- Home
- Skills
- DevOps & Cloud
- Infrastructure Drift Auditor
More screenshots
Works with the AI Agents you already use
Infrastructure Drift Auditor
Classify IaC-to-live drift and blast radius before the next infrastructure apply.
$19.99
Infrastructure Drift Auditor
Example session with this skill installed
Audit this supplied Terraform plan before apply. It opens HTTPS ingress from 10.0.0.0/16 to 0.0.0.0/0, creates a target group that evidence says already carries production traffic, renames a worker tag, changes provider-managed ASG desired capacity, recreates a manually decommissioned replica, and leaves the audit-log bucket unchanged. Return a scoped drift register, blast-radius tiers, and the human review order.
- Read your context and instructions
- Compiled the infrastructure drift auditor
Infrastructure Drift Register
Evidence reviewed: six resources in the supplied plan plus the attached notes. No cloud account was queried.
| Resource | Observed change | Risk | Decision |
|---|---|---|---|
| aws_security_group_rule.app_ingress | CIDR widens from 10.0.0.0/16 to 0.0.0.0/0 | CRITICAL | Block apply until the intended public-exposure decision is confirmed. |
| aws_lb_target_group.api_targets | Plan says create; supplied listener evidence says a live target group already receives production traffic | HIGH | Reconcile state/import before create to avoid collision or replacement. |
| aws_instance.worker_node | Name tag changes from worker-prod-01 to worker-manual-rename | MEDIUM | Confirm whether this is approved manual drift or an unintended rename. |
| aws_autoscaling_group.web_asg | desired_capacity moves 4 to 7 while target tracking manages the field | MEDIUM | Separate provider-managed runtime variance from configuration drift. |
| aws_db_instance.replica_old | Plan recreates a replica that ticket #4821 says was intentionally decommissioned | HIGH | Reconcile code and state with the approved deletion before apply. |
| aws_s3_bucket.audit_logs | No change; supplied state and policy agree | CLEAN | Preserve as explicit no-drift evidence. |
Human review order: network exposure → database recreation → live target-group reconciliation → autoscaling ownership → tag intent → unchanged audit bucket.
Scope boundary: classifications cover only the six supplied resources. Approval status and live reality remain unverified unless matching tickets, state, or provider output were supplied.
Connects securely to your tools. The creator never sees your data.
About this skill
Classify the gap between infrastructure-as-code and live cloud reality before the next apply. Infrastructure Drift Auditor parses the Terraform, CloudFormation, Pulumi, state, plan, or live-resource evidence you supply; assigns one evidence-backed drift class per resource; cites the exact block or field; separates intentional from unexplained change; and tiers blast radius without pretending it has cloud access.
You receive a resource-by-resource drift register, unsupported-finding filter, high-risk IAM and network review queue, and a human verification sequence before apply. The package includes the full SKILL.md workflow, drift protocol, structured samples, deterministic classifier, tests, and a six-page PDF buyer guide.
It does not connect to cloud accounts, run terraform apply, certify compliance, or know whether a manual change was approved unless that evidence is supplied.
Analyzes only supplied plans, state, configuration, live-resource exports, and approval evidence. It does not connect to cloud accounts, execute terraform apply, mutate infrastructure, certify compliance, or infer whether a manual change was approved when evidence is missing.
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