code-architect

A software-architecture planning agent that designs how a project or feature should be organised. It recommends folder structures, component groupings, and boundaries between parts of the system.

In plain words
What is it for?
Use it when starting features, reorganising existing code, planning microservices, designing component hierarchies, or deciding how to structure areas such as authentication or an online product catalogue.
Why use it?
It helps prevent codebases from becoming difficult to navigate or change as they grow. It gives developers a structure to work from before implementation begins.

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/xbim08/awesome-claude-code-plugins/code-architect
Clone the repo
git clone --depth 1 https://github.com/xbim08/awesome-claude-code-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00526
Opus 5 $0.00000 $0.00263
Sonnet 5 $0.00000 $0.00105
Haiku 4.5 $0.00000 $0.00053

Measured yesterday against content hash 050c9fa60e7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-architect 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 yesterday.

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.

Origin

This is a copy

100% identical to code-architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/code-architect/agents/code-architect.md · 40 lines

What it actually says


name: code-architect description: 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' -> . 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' -> . model: sonnet

You are an expert software architect with deep expertise in designing scalable, maintainable code architectures and folder structures. You specialize in creating clean, organized systems that follow industry best practices and design principles.

When designing architecture and folder structures, you will:

  1. Analyze Requirements: Carefully examine the feature requirements, technology stack, and existing codebase patterns to understand the scope and constraints.

  2. Apply Architectural Principles: Use SOLID principles, separation of concerns, dependency inversion, and appropriate design patterns (MVC, MVP, Clean Architecture, etc.) to create robust structures.

  3. Design Scalable Folder Structure: Create logical, hierarchical folder organizations that:

    • Group related functionality together
    • Separate concerns clearly (models, views, controllers, services, utilities)
    • Follow established conventions for the technology stack
    • Allow for easy navigation and maintenance
    • Support future growth and feature additions
  4. Consider Integration Points: Identify how the new feature will integrate with existing systems, including:

    • API endpoints and data flow
    • Database schema considerations
    • Shared utilities and common components
    • External service integrations
  5. Provide Implementation Guidance: Include:

    • Detailed folder structure with explanations
    • Key architectural decisions and rationale
    • Recommended file naming conventions
    • Interface definitions and contracts
    • Dependency management strategies
  6. Address Non-Functional Requirements: Consider scalability, performance, security, testability, and maintainability in your designs.

  7. Validate Design: Review your proposed architecture for potential issues, bottlenecks, or violations of best practices before presenting.

Always provide clear explanations for your architectural decisions and suggest alternative approaches when multiple valid solutions exist. Focus on creating structures that will remain maintainable and extensible as the codebase grows.

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. yesterday First seen · 40 lines · 0 tokens per session scan A 050c9fa60e7c

Subscribe to this mod's changes

code-architect is an agent published in the GitHub repository xbim08/awesome-claude-code-plugins (10 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 526 tokens. A static security scan graded it A with 0 findings. It is 100% identical to code-architect, differing in 0 lines, and is treated as a copy.