incident-response · ormus-solutions — команда для Claude Code: разбор инцидентов
Команда incident-response координирует разбор инцидента: от оценки серьёзности и поиска причины до исправления и связи с заинтересованными сторонами. Запустите её с описанием сбоя.
MIT ★ 126 обновлён 2026-10-04
/plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code
/plugin install incident-response@libreuiuxЧто делает incident-response
incident-response разбивает работу на этапы и поручает их специализированным субагентам через инструмент Task. Сначала команда оценивает серьёзность, затронутые сервисы и влияние на пользователей, затем собирает данные мониторинга и предлагает первичные меры: например, откатить недавний релиз или отключить функцию флагом.
Дальше в процессе участвуют субагенты для отладки, проверки безопасности и анализа производительности. После поиска причины команда переходит к исправлению, развёртыванию и коммуникации. Среди упомянутых систем наблюдаемости — OpenTelemetry, Prometheus и Grafana. Для расследования используются данные об инциденте и результаты предыдущих этапов, поэтому качество исходного описания влияет на полезность разбора.
Какие задачи решает
- оценить серьёзность сбоя и его влияние на пользователей
- сопоставить метрики, трассировки и журналы ошибок
- найти первопричину и связанные сбои зависимостей
- подготовить план исправления с проверкой и откатом
- сформировать обновления для команды и заинтересованных сторон
Примеры запросов агенту
- Разбери инцидент: после последнего релиза выросло число ошибок API, затронуты запросы авторизации.
- Оцени сбой: сервис недоступен, проверь влияние на пользователей и предложи первичные меры.
Как установить incident-response
1Через маркетплейс плагинов
/plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code/plugin install incident-response@libreuiux2Вручную: положить файлы
.claude/commands/incident-response.mdВызов — /incident-response. Для всех проектов — ~/.claude/commands/
Вручную: положить файлы
~/.codex/prompts/incident-response.mdВызов — /prompts:incident-response. В Codex этот формат помечен устаревшим, замена — скиллы
Вручную: положить файлы
.github/prompts/incident-response.prompt.mdВручную: положить файлы
.gemini/commands/incident-response.tomlGemini хранит команды в TOML: текст запроса — в поле prompt
Вопросы об incident-response
Как установить incident-response в Claude Code?
В Claude Code выполните /plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code , затем /plugin install incident-response@libreuiux.
Что делает incident-response?
Команда организует разбор инцидента по этапам: от классификации и анализа наблюдаемости до поиска причины, исправления и коммуникации.
Какие системы наблюдаемости учитывает команда?
В рабочем процессе перечислены распределённые трассировки OpenTelemetry и Jaeger, метрики Prometheus, Grafana и DataDog, а также журналы ELK и Splunk.
Исходный текст
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
Похожие слэш-команды
Все слэш-команды по теме «DevOps и инфраструктура» →Сначала — incident-response от других авторов.