Enforce software design and architecture best practices through automated multi-perspective code reviews that evaluate SOLID principles, Clean Architecture compliance, and API design quality, with iterative approval workflows for large coding tasks.
Reviews code for API design quality including naming conventions, self-documenting interfaces, method signatures, parameter design, type safety, and REST endpoint design.
Orchestrates an architecture-enforced implementation feedback loop. Implements code, then runs Object Oriented Design, Clean Architecture, and API Design reviews, iterating until all reviewers approve or the safety valve triggers. Use when implementing large coding tasks that require system design.
Orchestrates three architecture reviewers (Object Oriented Design, Clean Architecture, and API Design Reviewers). Use for comprehensive design review without implementation.
Reviews code for clean architecture compliance including component cohesion principles (REP, CRP, CCP), component coupling principles (ADP, SDP, SAP), and quality attributes (maintainability, extensibility, testability).
Reviews code for object-oriented design quality including SOLID principles, DRY violations, composition and inheritance choices, and Gang of Four design pattern applicability.
Reviews code for API design quality including naming conventions, self-documenting interfaces, method signatures, parameter design, type safety, and REST endpoint design. Use when evaluating the usability and readability of public interfaces, class APIs, or REST endpoints.
Orchestrates an architecture-enforced implementation feedback loop. Implements code, then runs Object Oriented Design, Clean Architecture, and API Design reviews, iterating until all reviewers approve or the safety valve triggers. Use when implementing code that should meet design quality standards.
Runs all three architecture reviewers (Object Oriented Design, Clean Architecture, and API Design Reviewers).
Reviews code for clean architecture compliance including component cohesion principles (REP, CRP, CCP), component coupling principles (ADP, SDP, SAP), and quality attributes (maintainability, extensibility, testability). Use when evaluating architectural soundness of new or modified code.
Reviews code for object-oriented design quality including SOLID principles, DRY violations, composition and inheritance choices, and Gang of Four design pattern applicability. Use when evaluating object oriented design of new or modified code.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Arxitect is an agentic coding plugin that enforces best-practice software design & architecture. It adds implementation agents and architecture reviewers to your client that enforce API Design, Object-Oriented Design, and Clean Architecture standards.
Coding agents often burn context, waste tokens, implement partial solutions, or miss major components of coding tasks because they naturally implement repetitive, brittle, and tactical code. Software design principles weren't meant to be just for humans. They were meant to make all code easier and safer to read, understand, refactor, modify, extend, test, and maintain. Arxitect helps coding agents build robust software through best practice design and architecture. It helps coding agents write better code. And in turn, coding agents become more efficient and more accurate.
Arxitect was influenced by the design of Superpowers. Arxitect extends Superpower's concept of improving agents at implementing coding tasks to improving agents at broader code architecture and software design.
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, Most notably 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 including maintainability and extensibility. To make things worse, this low code quality compounds as coding agents implement additional tasks.
Software design principles weren't established specifically to help humans. They were designed to make code easier to read, understand, refactor, modify, extend, test, and maintain. They proactively mitigate the risk of bugs. They reduce the surface area for changes. They minimize the amount of information needed to grok the code. All of these are just as important for agents. They reduce the amount of context needed to understand the code and make changes. They reduce the chance of bugs and improve testing efficacy. And they make agents more effective at implementing feature requests.
Arxitect provides sub-agents and skills that can implement features and review code against established design principles. These will automatically trigger when the Client determines architecture review is important for the requested changes or are relevant for the input prompt. Three specialized reviewers will examine your code from different angles:
Arxitect contains the following agents:
@architect that will plan and implement your change using best practices.@architecture-review that will review your code for adherence to best practices.And it contains the following skills:
/architect that will plan and implement your change using best practices./architecture-review that will review your code for adherence to best practices./api-design-review that will audit your code for adherence to api design principles./oo-design-review that will audit your code for adherence to object oriented design principles./clean-architecture-review that will audit your code for adherence to clean architecture principles./using-arxitect the bootstrap skill that teaches your client how and when to use ArxitectIn Claude Code, register the marketplace first:
/plugin marketplace add andonimichael/arxitect
Then install the plugin:
/plugin install arxitect@arxitect
Finally reload your plugins to pick up Arxitect in the current session:
/reload-plugins
npx claudepluginhub andonimichael/arxitect --plugin arxitectFull-spectrum design patterns skill: Detect anti-patterns, diagnose architectural debt, and generate production-ready refactored code. Covers GoF, SOLID, Clean Architecture, DDD, CQRS, Microservices, and Cloud patterns.
[Beta] 6つの専門エージェントチームでコードベースのアーキテクチャを多角的に分析するスキル
AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode
Architecture Deep Research — scan a repo, draft a PRD, run live deep research, get a cited handoff. Use when picking a topology, retrieval architecture, event bus, storage engine, auth pattern, or any system-design decision before code lands.
Architecture analysis, brainstorming, ADR generation, LLM-as-judge comparison, and spec gap resolution.
Use this agent when you need to design scalable architecture and folder structures for new features or projects. Examples include: when starting a new feature module, refactoring existing code organization, planning microservice boundaries, designing component hierarchies, or establishing project structure conventions. For example: user: 'I need to add a user authentication system to my app' -> assistant: 'I'll use the code-architect agent to design the architecture and folder structure for your authentication system' -> <uses agent>. Another example: user: 'How should I organize my e-commerce product catalog feature?' -> assistant: 'Let me use the code-architect agent to design a scalable structure for your product catalog' -> <uses agent>.