Modern coding agents are getting exceptionally good at implementing a given coding task. And with validation-in-the-loop, you can be reasonably confident they will implement a correct solution. However, their implementation often leaves a lot to be desired. It doesn't adhere to the decades of software design best-practices that the community has established and is often myopic to broader software quality attributes like maintainability and extensibility. To make things worse, this low code quality compounds as coding agents implement additional tasks.
These design principles weren't established specifically to help humans...they were designed to make code easier to refactor, modify, extend, test, and maintain! And these properties matter just as much in an agentic world. Design principles significantly reduce the amount of context humans or agents need to understand a codebase or implement a feature. They reduce the surface area for bugs, improve testing efficacy, and just generally make humans and agents more effective at building software.
This has been my biggest reservation for using coding agents on larger and more unstructured tasks, so I built Arxitect. I was inspired by the design of [Superpowers](https://github.com/obra/superpowers) and decided to extend that concept to software design principles.
Currently, it contains implementation and code review agents (and skills) that asses your code for:
*API Design - Assessing naming conventions, method signatures, parameter design, type safety, and REST endpoint design.
*Object Oriented Design - Assessing SOLID principles, DRY violations, composition vs. inheritance choices, and design pattern applicability.
*Clean Architecture - Assessing component cohesion, component coupling, and quality attributes like maintainability, extensibility, and testability.
Install in Claude Code with:
/plugin marketplace add andonimichael/arxitect
/plugin install arxitect@arxitect
/reload-plugins
No comments yet.