Optimizing cloud costs

Skill jeremylongshore/claude-code-plugins-plus-skills/plugins/devops/cloud-cost-optimizer/skills/optimizing-cloud-costs

'Execute use when you need to work with cloud cost optimization.From its SKILL.md

Install

npx -y skills add jeremylongshore/claude-code-plugins-plus-skills --skill optimizing-cloud-costs

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.3 KB, 822 tokens by cl100k_base, as published. Nobody here has run it

Optimizing Cloud Costs

Overview

Analyze cloud spending across AWS, GCP, and Azure to identify waste, recommend rightsizing, and generate cost-saving configurations. Covers reserved instances, spot/preemptible workloads, storage tiering, idle resource cleanup, and budget alerting using cloud-native cost management APIs.

Prerequisites

Cloud provider CLI authenticated with billing/cost-explorer read access
AWS: ce:GetCostAndUsage, ec2:DescribeInstances, cloudwatch:GetMetricData permissions
GCP: Billing Account Viewer and Compute Viewer roles
Azure: Cost Management Reader role
Access to current infrastructure-as-code (Terraform, CloudFormation) for rightsizing changes
At least 30 days of billing data for meaningful analysis

Instructions

Pull current cost data using cloud cost APIs (aws ce get-cost-and-usage, gcloud billing budgets list)
Identify the top 10 cost drivers by service, region, and resource tag
Detect idle resources: instances with < 5% average CPU over 14 days, unattached EBS volumes, unused Elastic IPs, orphaned snapshots
Recommend rightsizing: compare instance utilization against available instance types and suggest downsizing
Evaluate reserved instance or savings plan coverage against on-demand spend; recommend commitments for steady-state workloads
Identify spot/preemptible candidates: stateless, fault-tolerant workloads (batch jobs, CI runners, dev environments)
Review storage costs: recommend S3 Intelligent-Tiering, lifecycle policies for infrequent access, or Glacier for archives
Generate Terraform/IaC changes to implement approved optimizations
Set up budget alerts with thresholds at 50%, 80%, and 100% of monthly budget
Create a cost optimization report summarizing findings, savings estimates, and implementation priority

Output

Cost analysis report with per-service breakdown and savings recommendations
Terraform/CloudFormation changes for rightsizing and reserved instance purchases
S3 lifecycle policy configurations for storage tiering
Budget alert configurations (CloudWatch, GCP Budget, Azure Cost Alerts)
Cleanup scripts for idle resources (with dry-run mode for safety)

Error Handling

Error	Cause	Solution
`Access Denied on Cost Explorer API`	Missing `ce:*` IAM permissions	Attach the `AWSBillingReadOnlyAccess` managed policy to the IAM user/role
`No billing data available`	Account is too new or cost export not enabled	Enable Cost Explorer (takes 24h to populate) or set up CUR (Cost and Usage Report)
`Rightsizing recommendation breaks workload`	Instance too small for peak load	Base sizing on P95 utilization, not average; keep a 20% headroom buffer
`Spot instance terminated mid-job`	Spot capacity reclaimed by provider	Use spot fleet with diversified instance types and implement checkpointing
`Budget alert not firing`	SNS topic or notification channel misconfigured	Verify SNS subscription is confirmed and test with a low threshold

Examples

"Analyze AWS costs for the last 3 months, identify the top waste areas, and generate a cleanup script for unattached EBS volumes and unused Elastic IPs."
"Compare on-demand EC2 spend against Savings Plans pricing and recommend 1-year commitments for steady-state workloads."
"Create S3 lifecycle policies to move objects older than 90 days to Glacier and delete after 365 days across all buckets tagged env:production."

Resources

AWS Cost Explorer: https://docs.aws.amazon.com/cost-management/latest/userguide/ce-what-is.html
GCP Cost Management: https://cloud.google.com/billing/docs/how-to/budgets
Azure Cost Management: https://learn.microsoft.com/en-us/azure/cost-management-billing/
FinOps Foundation: https://www.finops.org/framework/

What ships with it: 8 files

11.9 KB alongside SKILL.md, 1 of them executable

Gives 0 of the 12 instructions most token cost skills give in 822 tokens

Counted across 84 of the 95 authors here whose files we hold, read 2026-09-06

Set explicit budget limits before processing batchesin 14 of 84, across 9 files
Define model names as constants or configin 14 of 84, across 9 files
Route simple tasks to cheaper modelsin 14 of 84, across 9 files
Log model selection decisionsin 14 of 84, across 9 files
Retry only transient errorsin 14 of 84, across 9 files
Track spend with immutable cost recordsin 13 of 84, across 8 files
Cache system prompts over 1024 tokensin 12 of 84, across 7 files
Check the budget before each API callin 12 of 84, across 7 files
Start with the cheapest modelin 9 of 84, across 8 files
Back off exponentially between retriesin 9 of 84, across 8 files
Review costs weeklyin 8 of 84, across 6 files
Use reserved capacity for steady workloadsin 8 of 84, across 6 files

Said here and by no other author read

Pull current cost data via cloud cost APIs
Identify the top cost drivers by service, region, and tag
Recommend rightsizing by comparing utilization to instance types
Recommend reserved instance or savings plan commitments for steady workloads
Identify spot candidates among stateless, fault-tolerant workloads
Recommend storage tiering and lifecycle policies

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.