- Home
- Skills
- DevOps & Cloud
- Enterprise Cloud Cost Optimization & Architecture Compliance
Works with the AI Agents you already use
Enterprise Cloud Cost Optimization & Architecture Compliance
This skill acts as a pre-emptive cost-control and compliance checkpoint for multi-cloud and Kubernetes environments.
$5
Enterprise Cloud Cost Optimization & Architecture Compliance
Example session with this skill installed
Run a FinOps audit on this Terraform snippet for our new HealthTech patient intake pipeline in our Dev environment:
resource "aws_s3_bucket" "patient_records" {
bucket = "healthtech-patient-intake-records-dev"
}
resource "aws_ebs_volume" "app_storage" {
availability_zone = "us-east-1a"
size = 500
type = "gp2"
}
resource "aws_instance" "pipeline_processor" {
ami = "ami-0c55b159cbfafe1f0"
instance_type = "m5.2xlarge"
tags = {
Name = "healthtech-intake-processor-dev"
}
}
- Read your context and instructions
- Compiled the enterprise cloud cost
Here's the FinOps audit for the patient intake pipeline (Dev environment, HealthTech context detected via "patient" keyword — HIPAA/PHI safeguards applied).
Findings Summary
| # | Resource | Issue | Impact |
|---|---|---|---|
| 1 | aws_s3_bucket.patient_records | No FinOps tags (Owner/CostCenter/Environment) | High |
| 2 | aws_s3_bucket.patient_records | No lifecycle policy — HealthTech safeguard requires Deep Archive transition for patient records >365 days | High |
| 3 | aws_ebs_volume.app_storage | Legacy gp2 volume type (500GB) — should be gp3 | Medium |
| 4 | aws_ebs_volume.app_storage | No FinOps tags | High |
| 5 | aws_instance.pipeline_processor | m5.2xlarge in Dev violates Non-Prod Restriction (burstable tiers only) | High |
| 6 | aws_instance.pipeline_processor | Missing CostCenter/Owner tags and Schedule: OffHours tag for nightly shutdown | High |
Remediation Diffs
1 & 2 — S3 bucket: tags + lifecycle policy
resource "aws_s3_bucket" "patient_records" {
bucket = "healthtech-patient-intake-records-dev"
+ tags = {
+ Owner = "TBD"
+ CostCenter = "TBD"
+ Environment = "dev"
+ }
}
+
+resource "aws_s3_bucket_lifecycle_configuration" "patient_records" {
+ bucket = aws_s3_bucket.patient_records.id
+
+ rule {
+ id = "healthtech-deep-archive-transition"
+ status = "Enabled"
+
+ transition {
+ days = 90
+ storage_class = "STANDARD_IA"
+ }
+
+ transition {
+ days = 365
+ storage_class = "DEEP_ARCHIVE"
+ }
+ }
+}
3 & 4 — EBS volume: gp3 + tags
resource "aws_ebs_volume" "app_storage" {
availability_zone = "us-east-1a"
size = 500
- type = "gp2"
+ type = "gp3"
+ tags = {
+ Owner = "TBD"
+ CostCenter = "TBD"
+ Environment = "dev"
+ }
}
5 & 6 — EC2 instance: right-size + tags + off-hours schedule
resource "aws_instance" "pipeline_processor" {
ami = "ami-0c55b159cbfafe1f0"
- instance_type = "m5.2xlarge"
+ instance_type = "t3.xlarge"
tags = {
- Name = "healthtech-intake-processor-dev"
+ Name = "healthtech-intake-processor-dev"
+ Owner = "TBD"
+ CostCenter = "TBD"
+ Environment = "dev"
+ Schedule = "OffHours"
}
}
Notes & Open Questions
Instance right-sizing: I defaulted m5.2xlarge → t3.xlarge (burstable, similar vCPU/RAM) since this is Dev. I don't have Datadog/CloudWatch utilization data — if this pipeline has sustained CPU-intensive workloads even in Dev, confirm before downsizing further, or a burst-credit-exhaustion issue could actually cost more in throttled reprocessing time.
TBDtag values: fill in actualOwner/CostCentervalues — I can't infer your org's cost-allocation taxonomy.- Dollar estimates skipped per policy (no pricing CLI active) — impact is graded qualitatively above.
Want me to write these corrected files to your workspace?
Connects securely to your tools. The creator never sees your data.
About this skill
This skill acts as a pre-emptive cost-control and compliance checkpoint for multi-cloud and Kubernetes environments. By scanning IaC (Terraform, Bicep) or K8s manifests, it identifies orphaned infrastructure, uncapped compute limits, and storage waste while automatically prescribing exact code diffs to patch the violations. It prevents developers from deploying unoptimized cloud resources while maintaining strict industry-specific compliance requirements.
Cannot provide exact dollar savings without an active pricing CLI connection. Requires manual confirmation for K8s request downsizing if historical metrics are unavailable.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected