Skip to main content
command CX Codex

incident-response · ormus-solutions — Claude Code command for incident response

The incident-response command coordinates incident triage, investigation, mitigation, and recovery. Give it an incident description to start a staged response.

MIT ★ 126 updated 2026-10-04

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code
/plugin install incident-response@libreuiux
Open on GitHub

What incident-response does

incident-response divides the work into phases and assigns tasks to specialist subagents through the Task tool. It begins by classifying severity, identifying affected services, and assessing user impact. It then gathers monitoring signals and suggests immediate actions such as rolling back a recent release or disabling a feature flag.

The workflow brings in subagents for debugging, security review, and performance analysis. After investigating the cause, it moves on to a fix, deployment, and stakeholder communication. Its observability checks name OpenTelemetry, Prometheus, and Grafana, among other systems. Findings from earlier phases feed into later ones, so a clear incident description gives the agents a better starting point.

What it helps with

  • classify an outage and assess its user impact
  • correlate metrics, traces, and error logs
  • trace a failure to its cause and dependencies
  • plan a fix with validation and rollback steps
  • prepare updates for engineers and stakeholders

Example prompts for the agent

  • Investigate this incident: API errors rose after the latest release, especially on authentication requests.
  • Triage this outage: the service is unavailable; assess user impact and suggest immediate mitigation.

How to install incident-response

1Plugin marketplace

/plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code
/plugin install incident-response@libreuiux

2Manually: put the files in place

.claude/commands/incident-response.md

Call it with /incident-response. For all projects use ~/.claude/commands/

Questions about incident-response

How do I install incident-response in Claude Code?

Run /plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code in Claude Code, then run /plugin install incident-response@libreuiux.

What does incident-response do?

It coordinates an incident workflow that covers severity assessment, observability checks, root-cause investigation, mitigation, fixes, and communication.

Which observability systems does the command check?

The workflow names OpenTelemetry and Jaeger for tracing, Prometheus, Grafana, and DataDog for metrics, plus ELK and Splunk for logs.

Source text

incident-response.md · MIT
---
description: "Coordinate incident response: triage, investigation, mitigation, and postmortem"
argument-hint: "[incident description]"
---

Orchestrate multi-agent incident response with modern SRE practices for rapid resolution and learning:

[Extended thinking: This workflow implements a comprehensive incident command system (ICS) following modern SRE principles. Multiple specialized agents collaborate through defined phases: detection/triage, investigation/mitigation, communication/coordination, and resolution/postmortem. The workflow emphasizes speed without sacrificing accuracy, maintains clear communication channels, and ensures every incident becomes a learning opportunity through blameless postmortems and systematic improvements.]

## Configuration

### Severity Levels
- **P0/SEV-1**: Complete outage, security breach, data loss - immediate all-hands response
- **P1/SEV-2**: Major degradation, significant user impact - rapid response required
- **P2/SEV-3**: Minor degradation, limited impact - standard response
- **P3/SEV-4**: Cosmetic issues, no user impact - scheduled resolution

### Incident Types
- Performance degradation
- Service outage
- Security incident
- Data integrity issue
- Infrastructure failure
- Third-party service disruption

## Phase 1: Detection & Triage

### 1. Incident Detection and Classification
- Use Task tool with subagent_type="incident-responder"
- Prompt: "URGENT: Detect and classify incident: $ARGUMENTS. Analyze alerts from PagerDuty/Opsgenie/monitoring. Determine: 1) Incident severity (P0-P3), 2) Affected services and dependencies, 3) User impact and business risk, 4) Initial incident command structure needed. Check error budgets and SLO violations."
- Output: Severity classification, impact assessment, incident command assignments, SLO status
- Context: Initial alerts, monitoring dashboards, recent changes

### 2. Observability Analysis
- Use Task tool with subagent_type="observability-monitoring::observability-engineer"
- Prompt: "Perform rapid observability sweep for incident: $ARGUMENTS. Query: 1) Distributed tracing (OpenTelemetry/Jaeger), 2) Metrics correlation (Prometheus/Grafana/DataDog), 3) Log aggregation (ELK/Splunk), 4) APM data, 5) Real User Monitoring. Identify anomalies, error patterns, and service degradation points."
- Output: Observability findings, anomaly detection, service health matrix, trace analysis
- Context: Severity level from step 1, affected services

### 3. Initial Mitigation
- Use Task tool with subagent_type="incident-responder"
- Prompt: "Implement immediate mitigation for P$SEVERITY incident: $ARGUMENTS. Actions: 1) Traffic throttling/rerouting if needed, 2) Feature flag disabling for affected features, 3) Circuit breaker activation, 4) Rollback assessment for recent deployments, 5) Scale resources if capacity-related. Prioritize user experience restoration."
- Output: Mitigation actions taken, temporary fixes applied, rollback decisions
- Context: Observability findings, severity classification

## Phase 2: Investigation & Root Cause Analysis

### 4. Deep System Debugging
- Use Task tool with subagent_type="error-debugging::debugger"
- Prompt: "Conduct deep debugging for incident: $ARGUMENTS using observability data. Investigate: 1) Stack traces and error logs, 2) Database query performance and locks, 3) Network latency and timeouts, 4) Memory leaks and CPU spikes, 5) Dependency failures and cascading errors. Apply Five Whys analysis."
- Output: Root cause identification, contributing factors, dependency impact map
- Context: Observability analysis, mitigation status

### 5. Security Assessment
- Use Task tool with subagent_type="security-scanning::security-auditor"
- Prompt: "Assess security implications of incident: $ARGUMENTS. Check: 1) DDoS attack indicators, 2) Authentication/authorization failures, 3) Data exposure risks, 4) Certificate issues, 5) Suspicious access patterns. Review WAF logs, security groups, and audit trails."
- Output: Security assessment, breach analysis, vulnerability identification
- Context: Root cause findings, system logs

### 6. Performance Engineering Analysis
- Use Task tool with subagent_type="application-performance::performance-engineer"
- Prompt: "Analyze performance aspects of incident: $ARGUMENTS. Examine: 1) Resource utilization patterns, 2) Query optimization opportunities, 3) Caching effectiveness, 4) Load balancer health, 5) CDN performance, 6) Autoscaling triggers. Identify bottlenecks and capacity issues."
- Output: Performance bottlenecks, resource recommendations, optimization opportunities
- Context: Debug findings, current mitigation state

## Phase 3: Resolution & Recovery

### 7. Fix Implementation
- Use Task tool with subagent_type="backend-development::backend-architect"
- Prompt: "Design and implement production fix for incident: $ARGUMENTS based on root cause. Requirements: 1) Minimal viable fix for rapid deployment, 2) Risk assessment and rollback capability, 3) Staged rollout plan with monitoring, 4) Validation criteria and health checks. Consider both immediate fix and long-term solution."
- Output: Fix implementation, deployment strategy, validation plan, rollback procedures
- Context: Root cause analysis, performance findings, security assessment

### 8. Deployment and Validation
- Use Task tool with subagent_type="deployment-strategies::deployment-engineer"
- Prompt: "Execute emergency deployment for incident fix: $ARGUMENTS. Process: 1) Blue-green or canary deployment, 2) Progressive rollout with monitoring, 3) Health check validation at each stage, 4) Rollback triggers configured, 5) Real-time monitoring during deployment. Coordinate with incident command."
- Output: Deployment status, validation results, monitoring dashboard, rollback readiness
- Context: Fix implementation, current system state

## Phase 4: Communication & Coordination

### 9. Stakeholder Communication
- Use Task tool with subagent_type="content-marketing::content-marketer"
- Prompt: "Manage incident communication for: $ARGUMENTS. Create: 1) Status page updates (public-facing), 2) Internal engineering updates (technical details), 3) Executive summary (business impact/ETA), 4) Customer support briefing (talking points), 5) Timeline documentation with key decisions. Update every 15-30 minutes based on severity."
- Output: Communication artifacts, status updates, stakeholder briefings, timeline log
- Context: All previous phases, current resolution status

### 10. Customer Impact Assessment
- Use Task tool with subagent_type="incident-responder"
- Prompt: "Assess and document customer impact for incident: $ARGUMENTS. Analyze: 1) Affected user segments and geography, 2) Failed transactions or data loss, 3) SLA violations and contractual implications, 4) Customer support ticket volume, 5) Revenue impact estimation. Prepare proactive customer outreach list."
- Output: Customer impact report, SLA analysis, outreach recommendations
- Context: Resolution progress, communication status

## Phase 5: Postmortem & Prevention

### 11. Blameless Postmortem
- Use Task tool with subagent_type="documentation-generation::docs-architect"
- Prompt: "Conduct blameless postmortem for incident: $ARGUMENTS. Document: 1) Complete incident timeline with decisions, 2) Root cause and contributing factors (systems focus), 3) What went well in response, 4) What could improve, 5) Action items with owners and deadlines, 6) Lessons learned for team education. Follow SRE postmortem best practices."
- Output: Postmortem document, action items list, process improvements, training needs
- Context: Complete incident history, all agent outputs

### 12. Monitoring and Alert Enhancement
- Use Task tool with subagent_type="observability-monitoring::observability-engineer"
- Prompt: "Enhance monitoring to prevent recurrence of: $ARGUMENTS. Implement: 1) New alerts for early detection, 2) SLI/SLO adjustments if needed, 3) Dashboard improvements for visibility, 4) Runbook automation opportunities, 5) Chaos engineering scenarios for testing. Ensure alerts are actionable and reduce noise."
- Output: New monitoring configuration, alert rules, dashboard updates, runbook automation
- Context: Postmortem findings, root cause analysis

### 13. System Hardening
- Use Task tool with subagent_type="backend-development::backend-architect"
- Prompt: "Design system improvements to prevent incident: $ARGUMENTS. Propose: 1) Architecture changes for resilience (circuit breakers, bulkheads), 2) Graceful degradation strategies, 3) Capacity planning adjustments, 4) Technical debt prioritization, 5) Dependency reduction opportunities. Create implementation roadmap."
- Output: Architecture improvements, resilience patterns, technical debt items, roadmap
- Context: Postmortem action items, performance analysis

## Success Criteria

### Immediate Success (During Incident)
- Service restoration within SLA targets
- Accurate severity classification within 5 minutes
- Stakeholder communication every 15-30 minutes
- No cascading failures or incident escalation
- Clear incident command structure maintained

### Long-term Success (Post-Incident)
- Comprehensive postmortem within 48 hours
- All action items assigned with deadlines
- Monitoring improvements deployed within 1 week
- Runbook updates completed
- Team training conducted on lessons learned
- Error budget impact assessed and communicated

## Coordination Protocols

### Incident Command Structure
- **Incident Commander**: Decision authority, coordination
- **Technical Lead**: Technical investigation and resolution
- **Communications Lead**: Stakeholder updates
- **Subject Matter Experts**: Specific system expertise

### Communication Channels
- War room (Slack/Teams channel or Zoom)
- Status page updates (StatusPage, Statusly)
- PagerDuty/Opsgenie for alerting
- Confluence/Notion for documentation

### Handoff Requirements
- Each phase provides clear context to the next
- All findings documented in shared incident doc
- Decision rationale recorded for postmortem
- Timestamp all significant events

Production incident requiring immediate response: $ARGUMENTS

© Seth Hobson · MIT · Ormus-Solutions/LibreUIUX-Claude-Code

Similar slash commands

All slash commands for DevOps and infrastructure →

incident-response by other authors comes first.

incident-response Seth Hobson Runs a staged, multi-agent incident response flow with triage, observability checks, mitigation, and approval checkpoints for SRE work. CX Codex +1 ★ 42,780repo stars ai-sre-incident-response devops-skills ai-sre-incident-response — a skill for Claude Code, Codex, Cursor and other platforms: builds SRE practices for AI incidents — model outage, quality regression, cost explosion, safety violations. CX Codex +1 365installs incident-responder Seth Hobson incident-responder guides on-call engineers through outage triage and production stabilization following SRE protocols. Activates incident command and structure during downtime. CX Codex 265installs sre-incident-response paulip114 sre-incident-response is a Claude Code skill that structures production outage management using Google IMAG methods. Responders deploy generic mitigations first and triage systematically. CX Codex +1 ★ 67repo stars New Relic Incident Response Agent official github The New Relic Incident Response Agent for GitHub Copilot correlates observability data from New Relic with code changes. It analyzes alerts and transaction traces to identify incident root causes. CX Codex +1 ★ 41,430repo stars incident-response-forensics securityskills incident-response-forensics — a skill for collecting and analyzing digital evidence during security incident investigations. Preserves proof without corruption, gathers ephemeral data, and constructs an attack timeline. CX Codex +1 254installs incident-commander Alireza Rezvani incident-commander — a Claude skill that runs an outage from declaration to post-mortem: severity classification, timeline reconstruction, root-cause analysis. CX Codex +1 610installs

From the same set42

The whole set →
full-review full-review runs a phased multi-agent code audit in Claude Code. Inspects architecture, OWASP vulnerabilities, runtime bottlenecks, and test suites. CX Codex +1 ★ 126repo stars full-stack-feature full-stack-feature runs feature work through four phases — schema design, API contracts, parallel implementation, testing — by delegating each step to a specialized subagent. Takes a feature description as its argument. CX Codex +1 ★ 126repo stars security-hardening The security-hardening command hardens an application through coordinated security agents. Use it to assess vulnerabilities, fix high-risk issues, and add layered controls. CX Codex +1 ★ 126repo stars performance-optimization performance-optimization coordinates end-to-end performance audits, database optimizations, frontend tuning, and load testing. CX Codex +1 ★ 126repo stars ui-responsive The ui-responsive command analyzes a component or page at five breakpoints and gives specific fixes for mobile, tablet and desktop layouts. CX Codex +1 ★ 126repo stars jungian-archetypes jungian-archetypes maps twelve brand archetypes to UI layout, typography, animations, and Tailwind styling. CX Codex +1 ★ 126repo stars feature-development feature-development is a Claude Code command that coordinates feature work from requirements through deployment preparation. It starts from a feature description. CX Codex +1 ★ 126repo stars legacy-modernize legacy-modernize — a command for gradually updating legacy systems using the strangler fig pattern. Orchestrates specialized agents for code assessment, test coverage, and incremental component replacement without service interruption. CX Codex +1 ★ 126repo stars

Project sponsors

Companies that keep this analytics open