By AstyanM
Developer toolkit plugin for Claude Code — agents for architecture, code review, testing, refactoring, and performance auditing; skills for API docs, DBML schemas, Draw.io diagrams, frontend design, and README editing; security hooks and guided workflows.
Guided feature development with codebase understanding and architecture focus
Génère un README.md complet depuis le codebase
Analyse et améliore le README.md du projet
Update CLAUDE.md with learnings from this session
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter
Analyzes codebases for performance anti-patterns, bottlenecks, and optimization opportunities. Detects N+1 queries, unnecessary re-renders, memory leaks, inefficient algorithms, bundle bloat, and slow I/O patterns, then provides concrete fixes with expected impact
Detects code smells, duplication, excessive complexity, and structural issues in a codebase, then proposes concrete, safe refactoring plans with step-by-step migration paths and regression risk assessment
Use this skill whenever the user wants to generate, edit, or improve API documentation. Triggers include: any mention of 'API docs', 'API documentation', 'OpenAPI', 'Swagger', 'endpoint documentation', 'route docs', 'API reference', 'Postman collection', or requests to document REST/GraphQL/gRPC APIs. Also use when the user asks to generate OpenAPI specs from code, document request/response schemas, or create API usage examples. Do NOT use for general README documentation (use readme-editor), internal code documentation (docstrings), or database schema documentation (use dbml).
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
Use this skill whenever the user wants to design, create, edit, or visualize a database schema using DBML (Database Markup Language). Triggers include: any mention of 'dbml', 'database schema', 'ERD', 'entity relationship diagram', 'table structure', 'data model', 'database design', 'db schema', or requests to model tables, relationships, foreign keys, or database architectures. Also use when converting SQL DDL to DBML, generating schemas from descriptions, or when the user has the DBML Live Preview VS Code extension installed. Do NOT use for writing raw SQL queries, Prisma schemas, actual database migrations, or ORM model code.
Use this skill whenever the user wants to create, edit, or manipulate Draw.io diagrams (.drawio, .drawio.svg, .drawio.png, .dio files). Triggers include: any mention of 'draw.io', 'drawio', 'diagram', 'flowchart', 'orgchart', 'architecture diagram', 'sequence diagram', 'network diagram', 'ER diagram', 'UML', 'state machine', 'mind map', or requests to visually represent processes, systems, or relationships. Also use when the user asks to convert text descriptions into visual diagrams, or to modify existing .drawio files. Do NOT use for Mermaid diagrams (.mermaid), SVG hand-coding, image generation, or non-diagram visualizations like charts/graphs (use xlsx or React for those).
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Modifies files
Hook triggers on file write and edit operations
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 developer toolkit plugin for Claude Code — agents, skills, commands, and hooks that turn Claude into a structured engineering assistant.
Claude Code is powerful out of the box, but complex engineering workflows benefit from structured guidance. This plugin provides opinionated agents, reusable skills, and safety hooks so that Claude follows best practices automatically — from architecture design to code review, test generation, and documentation.
| Category | What you get |
|---|---|
| Architecture & exploration | Agents that analyze codebases, design feature blueprints, and trace execution flows |
| Code quality | Automated code review with confidence scoring, refactoring advisor with smell detection, and performance auditing |
| Test generation | Agent that produces idiomatic, runnable test suites matching your project's framework and conventions |
| API documentation | Skill that generates OpenAPI 3.1 YAML, Markdown, or Postman collections from actual code |
| Diagrams | Skills for DBML database schemas (ERD) and Draw.io diagrams (flowcharts, architecture, UML) |
| Frontend design | Skill for distinctive, production-grade UI components that avoid generic AI aesthetics |
| Documentation | README generator/editor, CLAUDE.md auditor, and session-based learning capture |
| Security hook | Pre-edit hook that detects dangerous patterns (eval, innerHTML, os.system, command injection in GitHub Actions) |
| Guided workflows | 7-phase feature development command with discovery, architecture, implementation, and review |
| Agent | Description |
|---|---|
code-architect | Designs feature architectures with implementation blueprints |
code-explorer | Traces execution paths and maps architecture layers |
code-reviewer | Reviews code with confidence-based filtering (threshold ≥ 80%) |
test-generator | Generates comprehensive test suites adapted to the project's patterns |
refactoring-advisor | Detects code smells and proposes safe refactoring plans |
performance-auditor | Identifies bottlenecks (N+1, re-renders, memory leaks) with P0–P2 scoring |
| Skill | Description |
|---|---|
api-docs | Generates API documentation (OpenAPI, Markdown, Postman) from code |
dbml | Creates database schemas in DBML, visualizable as ERD in VS Code |
drawio | Creates Draw.io diagrams in XML (flowcharts, architecture, UML) |
frontend-design | Builds distinctive, production-grade frontend interfaces |
readme-editor | Generates and edits structured, high-quality README files |
claude-md-improver | Audits and improves CLAUDE.md files with quality scoring |
| Command | Description |
|---|---|
feature-dev | Guided feature development in 7 phases (discovery → summary) |
readme-generate | Generates a complete README from the actual codebase |
revise-claude-md | Updates CLAUDE.md with learnings from the current session |
| Hook | Trigger | Description |
|---|---|---|
security_reminder_hook | PreToolUse on Edit/Write | Warns about security anti-patterns (eval, innerHTML, command injection, pickle, os.system, etc.) — once per rule per file per session |
am-plugin/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── agents/
│ ├── code-architect.md
│ ├── code-explorer.md
│ ├── code-reviewer.md
│ ├── performance-auditor.md
│ ├── refactoring-advisor.md
│ └── test-generator.md
├── commands/
│ ├── feature-dev.md
│ ├── readme-generate.md
│ ├── readme.md
│ └── revise-claude-md.md
├── hooks/
│ ├── hooks.json
│ └── security_reminder_hook.py
├── skills/
│ ├── api-docs/
│ ├── claude-md-improver/
│ ├── dbml/
│ ├── drawio/
│ ├── frontend-design/
│ └── readme-editor/
├── mcp.json # Serena MCP server config
├── LICENSE
└── README.md
claude plugin add /path/to/am-plugin
Or reference it in your .claude/settings.json:
{
"plugins": ["/path/to/am-plugin"]
}
The plugin includes a Serena MCP server configuration for semantic code analysis (symbol navigation, referencing, renaming). It is configured in mcp.json and requires uvx to be available.
npx claudepluginhub astyanm/claude-am-plugin --plugin am-pluginDocumentation generation with API docs, architecture diagrams, and tutorials
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>.
Use this agent when you need to analyze a service or codebase component and create comprehensive documentation in CLAUDE.md files. This agent should be invoked after implementing new services, major refactoring, or when documentation needs updating to reflect the current codebase structure. Examples: <example>Context: The user has just implemented a new authentication service and wants to document it properly. user: 'I just finished implementing the auth service, can you document how it works?' assistant: 'I'll use the codebase-documenter agent to analyze the authentication service and create detailed documentation in CLAUDE.md' <commentary>Since the user has completed a service implementation and needs documentation, use the Task tool to launch the codebase-documenter agent to create comprehensive CLAUDE.md documentation.</commentary></example> <example>Context: The user wants to ensure a newly added API module is properly documented for the team. user: 'We need documentation for the new payment processing API I just added' assistant: 'Let me use the codebase-documenter agent to analyze the payment processing API and create proper documentation' <commentary>The user needs documentation for a new API module, so use the codebase-documenter agent to create CLAUDE.md files with setup instructions and architectural notes.</commentary></example>
코드 리뷰, API 설계, 테스트 생성 등 개발 관련 스킬 모음
Documentation generation, code explanation, and technical writing with automated doc generation and tutorial creation
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review