By thedotmack
Delegate analysis of technical requirements, evaluate architectural patterns with trade-offs, and generate Architectural Decision Records for scalable system design.
Use this agent for solving specific technical problems with architectural patterns and technology-agnostic recommendations . This agent analyzes requirements, recommends patterns, and provides architectural guidance for specific features or challenges . Use when you need pattern recommendations for a specific problem, not full system architecture design . Examples: <example>Context: Need to handle file uploads efficiently. user: 'How should we architect file upload handling for large files (up to 5GB)?' assistant: 'I'll use solution-architect to analyze requirements, evaluate patterns (chunked upload, resumable upload, direct-to-storage), and recommend an architecture with rationale and trade-offs.' <commentary>This is a specific problem requiring pattern selection and architectural guidance.</commentary></example> <example>Context: Need to improve search performance . user: 'Our search is slow. What architectural approach should we use?' assistant: 'Let me use solution-architect to analyze the search problem, evaluate solutions (full-text search, Elasticsearch, read replicas, caching), and recommend an approach based on your scale and requirements.' <commentary>Specific problem requiring architectural solution recommendation.</commentary></example>
Use this agent for system architecture design and evaluation. This agent focuses on architectural patterns, quality attributes, system design principles, and architectural decision-making . Use when you need to design system architecture, evaluate architectural trade-offs, or create architectural decision records . Examples: <example>Context: Need to design a new microservices-based system. user: 'We need to design the architecture for a distributed event processing system that handles 100K events/second' assistant: 'I'll use system-architect to analyze quality attribute requirements (scalability, performance, reliability), evaluate architectural patterns (event sourcing, CQRS, stream processing), and create an architectural blueprint with ADRs.' <commentary>This requires architectural thinking about patterns, trade-offs, and quality attributes.</commentary></example> <example>Context: Evaluating architectural options for a new feature . user: 'Should we use event-driven architecture or REST APIs for our notification system?' assistant: 'Let me use system-architect to evaluate both approaches against quality attributes, analyze trade-offs (consistency vs availability, coupling vs performance), and recommend the appropriate pattern with rationale.' <commentary>This is an architectural decision requiring trade-off analysis.</commentary></example>
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.
A curated marketplace of Claude Code plugins that embody the principles of ethical and professional software development.
Han (藩 - domain/clan) is a marketplace of Claude Code plugins built on the foundation of the seven Bushido virtues. Each plugin helps you write better code through skills, agents, validation hooks, and external integrations.
The marketplace is organized around Japanese martial arts philosophy:
The Bushido Code guides every plugin in this marketplace:
Use the han CLI tool to automatically detect and install appropriate plugins:
Important: Han must be installed globally for hooks to work. Hooks run validation commands (tests, linting, etc.) when you stop working, and they require
hanto be available in your PATH. Usingnpxwill install plugins but hooks will not function.
# Install globally (REQUIRED for hooks)
npm install -g @thebushidocollective/han
# Then install plugins
han plugin install --auto
For other installation methods (Homebrew, curl, manual download), visit han.guru.
The installer will:
.claude/settings.json automatically/plugin CommandUse Claude Code's built-in plugin command to add the marketplace:
/plugin marketplace add thebushidocollective/han
Then install individual plugins:
/plugin install bushido@han
/plugin install buki-typescript@han
Note: For hooks to work, you must also install
hanglobally and ensure it's in your PATH. See Automatic Installation above.
Add the Han marketplace to your Claude Code settings (.claude/settings.json):
{
"extraKnownMarketplaces": {
"han": {
"source": {
"source": "github",
"repo": "thebushidocollective/han"
}
}
},
"enabledPlugins": {
"bushido": true
}
}
Then browse available plugins using Claude Code's plugin interface.
Note: For hooks to work, you must also install
hanglobally and ensure it's in your PATH. See Automatic Installation above.
The foundational plugin containing the seven virtues, enforcement hooks, and core quality skills.
Always install this first - it provides the philosophical foundation and universal quality principles (SOLID, TDD, Boy Scout Rule, etc.).
Language and tool plugins that provide validation hooks for your development workflow.
Categories:
Each buki plugin includes validation hooks that run on Stop and SubagentStop events, ensuring code quality before you continue.
Browse all buki plugins: Check the /buki directory in this repository.
Specialized agents focused on development disciplines and practices.
Disciplines include:
Browse all dō plugins: Check the /do directory in this repository.
MCP servers that provide external knowledge and integrations.
Examples:
Browse all sensei plugins: Check the /sensei directory in this repository.
Reminder: Han must be installed globally for hooks to work. See han.guru for installation instructions.
# Interactive mode - browse and select plugins
han plugin install
# Auto-detect mode - AI analyzes codebase
han plugin install --auto
npx claudepluginhub thedotmack/han --plugin do-architectureMemory compression system for Claude Code - persist context across sessions
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Validation and quality enforcement for Claude Agent SDK projects with TypeScript type checking and structure validation.
Validation and quality enforcement for GitHub Actions workflows with act local testing.
MCP server for managing technical blueprint documentation. Use search_blueprints before creating, read_blueprint before modifying, write_blueprint after implementation changes. Includes skills and hooks for quality enforcement.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Use this agent when creating user interfaces, designing components, building design systems, or improving visual aesthetics. This agent specializes in creating beautiful, functional interfaces that can be implemented quickly within 6-day sprints. Examples:\n\n<example>\nContext: Starting a new app or feature design
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research