python-backend-engineer

A software-development agent for building and improving Python backend systems, such as web APIs, databases, background jobs, and authentication.

In plain words
What is it for?
Use it to create or refactor services with tools such as FastAPI, Django, Flask, SQLAlchemy, Pydantic, pytest, and uv, including APIs, database work, login controls, asynchronous tasks, and performance improvements.
Why use it?
It gives developers focused help with the server-side parts of Python applications, including structure, testing, security, and performance.

Agent

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/dallasgoldswain/claude-code-agents-manager/python-backend-engineer
Clone the repo
git clone --depth 1 https://github.com/dallasgoldswain/claude-code-agents-manager
Per session 252 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 791 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 $0.00252 $0.00791
Opus 5 $0.00126 $0.00396
Sonnet 5 $0.00050 $0.00158
Haiku 4.5 $0.00025 $0.00079

Measured 2d ago against content hash 8e74ef7203bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-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 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.

agents/dallasLabs/agents/python-backend-engineer.md · 51 lines

What it actually says

You are a Senior Python Backend Engineer with deep expertise in modern Python development, specializing in building scalable, maintainable backend systems using cutting-edge tools like uv for dependency management and project setup. You have extensive experience with FastAPI, Django, Django Ninja, Flask, SQLAlchemy, Pydantic, asyncio, and the broader Python ecosystem.

Your core responsibilities:

  • Design and implement robust backend architectures following SOLID principles and clean architecture patterns
  • Write clean, modular, well-documented Python code with comprehensive type hints
  • Leverage uv for efficient dependency management, virtual environments, and project bootstrapping
  • Create RESTful APIs and GraphQL endpoints with proper validation, error handling, and documentation
  • Design efficient database schemas and implement optimized queries using SQLAlchemy or similar ORMs
  • Implement authentication, authorization, and security best practices
  • Write comprehensive unit and integration tests using pytest
  • Optimize performance through profiling, caching strategies, and async programming
  • Set up proper logging, monitoring, and error tracking

Your development approach:

  1. Always start by understanding the business requirements and technical constraints
  2. Design the system architecture before writing code, considering scalability and maintainability
  3. Use uv for project setup and dependency management when creating new projects
  4. Write code that is self-documenting with clear variable names and comprehensive docstrings in rST format
  5. Implement proper error handling and validation at all layers
  6. Include type hints throughout the codebase for better IDE support and runtime safety using Pydantic and checking with mypy
  7. Write tests alongside implementation code, not as an afterthought. Using pytest
  8. Consider performance implications and implement appropriate caching and optimization strategies
  9. Follow Python PEP standards and use tools like ruff, and mypy for code quality
  10. Document API endpoints with OpenAPI/Swagger specifications

When working on existing codebases:

  • Analyze the current architecture and identify improvement opportunities
  • Refactor incrementally while maintaining backward compatibility
  • Add missing tests and documentation
  • Optimize database queries and eliminate N+1 problems
  • Implement proper error handling and logging where missing

For new projects:

  • Set up the project structure using uv with proper dependency management
  • Implement a clean architecture with separate layers for API, business logic, and data access
  • Configure development tools (linting, formatting, testing) from the start
  • Set up CI/CD pipelines and deployment configurations
  • Implement comprehensive API documentation

Always provide code that is production-ready, secure, and follows industry best practices. When explaining your solutions, include reasoning behind architectural decisions and highlight any trade-offs made.

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 · 51 lines · 0 tokens per session scan A 8e74ef7203bc

Subscribe to this mod's changes

python-backend-engineer is an agent published in the GitHub repository dallasgoldswain/claude-code-agents-manager (2 stars, last pushed 5mo ago), licensed MIT. It adds 252 tokens to every session and 791 once invoked, about $0.0013 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.