Implement policy as code with OPA, Sentinel, and Kyverno. Automate policy enforcement in CI/CD and infrastructure. Use when enforcing compliance through automation.
npx skills add https://github.com/BagelHole/DevOps-Security-Agent-Skills --skill policy-as-code
Automate policy enforcement through code using OPA/Rego, Kyverno, Checkov, and CI/CD integration to prevent compliance violations before they reach production.
# deny_public_s3.rego - Deny S3 buckets with public access
package terraform.aws.s3
import rego.v1
deny contains msg if {
resource := input.resource_changes[_]
resource.type == "aws_s3_bucket"
resource.change.after.acl == "public-read"
msg := sprintf(
"S3 bucket '%s' has public-read ACL. All buckets must be private. [Policy: no-public-s3]",
[resource.address]
)
}
deny contains msg if {
resource := input.resource_changes[_]
resource.type == "aws_s3_bucket"
resource.change.after.acl == "public-read-write"
msg := sprintf(
"S3 bucket '%s' has public-read-write ACL. This is strictly prohibited. [Policy: no-public-s3]",
[resource.address]
)
}
# require_encryption.rego - Require encryption on data stores
package terraform.aws.encryption
import rego.v1
deny contains msg if {
resource := input.resource_changes[_]
resource.type == "aws_db_instance"
not resource.change.after.storage_encrypted
msg := sprintf(
"RDS instance '%s' does not have storage encryption enabled. [Policy: require-rds-encryption]",
[resource.address]
)
}
deny contains msg if {
resource := input.resource_changes[_]
resource.type == "aws_ebs_volume"
not resource.change.after.encrypted
msg := sprintf(
"EBS volume '%s' is not encrypted. [Policy: require-ebs-encryption]",
[resource.address]
)
}
deny contains msg if {
resource := input.resource_changes[_]
resource.type == "aws_s3_bucket"
not has_encryption(resource)
msg := sprintf(
"S3 bucket '%s' does not have default encryption configured. [Policy: require-s3-encryption]",
[resource.address]
)
}
has_encryption(resource) if {
resource.change.after.server_side_encryption_configuration[_]
}
# require_tags.rego - Enforce mandatory tagging
package terraform.aws.tags
import rego.v1
required_tags := {"Environment", "Owner", "CostCenter", "DataClassification"}
deny contains msg if {
resource := input.resource_changes[_]
tags := object.get(resource.change.after, "tags", {})
missing := required_tags - {key | tags[key]}
count(missing) > 0
msg := sprintf(
"Resource '%s' is missing required tags: %v. [Policy: required-tags]",
[resource.address, missing]
)
}
# restrict_regions.rego - Limit resource deployment to approved regions
package terraform.aws.regions
import rego.v1
approved_regions := {"us-east-1", "us-west-2", "eu-west-1"}
deny contains msg if {
resource := input.resource_changes[_]
provider_config := input.configuration.provider_config.aws
region := provider_config.expressions.region.constant_value
not region in approved_regions
msg := sprintf(
"Resource '%s' is in region '%s'. Approved regions: %v. [Policy: approved-regions]",
[resource.address, region, approved_regions]
)
}
# Evaluate OPA policies against Terraform plan
terraform plan -out=tfplan
terraform show -json tfplan > tfplan.json
# Run OPA evaluation
opa eval \
--data policies/ \
--input tfplan.json \
"data.terraform.aws.s3.deny" \
--format pretty
# Use conftest for easier CI integration
conftest test tfplan.json --policy policies/ --output table
# require-labels.yaml - Enforce required labels on all pods
apiVersion: kyverno.io/v1
kind: ClusterPolicy
metadata:
name: require-labels
annotations:
policies.kyverno.io/title: Require Labels
policies.kyverno.io/category: Best Practices
policies.kyverno.io/severity: medium
spec:
validationFailureAction: Enforce
background: true
rules:
- name: check-required-labels
match:
any:
- resources:
kinds:
- Pod
validate:
message: >-
Labels 'app.kubernetes.io/name', 'app.kubernetes.io/version',
and 'team' are required on all Pods.
pattern:
metadata:
labels:
app.kubernetes.io/name: "?*"
app.kubernetes.io/version: "?*"
team: "?*"
---
# disallow-privileged.yaml - Block privileged containers
apiVersion: kyverno.io/v1
kind: ClusterPolicy
metadata:
name: disallow-privileged-containers
annotations:
policies.kyverno.io/title: Disallow Privileged Containers
policies.kyverno.io/category: Pod Security
policies.kyverno.io/severity: high
spec:
validationFailureAction: Enforce
background: true
rules:
- name: deny-privileged
match:
any:
- resources:
kinds:
- Pod
validate:
message: "Privileged containers are not allowed."
pattern:
spec:
containers:
- securityContext:
privileged: "false"
=(initContainers):
- securityContext:
privileged: "false"
---
# require-resource-limits.yaml - Enforce resource limits
apiVersion: kyverno.io/v1
kind: ClusterPolicy
metadata:
name: require-resource-limits
annotations:
policies.kyverno.io/title: Require Resource Limits
policies.kyverno.io/severity: medium
spec:
validationFailureAction: Enforce
background: true
rules:
- name: check-resource-limits
match:
any:
- resources:
kinds:
- Pod
validate:
message: "All containers must have CPU and memory limits defined."
pattern:
spec:
containers:
- resources:
limits:
memory: "?*"
cpu: "?*"
---
# disallow-latest-tag.yaml - Block usage of 'latest' image tag
apiVersion: kyverno.io/v1
kind: ClusterPolicy
metadata:
name: disallow-latest-tag
annotations:
policies.kyverno.io/title: Disallow Latest Tag
policies.kyverno.io/severity: medium
spec:
validationFailureAction: Enforce
background: true
rules:
- name: validate-image-tag
match:
any:
- resources:
kinds:
- Pod
validate:
message: "Images must use a specific tag, not 'latest'."
pattern:
spec:
containers:
- image: "!*:latest & *:*"
---
# restrict-image-registries.yaml - Allow only approved registries
apiVersion: kyverno.io/v1
kind: ClusterPolicy
metadata:
name: restrict-image-registries
annotations:
policies.kyverno.io/title: Restrict Image Registries
policies.kyverno.io/severity: high
spec:
validationFailureAction: Enforce
background: true
rules:
- name: validate-registries
match:
any:
- resources:
kinds:
- Pod
validate:
message: >-
Images must come from approved registries:
123456789012.dkr.ecr.us-east-1.amazonaws.com or ghcr.io/your-org.
pattern:
spec:
containers:
- image: "123456789012.dkr.ecr.*.amazonaws.com/* | ghcr.io/your-org/*"
---
# require-networkpolicy.yaml - Ensure namespaces have NetworkPolicies
apiVersion: kyverno.io/v1
kind: ClusterPolicy
metadata:
name: require-networkpolicy
annotations:
policies.kyverno.io/title: Require Network Policy
policies.kyverno.io/severity: high
spec:
validationFailureAction: Audit
background: true
rules:
- name: check-networkpolicy
match:
any:
- resources:
kinds:
- Deployment
preconditions:
all:
- key: "{{request.object.metadata.namespace}}"
operator: NotIn
value: ["kube-system", "kube-public"]
validate:
message: "A NetworkPolicy must exist in namespace '{{request.object.metadata.namespace}}' before deploying workloads."
deny:
conditions:
all:
- key: "{{request.object.metadata.namespace}}"
operator: AnyNotIn
value: "{{request.object.metadata.namespace}}"
# custom_checks/require_s3_versioning.py
from checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck
from checkov.common.models.enums import CheckResult, CheckCategories
class S3Versioning(BaseResourceCheck):
def __init__(self):
name = "Ensure S3 bucket has versioning enabled"
id = "CUSTOM_S3_001"
supported_resources = ["aws_s3_bucket_versioning"]
categories = [CheckCategories.BACKUP_AND_RECOVERY]
super().__init__(name=name, id=id,
categories=categories,
supported_resources=supported_resources)
def scan_resource_conf(self, conf):
versioning = conf.get("versioning_configuration", [{}])
if isinstance(versioning, list):
versioning = versioning[0] if versioning else {}
status = versioning.get("status", ["Disabled"])
if isinstance(status, list):
status = status[0]
return CheckResult.PASSED if status == "Enabled" else CheckResult.FAILED
check = S3Versioning()
# custom_checks/require_rds_backup.py
from checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck
from checkov.common.models.enums import CheckResult, CheckCategories
class RDSBackupRetention(BaseResourceCheck):
def __init__(self):
name = "Ensure RDS has backup retention of at least 7 days"
id = "CUSTOM_RDS_001"
supported_resources = ["aws_db_instance"]
categories = [CheckCategories.BACKUP_AND_RECOVERY]
super().__init__(name=name, id=id,
categories=categories,
supported_resources=supported_resources)
def scan_resource_conf(self, conf):
retention = conf.get("backup_retention_period", [0])
if isinstance(retention, list):
retention = retention[0]
return CheckResult.PASSED if int(retention) >= 7 else CheckResult.FAILED
check = RDSBackupRetention()
# Run Checkov with custom checks
checkov -d ./terraform \
--framework terraform \
--external-checks-dir ./custom_checks \
--output cli \
--compact
# Run specific check IDs
checkov -d ./terraform \
--check CUSTOM_S3_001,CUSTOM_RDS_001,CKV_AWS_18,CKV_AWS_19
# Generate SARIF output for GitHub Advanced Security integration
checkov -d ./terraform \
--framework terraform \
--output sarif \
--output-file checkov-results.sarif
# Skip specific checks with documented justification
checkov -d ./terraform \
--skip-check CKV_AWS_145 \
--skip-check CKV_AWS_79
# GitHub Actions - Policy enforcement in PR workflow
name: Policy Checks
on:
pull_request:
paths:
- 'terraform/**'
- 'kubernetes/**'
jobs:
terraform-policy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Setup Terraform
uses: hashicorp/setup-terraform@v3
- name: Terraform Init and Plan
working-directory: terraform/
run: |
terraform init -backend=false
terraform plan -out=tfplan
terraform show -json tfplan > tfplan.json
- name: OPA Policy Check
uses: open-policy-agent/setup-opa@v2
with:
version: latest
- run: |
RESULTS=$(opa eval \
--data policies/ \
--input terraform/tfplan.json \
--format json \
"data.terraform" | jq '.result[0].expressions[0].value')
DENY_COUNT=$(echo "$RESULTS" | jq '[.. | .deny? // empty | .[] ] | length')
if [ "$DENY_COUNT" -gt 0 ]; then
echo "::error::Policy violations found:"
echo "$RESULTS" | jq '.. | .deny? // empty | .[]'
exit 1
fi
- name: Checkov Scan
uses: bridgecrewio/checkov-action@v12
with:
directory: terraform/
framework: terraform
output_format: cli,sarif
output_file_path: console,checkov-results.sarif
soft_fail: false
external_checks_dirs: custom_checks/
- name: Upload SARIF
if: always()
uses: github/codeql-action/upload-sarif@v3
with:
sarif_file: checkov-results.sarif
kubernetes-policy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Install Kyverno CLI
run: |
curl -LO https://github.com/kyverno/kyverno/releases/latest/download/kyverno-cli_linux_amd64.tar.gz
tar -xzf kyverno-cli_linux_amd64.tar.gz
sudo mv kyverno /usr/local/bin/
- name: Test Kyverno Policies
run: |
kyverno apply policies/kyverno/ \
--resource kubernetes/manifests/ \
--detailed-results \
--output-format table
- name: Conftest Kubernetes Manifests
uses: open-policy-agent/conftest-action@v2
with:
files: kubernetes/manifests/
policy: policies/kubernetes/
exception_workflow:
request:
fields:
- policy_id: "Which policy needs an exception"
- resource: "Specific resource requiring exception"
- justification: "Business reason for the exception"
- compensating_controls: "Alternative mitigations in place"
- duration: "Temporary (with expiry) or permanent"
- requestor: "Person requesting"
- approver: "Security team member who approved"
approval_process:
1: "Requestor submits exception with justification"
2: "Security team reviews and assesses risk"
3: "Compensating controls verified"
4: "Exception approved or denied with rationale"
5: "Exception documented in registry"
6: "Automated enforcement updated to allow exception"
enforcement:
opa: |
# Exception list loaded as data
# policies/exceptions.json
# {"exceptions": [{"resource": "aws_s3_bucket.public_website", "policy": "no-public-s3", "expires": "2025-06-01"}]}
kyverno: |
# Use Kyverno PolicyException resource
apiVersion: kyverno.io/v2beta1
kind: PolicyException
metadata:
name: allow-public-website
namespace: web
spec:
exceptions:
- policyName: disallow-privileged-containers
ruleNames:
- deny-privileged
match:
any:
- resources:
kinds:
- Pod
names:
- legacy-app-*
review_schedule:
- Review all active exceptions quarterly
- Expire temporary exceptions automatically
- Re-justify permanent exceptions annually
- Track exception count trends as a security metric
# Test OPA policies with mock input
mkdir -p policies/tests
# Create test input
cat > policies/tests/public_bucket_test.json <<'EOF'
{
"resource_changes": [{
"address": "aws_s3_bucket.test",
"type": "aws_s3_bucket",
"change": {
"after": {"acl": "public-read"}
}
}]
}
EOF
# Run test
opa eval --data policies/ --input policies/tests/public_bucket_test.json \
"data.terraform.aws.s3.deny" --format pretty
# Should output the deny message
# OPA unit tests
cat > policies/tests/s3_test.rego <<'EOF'
package terraform.aws.s3_test
import rego.v1
import data.terraform.aws.s3
test_deny_public_bucket if {
result := s3.deny with input as {"resource_changes": [{"address": "test", "type": "aws_s3_bucket", "change": {"after": {"acl": "public-read"}}}]}
count(result) > 0
}
test_allow_private_bucket if {
result := s3.deny with input as {"resource_changes": [{"address": "test", "type": "aws_s3_bucket", "change": {"after": {"acl": "private"}}}]}
count(result) == 0
}
EOF
opa test policies/ -v
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.
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.
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).
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).
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).
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.
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
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.
Take bagelhole/policy-as-code from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.