Compares deployed CloudFormation templates with locally synthesized CDK templates to detect drift, validate changes, and ensure consistency before deployment. Use when the user wants to compare CDK output with a deployed stack, check for infrastructure drift, run a pre-deployment validation, audit IAM or security changes, investigate a failing deployment, or perform a 'cdk diff'-style review. Triggered by phrases like 'compare templates', 'check for drift', 'cfn drift', 'stack comparison', 'infrastructure drift detection', 'safe to deploy', or 'what changed in my CDK stack'.
95
93%
Does it follow best practices?
Impact
100%
1.08xAverage score across 5 eval scenarios
Passed
No known issues
{
"context": "Tests whether the agent can properly categorize template differences by risk level and make appropriate deployment recommendations.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Risk categories defined",
"description": "risk-assessment.md defines or lists at least 4 risk categories (Expected, Low, Medium, High, Critical or similar)",
"max_score": 10
},
{
"name": "GitRef as expected",
"description": "The GitRef tag change is categorized as Expected or Low risk (environment-specific metadata)",
"max_score": 10
},
{
"name": "Alarm threshold as medium",
"description": "The alarm threshold change is categorized as Medium risk (requires review)",
"max_score": 12
},
{
"name": "IAM policy as high risk",
"description": "The IAM policy modification is categorized as High risk (requires explicit sign-off)",
"max_score": 15
},
{
"name": "CDK Nag suppression as critical",
"description": "The new CDK Nag suppression is categorized as Critical or High risk (security override)",
"max_score": 15
},
{
"name": "Resource changes assessed",
"description": "The added CloudWatch alarms and removed S3 lifecycle policy are categorized with risk levels",
"max_score": 10
},
{
"name": "Deployment decision present",
"description": "Document includes a clear deployment decision (approve, review, sign-off, or block)",
"max_score": 10
},
{
"name": "Decision matches risk",
"description": "The deployment decision is appropriate for the risk levels found (should require sign-off or block due to IAM/CDK Nag changes)",
"max_score": 10
},
{
"name": "Required actions listed",
"description": "Document lists specific actions required before deployment (e.g., InfoSec approval, stakeholder review)",
"max_score": 8
}
]
}