{
  "markdown": "# 📊 DatadOps - Intelligent Monitoring Workflows\n\n**Advanced Datadog workflows for Claude Code** - Transforms raw monitoring data into actionable insights through intelligent DatadOps automation.\n\n## 🎬 Demo\n\nhttps://github.com/user-attachments/assets/d7403866-67db-448b-8fee-f58beeed79fc\n\n## ✨ What is DatadOps?\n\nA **lightweight Claude Code plugin** that bundles the [official Datadog MCP server](https://docs.datadoghq.com/bits_ai/mcp_server/) configuration and adds intelligent workflows on top of it. The official server provides access to raw Datadog data; DatadOps orchestrates that data into complete operational workflows.\n\n### 🆚 Official MCP Server vs DatadOps\n\n| Aspect | Official Datadog MCP | DatadOps |\n|--------|---------------------|-------------------|\n| **Purpose** | Raw data access | Intelligent workflows |\n| **Usage** | `search_datadog_logs`, `get_datadog_metric` | *\"Investigate payment service issues\"* |\n| **Output** | JSON data | Actionable insights + recommendations |\n| **Expertise** | Requires Datadog knowledge | Guides non-experts |\n| **Scope** | Individual queries | End-to-end scenarios |\n\n## 🚀 Key Features\n\n### 🚨 **Incident Response Automation**\n- **Multi-signal correlation**: Automatically correlates logs, metrics, APM traces\n- **Timeline reconstruction**: Maps events, deployments, and failures  \n- **Impact assessment**: Quantifies customer and business impact\n- **Actionable remediation**: Specific next steps with confidence levels\n\n### 🔍 **Performance Investigation**\n- **Bottleneck identification**: Pinpoints root causes across the stack\n- **Resource correlation**: Links performance to infrastructure constraints\n- **Optimization recommendations**: Specific improvements with impact estimates\n- **Trend analysis**: Historical context and pattern recognition\n\n### 📋 **Deployment Validation**\n- **Before/after comparison**: Statistical analysis of deployment impact\n- **Regression detection**: Automated identification of performance degradations\n- **Rollback recommendations**: Data-driven go/no-go decisions\n- **Health scoring**: Quantified deployment success metrics\n\n### 🩺 **Service Health Dashboards**\n- **Overall health scoring**: 0-100 health scores with component breakdown\n- **Proactive alerting**: Early warning before customer impact\n- **Dependency mapping**: Service relationship health analysis\n- **Executive reporting**: Business-friendly health summaries\n\n## 🎯 Perfect For\n\n### **SRE/DevOps Teams**\n- Faster incident response (30-minute investigations → 5 minutes)\n- Standardized troubleshooting procedures\n- Automated deployment validation\n- Proactive performance optimization\n\n### **Development Teams**\n- Performance bottleneck identification without deep Datadog expertise\n- Deployment confidence through automated health checks\n- Quick service health assessment\n- Integration with CI/CD pipelines\n\n### **Management & Product**\n- Service health visibility in business terms\n- Impact assessment for incidents\n- Performance trend reporting\n- Resource optimization ROI\n\n## 📊 Usage Examples\n\n### Incident Response\n```\nUser: \"Payment service is returning 500 errors. Help me investigate.\"\n\nDatadOps Response:\n🚨 INCIDENT ANALYSIS - Payment Service\n\nSEVERITY: HIGH (Customer Impact Detected)\nDURATION: 23 minutes (since 14:37 UTC)\n\nROOT CAUSE ANALYSIS:\n• Database connection pool exhaustion (95% utilization)\n• Spike in payment processing requests (+300% vs baseline)\n• Payment gateway API latency increased to 2.4s (baseline: 200ms)\n\nIMMEDIATE ACTIONS:\n1. Scale payment service to 6 instances (currently 3)\n2. Increase DB connection pool from 20→40\n3. Enable circuit breaker for payment gateway\n\nIMPACT:\n• ~1,200 affected transactions\n• Payment success rate: 45% (baseline: 99.2%)\n• Estimated revenue impact: $15K/hour\n\nMONITORING:\n• payment.success_rate < 95%: Page oncall\n• db.connections > 90%: Auto-scale\n```\n\n### Performance Investigation\n```\nUser: \"Checkout service is slow. What's the bottleneck?\"\n\nDatadOps Response:\n🔍 PERFORMANCE ANALYSIS - Checkout Service\n\nPERFORMANCE DEGRADATION: 340ms → 1.2s (P95 latency)\n\nBOTTLENECK BREAKDOWN:\n1. 🥇 Database queries: 420ms (35% of total)\n   - Order validation: 180ms (missing index on user_id)\n   - Inventory check: 240ms (N+1 query pattern)\n\n2. 🥈 External API calls: 380ms (32% of total)\n   - Payment gateway: 280ms (network latency)\n   - Inventory service: 100ms (within SLA)\n\n3. 🥉 Application logic: 260ms (22% of total)\n   - Price calculation: 180ms (inefficient algorithm)\n\nOPTIMIZATION RECOMMENDATIONS:\n• HIGH IMPACT: Add index on orders(user_id) → -180ms\n• MEDIUM IMPACT: Batch inventory queries → -150ms  \n• LOW IMPACT: Cache price calculations → -100ms\n\nESTIMATED IMPROVEMENT: 1.2s → 590ms (51% faster)\n```\n\n### Deployment Health Check\n```\nUser: \"Validate the checkout-service v2.1.4 deployment.\"\n\nDatadOps Response:\n📋 DEPLOYMENT HEALTH - Checkout Service v2.1.4\n\nOVERALL HEALTH SCORE: 92/100 ✅ HEALTHY\n\nMETRICS COMPARISON (30min post vs baseline):\n✅ Success Rate: 99.1% → 99.3% (+0.2%)\n✅ P95 Latency: 280ms → 260ms (-7%)\n✅ Error Rate: 0.8% → 0.5% (-37%)\n⚠️  CPU Usage: 45% → 65% (+44%)\n\nPERFORMANCE IMPACT:\n• Response times improved across all percentiles\n• Memory usage stable (+2%)\n• No new error patterns detected\n• Database performance unchanged\n\nRECOMMENDATIONS:\n✅ Continue deployment - performance improved\n⚠️  Monitor CPU usage - approaching 70% threshold\n📈 Consider auto-scaling trigger adjustment\n\nNEXT CHECKPOINT: Monitor for 2 hours, validate at high traffic\n```\n\n## 🛠 Installation\n\n### 1. Install DatadOps Plugin\n```bash\nclaude plugin install datadops\n```\n\nThis installs the plugin and its bundled Datadog MCP configuration.\nIf you install or update the plugin during an active Claude Code session, run `/reload-plugins`.\n\n### 2. Authenticate with Datadog\n1. Open Claude Code\n2. Type `/mcp`\n3. Select `datadog` → Authenticate\n4. Complete the OAuth flow in your browser\n\n### 3. Test Installation\n```\nAsk Claude: \"Give me a health overview of production services\"\n```\n\nOr invoke the skill directly:\n```\n/datadops:service-health-overview production services\n```\n\n[📖 **Detailed Installation Guide**](setup/installation-guide.md)\n\n## 🎮 Skills Overview\n\n| Skill | Trigger Phrases | Time to Resolution |\n|-------|----------------|-------------------|\n| **incident-response** | \"investigate incident\", \"service down\", \"production issues\" | 2-5 minutes |\n| **performance-investigation** | \"performance issue\", \"slow response\", \"bottleneck\" | 3-7 minutes |\n| **deployment-health-check** | \"validate deployment\", \"check release\" | 1-3 minutes |\n| **service-health-overview** | \"health check\", \"service status\", \"overview\" | 30-60 seconds |\n\n## 🏗 Architecture\n\n```\n┌─────────────────┐    ┌──────────────────┐    ┌─────────────────┐\n│                 │    │                  │    │                 │\n│  Claude Code    │◄──►│    DatadOps      │◄──►│  Datadog MCP    │\n│                 │    │  Plugin          │    │  Server         │\n│  (User Query)   │    │  (Workflows)     │    │  (Raw Data)     │\n└─────────────────┘    └──────────────────┘    └─────────────────┘\n                                ▲                         ▲\n                                │                         │\n                       Orchestrates 15-20            Fetches from\n                       MCP tools into               Official Datadog\n                       complete workflows                API\n```\n\n## 📈 Impact Metrics\n\n**Before DatadOps:**\n- 30+ minutes per incident investigation\n- Manual correlation across multiple Datadog pages\n- Inconsistent troubleshooting approaches\n- High expertise barrier for non-SRE teams\n\n**After DatadOps:**\n- < 5 minutes for comprehensive incident analysis\n- Automated multi-signal correlation\n- Standardized investigation workflows  \n- Accessible to all team members\n\n## 🤝 Contributing\n\n### Adding New Skills\n\n1. **Identify workflow gap**: What manual process takes > 10 minutes?\n2. **Map MCP tools needed**: Which official Datadog MCP tools are required?\n3. **Define success criteria**: What constitutes a successful workflow outcome?\n4. **Create skill template**: Follow existing skill structure\n5. **Add test cases**: Include realistic scenarios and expected outcomes\n\n### Skill Template\n\n```markdown\n---\nname: your-skill-name\ndescription: Brief description with trigger conditions\ncompatibility:\n  tools: [datadog]\n  dependencies: [list_of_required_mcp_tools]\n---\n\n# Your Skill Name\n\n## Capabilities\n- What this skill accomplishes\n- Key value propositions\n\n## Usage Examples\n- Realistic user prompts\n- Expected workflow outputs\n\n## Success Metrics\n- Time to resolution targets\n- Accuracy/completeness measures\n```\n\n## 📄 License\n\nMIT License - Use freely, contribute back improvements.\n\n## 🔗 Related Projects\n\n- [Official Datadog MCP Server](https://docs.datadoghq.com/bits_ai/mcp_server/)\n- [Claude Code Plugins](https://claude.com/plugins)\n- [Model Context Protocol](https://modelcontextprotocol.io/)\n\n## 🔎 Validation\n\nRun the local smoke test before publishing plugin changes:\n\n```bash\npython3 scripts/smoke_test.py\n```\n\n---\n\n**🚀 Ready to transform your Datadog monitoring into intelligent workflows?**\n\n[📖 Get Started](setup/installation-guide.md) • [🎯 View Test Cases](test-cases.json) • [💡 Request Features](https://github.com/your-repo/issues)\n",
  "bytes": 9318,
  "sha": "b5c385c5a4c2bfd1e503d2074f2188f43db25513446ccb5f71dd35a8a975ca18",
  "repo_slug": "ahmidbbc/datadops",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_ahmidbbc_datadops_datadops_935b9894/readme"
}