cost check · challenger · customer ideation
- Works with
- aws
- Use cases
- devops
- Pricing
- Free
What cost-check says it does
You are an AWS cost optimization specialist.
Data transfer costs are the silent killer — especially cross-AZ and cross-region
Graviton instances are ~20% cheaper and often faster — use them unless you need x86
npx skills add https://github.com/aws-samples/sample-claude-code-plugins-for-startups --skill cost-checkAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 3 |
|---|---|
| repo stars | ★ 12 |
| Last updated | June 8, 2026 |
| Repository | aws-samples/sample-claude-code-plugins-for-startups ↗ |
What it does
Analyze an AWS bill, find the top cost drivers, and propose optimizations ranked by savings versus effort.
Who is it for?
Reviewing AWS infrastructure for savings, estimating new-architecture cost, or investigating unexpected charges.
Skip if: Non-AWS cloud billing or general FinOps outside AWS.
When should I use this skill?
Reviewing infrastructure for cost savings, estimating costs for a new architecture, investigating unexpected charges, or comparing pricing between service options.
What you get
A ranked table of optimizations with current cost, estimated savings and effort.
- Top cost drivers
- Ranked optimization table
- Estimated savings and effort
By the numbers
- 9-item quick-wins checklist
- Spot saves 60-90%
- Graviton ~20% cheaper
Files
You are an AWS cost optimization specialist.
Process
1. Use the aws-cost MCP tools to pull current cost data when available 2. Use the awsknowledge MCP tools (mcp__plugin_aws-dev-toolkit_awsknowledge__aws___search_documentation, mcp__plugin_aws-dev-toolkit_awsknowledge__aws___read_documentation, mcp__plugin_aws-dev-toolkit_awsknowledge__aws___recommend) to verify current pricing models 3. Identify the top cost drivers 4. Propose optimizations ranked by savings potential vs implementation effort
Quick Wins Checklist
- [ ] Unused EBS volumes and unattached Elastic IPs
- [ ] Idle or oversized EC2 instances (check CPU/memory utilization)
- [ ] Missing S3 lifecycle policies on log/temp buckets
- [ ] NAT Gateway traffic that could use VPC endpoints
- [ ] Over-provisioned RDS instances
- [ ] Lambda functions with excessive memory allocation
- [ ] CloudWatch log retention set to "Never expire"
- [ ] Unused Elastic Load Balancers
- [ ] Old EBS snapshots and AMIs
Gotchas
- Data transfer costs are the silent killer — especially cross-AZ and cross-region
- Reserved Instances / Savings Plans: don't commit until you have 3+ months of stable usage data
- Spot Instances save 60-90% but need fault-tolerant workloads
- DynamoDB on-demand vs provisioned: on-demand is cheaper below ~20% utilization of provisioned capacity
- S3 Intelligent-Tiering has a monitoring fee per object — not worth it for millions of tiny objects
- CloudFront can be cheaper than S3 direct for high-traffic reads (no S3 request fees)
- Graviton instances are ~20% cheaper and often faster — use them unless you need x86
Output Format
| Resource | Current Cost | Optimization | Estimated Savings | Effort |
|---|---|---|---|---|
| ... | ... | ... | ... | Low/Med/High |
Related skills
Azure AiIntegrates Azure AI Content Safety, Document Intelligence, Speech, and Search services into Java-based agents and applications.495k1.4kAzure PrepareGenerate the exact Azure infrastructure files, Dockerfiles, and azure.yaml configuration needed before deploying any new or modernized application.494k1.4kAzure StorageConnect agents and applications to Azure Blob Storage, File Shares, Queues, Tables, and Data Lake without leaving the coding environment.494k1.4kAppinsights InstrumentationAutomatically instrument web applications running on Azure App Service with Application Insights for observability without manual configuration.493k1.4kAzure Resource LookupInstantly list, query, and discover any Azure resources across subscriptions without leaving the agent chat.493k1.4kAzure AigatewayConfigure Azure API Management as a secure, governed gateway for routing traffic to LLMs, MCP servers, and agent tools.493k1.4kFAQ
What are the biggest hidden AWS costs?
Data transfer costs, especially cross-AZ and cross-region, are the silent killer.
When should I commit to Reserved Instances?
Don't commit until you have 3+ months of stable usage data.