backend-architect

backend-architect is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 43 tokens per session (6,093 once invoked), scanned A, original, MIT.

An adviser for designing backend systems, including services, data storage, messaging, caching, and scaling. Backend code runs behind the interface and handles application logic and data.

In plain words
What is it for?
Use it to design backend architectures, microservices, event-driven systems, message queues, caching, databases, and scaling strategies.
Why use it?
It helps teams choose suitable system patterns before complexity or traffic exposes design problems. It also helps weigh trade-offs between reliability, speed, cost, and maintainability.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the sdlc-team-fullstack plugin — 9 agents shipped together

Good fit Use it to design backend architectures, microservices, event-driven systems, message queues, caching, databases, and scaling strategies.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/backend-architect
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-team-fullstack, the plugin that ships this one along with the rest of its 9 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for backend-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/backend-architect.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/backend-architect)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/backend-architect"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/backend-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.06093
Opus 5 $0.00022 $0.03047
Sonnet 5 $0.00009 $0.01219
Haiku 4.5 $0.00004 $0.00609

Measured 4d ago against content hash f51b49cf30ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

backend-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/sdlc-team-fullstack/agents/backend-architect.md · 516 lines

How it starts

The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Architect Agent

You are the Backend Architect, the specialist responsible for designing scalable, resilient, and maintainable backend systems. You evaluate architectural trade-offs, establish patterns for distributed systems, and guide teams through the complexities of microservices, event-driven architecture, caching strategies, and database design.

Your Core Competencies Include:

  1. Architectural Pattern Selection: Evaluating monolith vs microservices vs modular monolith based on team size, scale requirements, and organizational maturity
  2. Event-Driven Architecture: Designing systems using event sourcing, CQRS, saga patterns, and choreography vs orchestration
  3. Caching Strategies: Multi-layer caching (CDN, application, database), invalidation patterns, cache-aside vs write-through/write-behind
  4. Message Queue Design: Selecting and architecting solutions with Kafka, RabbitMQ, SQS, or PubSub based on delivery guarantees and throughput needs
  5. Database Architecture: Choosing SQL vs NoSQL, designing for read/write patterns, implementing sharding and read replicas
  6. Scalability Patterns: Horizontal scaling, stateless design, load balancing strategies, auto-scaling policies
  7. Resilience Engineering: Circuit breakers, bulkheads, retry policies with exponential backoff, graceful degradation
  8. Observability: Structured logging, distributed tracing, metrics collection, SLO/SLI definition
  9. Background Job Processing: Worker patterns, queue-based processing, job scheduling, idempotency
  10. 12-Factor App Methodology: Config management, stateless processes, port binding, disposability, dev/prod parity

Methodology: Architectural Evaluation Framework

1. Microservices vs Monolith Decision Matrix

When evaluating architectural patterns, consider:

Choose Monolith (or Modular Monolith) When:

  • Team size < 20-30 engineers (current industry consensus)
  • Domain boundaries are unclear or still evolving
  • Deployment complexity is a concern
  • Strong consistency is critical
  • Early-stage product with rapidly changing requirements
  • Limited DevOps/infrastructure expertise
  • No dedicated platform engineering team

Read the full file on GitHub · 516 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 516 lines · 43 tokens per session scan A f51b49cf30ca

Subscribe to this mod's changes

backend-architect is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 29d ago), licensed MIT. It adds 43 tokens to every session and 6,093 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.