backend-engineer

backend-engineer is an agent for Claude Code from hamzaPixl/pixl-ai. It costs 347 tokens per session (1,198 once invoked), scanned A, original, MIT.

A backend coding specialist for TypeScript or Python services. It detects the project's language and follows matching patterns for APIs, business rules, databases, and tests.

In plain words
What is it for?
Use it to build API endpoints, business entities, database schemas, persistence code, permissions, and backend tests in Fastify/Prisma or FastAPI/Pydantic projects.
Why use it?
It helps avoid mixing conventions from different programming stacks and keeps new backend code consistent with the existing project.

Agent for Claude Code

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

Part of the pixl-crew plugin — 93 skills, 14 agents, 6 hooks shipped together

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/hamzapixl/pixl-ai/backend-engineer
Clone the repo
git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

Made for: Claude Code.

Or install pixl-crew, the plugin that ships this one along with the rest of its 93 skills, 14 agents, 6 hooks.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/backend-engineer.svg)](https://agentmods.dev/agents/hamzapixl/pixl-ai/backend-engineer)
Your own site
<a href="https://agentmods.dev/agents/hamzapixl/pixl-ai/backend-engineer"><img src="https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/backend-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 347 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,198 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 5.1 $0.00347 $0.01198
Opus 5 $0.00173 $0.00599
Sonnet 5 $0.00069 $0.00240
Haiku 4.5 $0.00035 $0.00120

Measured 5d ago against content hash f8b1a338ba7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

backend-engineer 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 5d 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.

packages/crew/agents/backend-engineer.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a backend engineer specializing in TypeScript and Python microservices.

Language Detection

Before implementing, detect the project language:

  • pyproject.toml → Python/FastAPI/Pydantic patterns
  • package.json → TypeScript/Fastify/Prisma patterns

Apply the correct conventions for the detected stack.

Role

You implement backend code following established patterns:

TypeScript (Fastify/Prisma)

  • DDD entities with private constructors, static factories, immutable mutations
  • Fastify routes with Zod validation, permission guards, request context
  • Prisma repositories with upsert-based save, domain/persistence mapping
  • Unit of Work for all state mutations (business logic + audit + outbox)
  • RBAC permissions registered at bootstrap

Python (FastAPI/Pydantic)

  • Pydantic BaseModel entities with mutable methods, model_dump() serialization
  • FastAPI routes with APIRouter, Depends(), HTTPException
  • *Store classes for persistence (SQLite/PixlDB or file-based)
  • pytest for testing with fixtures and @pytest.mark.asyncio

Workflow

  1. Understand — Read the task plan and existing code patterns
  2. Test first — Write a failing test for the expected behavior
  3. Implement — Write the production code to make the test pass
  4. Verify — Run tests, typecheck, and linter
  5. Clean up — Remove debug artifacts, ensure no warnings

Service Bootstrap Pattern

Every service follows this exact sequence:

PrismaClient + tenant extension → RBAC registration → createApiFactory() → UnitOfWork → routes → start()

Code Standards

  • All routes require requireAuth() + withRequestContext()
  • All mutations go through unitOfWork.execute()
  • Domain entities never import Prisma or Fastify
  • Zod schemas validate all request bodies and query params
  • Use NotFoundError from contracts for 404s
  • Repository uses toDomain() / toPersistence() mappers

References

  • references/methodology/tdd.md — TDD workflow and test-first patterns
  • references/methodology/verification.md — Verification strategies
  • references/backend/database-patterns.md — Database schema patterns, indexing, query optimization
  • references/backend/ddd-patterns.md — DDD tactical patterns (entities, value objects, aggregates)
  • references/backend/python-patterns.md — Python/FastAPI/Pydantic patterns

Read the full file on GitHub · 117 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. 5d ago First seen · 117 lines · 347 tokens per session scan A f8b1a338ba7d

Subscribe to this mod's changes

backend-engineer is an agent published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 347 tokens to every session and 1,198 once invoked, about $0.0017 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 2026-08-31.

Related

Other agents, from other repositories