mcpbeat Sign in

AWS Cost Cleanup Agent Skill

Automated cleanup of unused AWS resources to reduce costs

2k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
1
copies elsewhere
how many repositories repackaged it
223
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/lingxling/awesome-skills-cn --skill aws-cost-cleanup

The instruction itself

18 sections, as written by the author

AWS Cost Cleanup

Automate the identification and removal of unused AWS resources to eliminate waste.

When to Use This Skill

Use this skill when you need to automatically clean up unused AWS resources to reduce costs and eliminate waste.

Automated Cleanup Targets

Storage

  • Unattached EBS volumes
  • Old EBS snapshots (>90 days)
  • Incomplete multipart S3 uploads
  • Old S3 versions in versioned buckets

Compute

  • Stopped EC2 instances (>30 days)
  • Unused AMIs and associated snapshots
  • Unused Elastic IPs

Networking

  • Unused Elastic Load Balancers
  • Unused NAT Gateways
  • Orphaned ENIs

Cleanup Scripts

Safe Cleanup (Dry-Run First)

#!/bin/bash
# cleanup-unused-ebs.sh

echo "Finding unattached EBS volumes..."
VOLUMES=$(aws ec2 describe-volumes \
  --filters Name=status,Values=available \
  --query 'Volumes[*].VolumeId' \
  --output text)

for vol in $VOLUMES; do
  echo "Would delete: $vol"
  # Uncomment to actually delete:
  # aws ec2 delete-volume --volume-id $vol
done
#!/bin/bash
# cleanup-old-snapshots.sh

CUTOFF_DATE=$(date -d '90 days ago' --iso-8601)

aws ec2 describe-snapshots --owner-ids self \
  --query "Snapshots[?StartTime<='$CUTOFF_DATE'].[SnapshotId,StartTime,VolumeSize]" \
  --output text | while read snap_id start_time size; do
  
  echo "Snapshot: $snap_id (Created: $start_time, Size: ${size}GB)"
  # Uncomment to delete:
  # aws ec2 delete-snapshot --snapshot-id $snap_id
done
#!/bin/bash
# release-unused-eips.sh

aws ec2 describe-addresses \
  --query 'Addresses[?AssociationId==null].[AllocationId,PublicIp]' \
  --output text | while read alloc_id public_ip; do
  
  echo "Would release: $public_ip ($alloc_id)"
  # Uncomment to release:
  # aws ec2 release-address --allocation-id $alloc_id
done

S3 Lifecycle Automation

# Apply lifecycle policy to transition old objects to cheaper storage
cat > lifecycle-policy.json <<EOF
{
  "Rules": [
    {
      "Id": "Archive old objects",
      "Status": "Enabled",
      "Transitions": [
        {
          "Days": 90,
          "StorageClass": "STANDARD_IA"
        },
        {
          "Days": 180,
          "StorageClass": "GLACIER"
        }
      ],
      "NoncurrentVersionExpiration": {
        "NoncurrentDays": 30
      },
      "AbortIncompleteMultipartUpload": {
        "DaysAfterInitiation": 7
      }
    }
  ]
}
EOF

aws s3api put-bucket-lifecycle-configuration \
  --bucket my-bucket \
  --lifecycle-configuration file://lifecycle-policy.json

Cost Impact Calculator

#!/usr/bin/env python3
# calculate-savings.py

import boto3
from datetime import datetime, timedelta

ec2 = boto3.client('ec2')

# Calculate EBS volume savings
volumes = ec2.describe_volumes(
    Filters=[{'Name': 'status', 'Values': ['available']}]
)

total_size = sum(v['Size'] for v in volumes['Volumes'])
monthly_cost = total_size * 0.10  # $0.10/GB-month for gp3

print(f"Unattached EBS Volumes: {len(volumes['Volumes'])}")
print(f"Total Size: {total_size} GB")
print(f"Monthly Savings: ${monthly_cost:.2f}")

# Calculate Elastic IP savings
addresses = ec2.describe_addresses()
unused = [a for a in addresses['Addresses'] if 'AssociationId' not in a]

eip_cost = len(unused) * 3.65  # $0.005/hour * 730 hours
print(f"\nUnused Elastic IPs: {len(unused)}")
print(f"Monthly Savings: ${eip_cost:.2f}")

print(f"\nTotal Monthly Savings: ${monthly_cost + eip_cost:.2f}")
print(f"Annual Savings: ${(monthly_cost + eip_cost) * 12:.2f}")

Automated Cleanup Lambda

import boto3
from datetime import datetime, timedelta

def lambda_handler(event, context):
    ec2 = boto3.client('ec2')
    
    # Delete unattached volumes older than 7 days
    volumes = ec2.describe_volumes(
        Filters=[{'Name': 'status', 'Values': ['available']}]
    )
    
    cutoff = datetime.now() - timedelta(days=7)
    deleted = 0
    
    for vol in volumes['Volumes']:
        create_time = vol['CreateTime'].replace(tzinfo=None)
        if create_time < cutoff:
            try:
                ec2.delete_volume(VolumeId=vol['VolumeId'])
                deleted += 1
                print(f"Deleted volume: {vol['VolumeId']}")
            except Exception as e:
                print(f"Error deleting {vol['VolumeId']}: {e}")
    
    return {
        'statusCode': 200,
        'body': f'Deleted {deleted} volumes'
    }

Cleanup Workflow

  • Discovery Phase (Read-only)
  • Run all describe commands
  • Generate cost impact report
  • Review with team
  • Validation Phase
  • Verify resources are truly unused
  • Check for dependencies
  • Notify resource owners
  • Execution Phase (Dry-run first)
  • Run cleanup scripts with dry-run
  • Review proposed changes
  • Execute actual cleanup
  • Verification Phase
  • Confirm deletions
  • Monitor for issues
  • Document savings

Safety Checklist

  • [ ] Run in dry-run mode first
  • [ ] Verify resources have no dependencies
  • [ ] Check resource tags for ownership
  • [ ] Notify stakeholders before deletion
  • [ ] Create snapshots of critical data
  • [ ] Test in non-production first
  • [ ] Have rollback plan ready
  • [ ] Document all deletions

Example Prompts

Discovery

  • "Find all unused resources and calculate potential savings"
  • "Generate a cleanup report for my AWS account"
  • "What resources can I safely delete?"

Execution

  • "Create a script to cleanup unattached EBS volumes"
  • "Delete all snapshots older than 90 days"
  • "Release unused Elastic IPs"

Automation

  • "Set up automated cleanup for old snapshots"
  • "Create a Lambda function for weekly cleanup"
  • "Schedule monthly resource cleanup"

Integration with AWS Organizations

# Run cleanup across multiple accounts
for account in $(aws organizations list-accounts \
  --query 'Accounts[*].Id' --output text); do
  
  echo "Checking account: $account"
  aws ec2 describe-volumes \
    --filters Name=status,Values=available \
    --profile account-$account
done

Monitoring and Alerts

# Create CloudWatch alarm for cost anomalies
aws cloudwatch put-metric-alarm \
  --alarm-name high-cost-alert \
  --alarm-description "Alert when daily cost exceeds threshold" \
  --metric-name EstimatedCharges \
  --namespace AWS/Billing \
  --statistic Maximum \
  --period 86400 \
  --evaluation-periods 1 \
  --threshold 100 \
  --comparison-operator GreaterThanThreshold

Best Practices

  • Schedule cleanup during maintenance windows
  • Always create final snapshots before deletion
  • Use resource tags to identify cleanup candidates
  • Implement approval workflow for production
  • Log all cleanup actions for audit
  • Set up cost anomaly detection
  • Review cleanup results weekly

Risk Mitigation

Medium Risk Actions:

  • Deleting unattached volumes (ensure no planned reattachment)
  • Removing old snapshots (verify no compliance requirements)
  • Releasing Elastic IPs (check DNS records)

Always:

  • Maintain 30-day backup retention
  • Use AWS Backup for critical resources
  • Test restore procedures
  • Document cleanup decisions

Kiro CLI Integration

# Analyze and cleanup in one command
kiro-cli chat "Use aws-cost-cleanup to find and remove unused resources"

# Generate cleanup script
kiro-cli chat "Create a safe cleanup script for my AWS account"

# Schedule automated cleanup
kiro-cli chat "Set up weekly automated cleanup using aws-cost-cleanup"

Additional Resources

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Other skills for the same job

different authors, same section of the catalogue
Azure Kubernetes Automatic Readiness
by microsoft
vendor ×3

Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.

13k tokens
Capacity
by microsoft
vendor ×3

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.

6k tokens scripts
Customize
by microsoft
vendor ×3

Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).

8k tokens
Deploy Model
by microsoft
vendor ×3

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

26k tokens scripts
Preset
by microsoft
vendor ×3

Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).

9k tokens
Lamindb
by christophacham
×3

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

22k tokens
Latchbio Integration
by christophacham
×3

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

12k tokens
Modal
by christophacham
×3

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

17k tokens

How to use it

Copy the folder

Take lingxling/aws-cost-cleanup from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.