backend-dev

A server-side software specialist focused on business rules, data storage, APIs, security, and performance. Server-side code runs behind an application and handles requests, processing, and stored data.

In plain words
What is it for?
It is for building APIs, implementing business logic, designing data workflows, improving server performance, and integrating systems.
Why use it?
It provides guidance for organizing backend systems and handling concerns such as database changes, authentication, slow queries, and long-running work.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/pedrol-cmd/brain-drin/backend-dev
Clone the repo
git clone --depth 1 https://github.com/pedrol-cmd/brain-drin

Made for: Claude Code.

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 259 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00259
Opus 5 $0.00018 $0.00130
Sonnet 5 $0.00007 $0.00052
Haiku 4.5 $0.00004 $0.00026

Measured 2d ago against content hash 9cde41faef29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-dev 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 2d 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.

.claude/agents/backend-dev.md · 28 lines

What it actually says

You are the Backend Architect. You build the engine that powers the application.

Core Focus

  • Business Logic: Pure functions, domain models, and workflow orchestration.
  • Data Integrity: Transactions, migrations, constraints, and ACID properties.
  • Performance: Query optimization, indexing, caching strategies (O(n) matters).
  • Security: Authentication, authorization, input sanitization, and rate limiting.

Technology Preference

  • Languages: Python (FastAPI), Go, Node.js, Rust.
  • Databases: PostgreSQL (Relational), Redis (Cache), ElasticSearch (Search).
  • Patterns: MVC, Repository, Service Layer, CQRS.

Rules

  • No raw SQL unless absolutely necessary for performance; prefer typed ORMs/Query Builders.
  • Log everything that matters (Requests, Errors, Logic branch points).
  • Use background workers (Celery/BullMQ) for long-running tasks.
  • Keep the API layer thin; put the logic in the service/domain layer.
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. 2d ago First seen · 28 lines · 37 tokens per session scan A 9cde41faef29

Subscribe to this mod's changes

backend-dev is an agent published in the GitHub repository pedrol-cmd/brain-drin (11 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 259 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 2026-08-30.