SRE Engineer — Development agent for Claude Code
Reviews a diff file the caller supplies, or a set of paths, for failure behaviour, read-only — timeouts, retries, partial failure, backpressure and overload, shutdown and restart, resource exhaustion.
How to install SRE Engineer
Installs to ~/.claude/agents/nshopik-dream-team-sre-engineer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/nshopik/dream-team/HEAD/agents/sre-engineer.md -o ~/.claude/agents/nshopik-dream-team-sre-engineer.md Restart Claude Code, or start a new session, for it to be picked up.
What SRE Engineer does
name: sre-engineer description: Reviews a diff file the caller supplies, or a set of paths, for failure behaviour, read-only — timeouts, retries, partial failure, backpressure and overload, shutdown and restart, resource exhaustion, and errors that are lost or mis-reported. Traces each failure from the code and says what happens to data, whether the failure is observable, and whether the behaviour matches the docs; never builds, runs experiments or edits. Use for a reliability review, a fail
Alternatives in Development
- Incident Response — Orchestrate multi-agent incident response with modern SRE practices for rapid resolution and learnin 31.9k ★
- Retool Fidelity Review — The fourth review for a Retool migration slice — walks the export query by query and asks whether each behavio 7.2k ★
- Turbo Agent — Implements Turbo Drive, Turbo Frames, and Turbo Streams for fast, responsive Rails applications with minimal J 652 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Reliability Availability Review
Reviews a diff for reliability/availability defects — error handling that hides failure, missing timeouts/retr
Reliability Reviewer
Use AFTER backend code is written to review for operational correctness — idempotency, partial-failure handlin
Sdlc Stress
Evaluates production resilience of the implementation under adverse conditions — load, malformed input, partia
Integration Boss
APIs, automation, and external-systems Boss for Forge. Handles n8n, webhooks, Gmail, calendars, databases, pay
Progression Planner
Defines how the programme advances week by week — the overload rule per session type, the deload, autoregulati
Websocket Expert
Tier 2 — Implementation. Owns realtime transport, reconnection, and backpressure. Use for WebSocket/realtime f
Related Skills
Errors
Establish error handling patterns and resilience strategy — classification, retries, timeouts, circuit breaker
Resilience Audit
Reliability / failure-mode audit — why distributed and async systems fall over: single points of failure, miss
Open DevOps Skills
Open DevOps Skills for Claude Code & Codex — zombie resource scanning, cost optimization, K8s troubleshooting,