mirror of
https://github.com/wshobson/agents.git
synced 2026-03-18 17:47:16 +00:00
3802bca865
Plugin Scope Improvements: - Remove language-specialists plugin (not task-focused) - Split specialized-domains into 5 focused plugins: * blockchain-web3 - Smart contract development only * quantitative-trading - Financial modeling and trading only * payment-processing - Payment gateway integration only * game-development - Unity and Minecraft only * accessibility-compliance - WCAG auditing only - Split business-operations into 3 focused plugins: * business-analytics - Metrics and reporting only * hr-legal-compliance - HR and legal docs only * customer-sales-automation - Support and sales workflows only - Fix infrastructure-devops scope: * Remove database concerns (db-migrate, database-admin) * Remove observability concerns (observability-engineer) * Move slo-implement to incident-response * Focus purely on container orchestration (K8s, Docker, Terraform) - Fix customer-sales-automation scope: * Remove content-marketer (unrelated to customer/sales workflows) Marketplace Statistics: - Total plugins: 27 (was 22) - Tool coverage: 100% (42/42 tools referenced) - Fat plugins removed: 3 (language-specialists, specialized-domains, business-operations) - All plugins now have clear, focused tasks Model Migration: - Migrate all 42 tools from claude-sonnet-4-0/opus-4-1 to model: sonnet - Migrate all 15 workflows from claude-opus-4-1 to model: sonnet - Use short model syntax consistent with agent files Documentation Updates: - Update README.md with refined plugin structure - Update plugin descriptions to be task-focused - Remove anthropomorphic and marketing language - Improve category organization (now 16 distinct categories) Ready for October 9, 2025 @ 9am PST launch
85 lines
4.3 KiB
Markdown
85 lines
4.3 KiB
Markdown
---
|
|
model: sonnet
|
|
---
|
|
|
|
Respond to production incidents with coordinated agent expertise for rapid resolution:
|
|
|
|
[Extended thinking: This workflow handles production incidents with urgency and precision. Multiple specialized agents work together to identify root causes, implement fixes, and prevent recurrence.]
|
|
|
|
## Phase 1: Immediate Response
|
|
|
|
### 1. Incident Assessment
|
|
- Use Task tool with subagent_type="incident-responder"
|
|
- Prompt: "URGENT: Assess production incident: $ARGUMENTS. Determine severity, impact, and immediate mitigation steps. Time is critical."
|
|
- Output: Incident severity, impact assessment, immediate actions
|
|
|
|
### 2. Initial Troubleshooting
|
|
- Use Task tool with subagent_type="devops-troubleshooter"
|
|
- Prompt: "Investigate production issue: $ARGUMENTS. Check logs, metrics, recent deployments, and system health. Identify potential root causes."
|
|
- Output: Initial findings, suspicious patterns, potential causes
|
|
|
|
## Phase 2: Root Cause Analysis
|
|
|
|
### 3. Deep Debugging
|
|
- Use Task tool with subagent_type="debugger"
|
|
- Prompt: "Debug production issue: $ARGUMENTS using findings from initial investigation. Analyze stack traces, reproduce issue if possible, identify exact root cause."
|
|
- Output: Root cause identification, reproduction steps, debug analysis
|
|
|
|
### 4. Performance Analysis (if applicable)
|
|
- Use Task tool with subagent_type="performance-engineer"
|
|
- Prompt: "Analyze performance aspects of incident: $ARGUMENTS. Check for resource exhaustion, bottlenecks, or performance degradation."
|
|
- Output: Performance metrics, resource analysis, bottleneck identification
|
|
|
|
### 5. Database Investigation (if applicable)
|
|
- Use Task tool with subagent_type="database-optimizer"
|
|
- Prompt: "Investigate database-related aspects of incident: $ARGUMENTS. Check for locks, slow queries, connection issues, or data corruption."
|
|
- Output: Database health report, query analysis, data integrity check
|
|
|
|
## Phase 3: Resolution Implementation
|
|
|
|
### 6. Fix Development
|
|
- Use Task tool with subagent_type="backend-architect"
|
|
- Prompt: "Design and implement fix for incident: $ARGUMENTS based on root cause analysis. Ensure fix is safe for immediate production deployment."
|
|
- Output: Fix implementation, safety analysis, rollout strategy
|
|
|
|
### 7. Emergency Deployment
|
|
- Use Task tool with subagent_type="deployment-engineer"
|
|
- Prompt: "Deploy emergency fix for incident: $ARGUMENTS. Implement with minimal risk, include rollback plan, and monitor deployment closely."
|
|
- Output: Deployment execution, rollback procedures, monitoring setup
|
|
|
|
## Phase 4: Stabilization and Prevention
|
|
|
|
### 8. System Stabilization
|
|
- Use Task tool with subagent_type="devops-troubleshooter"
|
|
- Prompt: "Stabilize system after incident fix: $ARGUMENTS. Monitor system health, clear any backlogs, and ensure full recovery."
|
|
- Output: System health report, recovery metrics, stability confirmation
|
|
|
|
### 9. Security Review (if applicable)
|
|
- Use Task tool with subagent_type="security-auditor"
|
|
- Prompt: "Review security implications of incident: $ARGUMENTS. Check for any security breaches, data exposure, or vulnerabilities exploited."
|
|
- Output: Security assessment, breach analysis, hardening recommendations
|
|
|
|
## Phase 5: Post-Incident Activities
|
|
|
|
### 10. Monitoring Enhancement
|
|
- Use Task tool with subagent_type="devops-troubleshooter"
|
|
- Prompt: "Enhance monitoring to prevent recurrence of: $ARGUMENTS. Add alerts, improve observability, and set up early warning systems."
|
|
- Output: New monitoring rules, alert configurations, observability improvements
|
|
|
|
### 11. Test Coverage
|
|
- Use Task tool with subagent_type="test-automator"
|
|
- Prompt: "Create tests to prevent regression of incident: $ARGUMENTS. Include unit tests, integration tests, and chaos engineering scenarios."
|
|
- Output: Test implementations, regression prevention, chaos tests
|
|
|
|
### 12. Documentation
|
|
- Use Task tool with subagent_type="incident-responder"
|
|
- Prompt: "Document incident postmortem for: $ARGUMENTS. Include timeline, root cause, impact, resolution, and lessons learned. No blame, focus on improvement."
|
|
- Output: Postmortem document, action items, process improvements
|
|
|
|
## Coordination Notes
|
|
- Speed is critical in early phases - parallel agent execution where possible
|
|
- Communication between agents must be clear and rapid
|
|
- All changes must be safe and reversible
|
|
- Document everything for postmortem analysis
|
|
|
|
Production incident: $ARGUMENTS |