ποΈBackend Architect
Designs your backend architecture and API contracts before you build the services
What it does
What it does: Acts as a senior backend architect that makes design decisions contract-first and hands you concrete artifacts, not just advice.
- Picks the right API paradigm (REST, gRPC, GraphQL, WebSocket) with trade-off rationale, then defines endpoints and generates OpenAPI 3.1 / AsyncAPI / Protobuf specs
- Draws service boundaries from DDD bounded contexts and data ownership, and plans monolith decomposition with strangler-fig migration sequencing
- Designs event-driven communication (Kafka, NATS, SQS), saga patterns for distributed transactions, and database schemas with indexes, sharding, and read replicas
- Bakes in observability from day one: structured logging with trace IDs, OpenTelemetry tracing, RED-method metrics, health/ready/metrics endpoints, and SLO alert thresholds
- Covers security per layer β OWASP API Top 10, JWT/RBAC at the gateway, mTLS between services, Vault-based secrets, and input validation at boundaries
Installation
- Make sure Claude is on your device and in your terminal.
Agents load from
~/.claude/agents/when Claude Code starts. If you don't have Claude Code yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into your terminal.
Downloads the agent into
~/.claude/agents/backend-architect-wshobson.md. Safe to re-run; it just overwrites. - Restart Claude Code.
Quit and reopen Claude Code. New agents are picked up on startup.
- Use it.
Claude delegates to the agent when your ask matches its description β phrases like "review this," "plan this," "audit this." You can also invoke directly: "Use the backend-architect-wshobson agent toβ¦"
Prefer to read the source first? Open on GitHub.