Templates
DevOps Templates

DevOps Templates

Pre-built workflow templates for code review, incident analysis, deployment validation, and infrastructure auditing.

code-review-v1

AI Code Review -- Analyzes code changes for security vulnerabilities, performance issues, and best practice violations.

PropertyValue
Steps3 (parse-diff, analyze-issues, review-report)
ModelsSonnet (all steps)
HITLNone (automated review)
Est. Cost$0.025 per execution
Est. Duration15-30 seconds

Input Schema

{
  diff: string;              // Required: git diff output
  language?: string;         // Auto-detected if not specified
  framework?: string;        // e.g., 'express', 'react', 'django'
  focusAreas?: ('security' | 'performance' | 'style' | 'testing' | 'all')[];
  severity?: 'strict' | 'moderate' | 'lenient'; // Default: 'moderate'
}

Usage

# Pipe git diff directly
git diff origin/main...HEAD | devteam templates deploy code-review-v1 \
  --input diff=@- \
  --input language="typescript" \
  --input framework="express" \
  --input 'focusAreas=["security","performance"]' \
  --wait

Output Format

## Code Review Summary
 
**Files Changed:** 5
**Issues Found:** 3 (1 high, 1 medium, 1 low)
 
### HIGH: SQL Injection in user-service.ts:42
```typescript
// Current (vulnerable)
const query = `SELECT * FROM users WHERE id = ${req.params.id}`;
 
// Recommended (parameterized)
const query = 'SELECT * FROM users WHERE id = $1';
const result = await db.query(query, [req.params.id]);

MEDIUM: Missing error boundary in Dashboard.tsx:15

...


---

## incident-analysis-v1

**Incident Post-Mortem Analysis** -- Analyzes incident data, identifies root cause, and generates a post-mortem report.

| Property | Value |
|----------|-------|
| Steps | 4 (parse-timeline, root-cause-analysis, impact-assessment, postmortem-report) |
| Models | Sonnet (parse, impact), Opus (root-cause, report) |
| HITL | Enabled on `root-cause-analysis` (threshold: 0.80) |
| Est. Cost | $0.032 per execution |
| Est. Duration | 25-50 seconds |

### Input Schema

```typescript
{
  incidentDescription: string;   // Required: what happened
  timeline?: string;             // Chronological event log
  logs?: string;                 // Relevant application/system logs
  metrics?: string;              // Performance metrics during incident
  affectedServices?: string[];   // List of impacted services
  severity: 'SEV1' | 'SEV2' | 'SEV3' | 'SEV4';
  duration?: string;             // e.g., "45 minutes"
}

Usage

const result = await client.deployTemplate('incident-analysis-v1', {
  input: {
    incidentDescription: 'API latency spike to 30s, 50% of requests timing out',
    timeline: `
      14:00 - Deployment of v2.4.1 started
      14:05 - Deployment complete
      14:12 - Latency alerts triggered (p99 > 5s)
      14:15 - 50% error rate detected
      14:20 - Rollback initiated
      14:25 - Service recovered
    `,
    logs: logFileContent,
    affectedServices: ['api-gateway', 'user-service', 'payment-service'],
    severity: 'SEV1',
    duration: '25 minutes',
  },
  wait: true,
});

infra-audit-v1

Infrastructure Audit -- Reviews infrastructure configuration for security, cost optimization, and reliability.

PropertyValue
Steps5 (collect-config, security-review, cost-analysis, reliability-check, audit-report)
ModelsSonnet (all analysis steps), Opus (audit-report)
HITLEnabled on audit-report (threshold: 0.85)
Est. Cost$0.048 per execution
Est. Duration40-80 seconds

Input Schema

{
  infrastructure: string;        // Required: description or config export
  provider: 'aws' | 'gcp' | 'azure' | 'multi-cloud';
  configFiles?: string[];        // Terraform, CloudFormation, Kubernetes YAML
  monthlySpend?: string;         // Current monthly cloud spend
  complianceRequirements?: string[]; // e.g., ['SOC2', 'HIPAA', 'PCI-DSS']
  auditScope?: ('security' | 'cost' | 'reliability' | 'performance' | 'all')[];
}

Usage

devteam templates deploy infra-audit-v1 \
  --input infrastructure=@./terraform-state.json \
  --input provider="aws" \
  --input monthlySpend="\$12,000" \
  --input 'complianceRequirements=["SOC2"]' \
  --input 'auditScope=["security","cost"]' \
  --wait

Output Includes

  • Security findings ranked by severity (CRITICAL, HIGH, MEDIUM, LOW)
  • Cost optimization opportunities with estimated savings
  • Reliability gaps and single points of failure
  • Compliance mapping against specified standards
  • Prioritized remediation roadmap

For infrastructure audits, provide as much configuration detail as possible. Terraform state files, Kubernetes manifests, and cloud provider exports yield the most accurate results.

Next Steps