SRE Investigator — DevOps & Infrastructure agent for Claude Code
Investigates Northstar incidents — reads health endpoints, logs, metrics, Kubernetes state, and events; forms an evidence-backed hypothesis.
How to install SRE Investigator
Installs to ~/.claude/agents/schoolofdevops-306-agentic-devops-claude-labs-sre-investigator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/schoolofdevops/306-agentic-devops-claude-labs/HEAD/.claude/agents/sre-investigator.md -o ~/.claude/agents/schoolofdevops-306-agentic-devops-claude-labs-sre-investigator.md Restart Claude Code, or start a new session, for it to be picked up.
What SRE Investigator does
name: sre-investigator description: Investigates Northstar incidents — reads health endpoints, logs, metrics, Kubernetes state, and events; forms an evidence-backed hypothesis. Read-only. Never modifies deployments, applies, or deletes. Hand off structured evidence for someone else to act on. model: sonnet tools: ["Read", "Grep", "Glob", "Bash"] disallowedTools: ["Edit", "Write", "MultiEdit", "NotebookEdit"]
You are the **SRE Investigator** for Northstar Commerce. Your job is to find ou
Alternatives in DevOps & Infrastructure
- Terraform Specialist — You are a Terraform/OpenTofu specialist focused on advanced infrastructure automation, state managem 31.9k ★
- DevOps Hightower — 公司 DevOps/SRE(Kelsey Hightower 思维模型) 141 ★
- DevOps SRE 76 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
FinOps Analyst
Analyzes Northstar infrastructure cost — reads Terraform plan fixtures and environment configs, compares insta
Prod Engineer
Triage production incidents, diagnose with evidence, apply safe mitigations, and harden systems. Use for outag
SRE
Site Reliability Engineer. On-demand infra agent — designs cloud infrastructure, runs load tests, and triages
Infrastructure Analyst
Analyzes infrastructure as code, plans, drift, IAM, network exposure, state layout and recovery from the Unkno
Changeset Builder
Build or validate a deployment Change Set manifest. SfSkills devops workflow agent, /build-changeset: reads it
Deployment Risk Scorer
Risk-score a change set before deploy. SfSkills devops workflow agent, /score-deployment: reads its AGENT.md p
Related Skills
Kubescout MCP
Read-only by default MCP server for diagnosing Kubernetes incidents. Gives Claude Code and other AI agents one
AI Incident Agent
AI-powered incident response agent built with Spring Boot and Claude AI. Automatically investigates, diagnoses
Ops Engineering Skills
Open-source, cross-agent Agent Skills for DevOps, DevSecOps, Cloud, Kubernetes/platform engineering, CI/CD too