Claude Code plugin that orchestrates a team of specialized AI agents for full-cycle software development with inline quality gates
Agent
Internal orchestration agent for mandatory adversarial review of a newly created or revised PRD or execution plan. Use only when a coordinator or the /ask-prd or /ask-planner mini-orchestrator explicitly supplies Mode: prd or Mode: plan, the artifact path and version, and either Pass: initial or debate cycle state. Do…
Agent
Use this agent when a system or feature needs architectural design — component structure, interfaces, data flow, and technical decisions. Works for both greenfield projects and extensions to existing codebases. This is a read-only designer — it cannot modify files. Context: Starting a new project from scratch user…
Agent
Use this agent when the task involves server-side implementation — API endpoints, data models, services, middleware, authentication, or database operations. Framework-agnostic: skills provide NestJS/Django/FastAPI/etc. knowledge. Context: A new API endpoint needs to be built user: "Create a REST endpoint for user…
Agent
Use this agent when code changes need to be reviewed for quality, bugs, and adherence to project conventions. This is a read-only reviewer — it cannot modify files. Context: A development task has been completed and needs quality verification user: "Review the authentication changes for bugs and code quality"…
Agent
Use this agent when documentation produced by other agents needs critical review — PRDs, architecture blueprints, design specifications, API specs, and execution plans. This is a read-only reviewer — it cannot modify files. Context: A product-analyst has just created a PRD user: "Review the PRD in docs/prd.md for…
Agent
Use this agent when the task involves UI implementation — building components, pages, forms, layouts, styling, or client-side logic. Framework-agnostic: skills provide React/Vue/Svelte/etc. knowledge. Context: A new UI feature needs to be built user: "Build a user registration form with validation" assistant: "I'll…
Agent
Use this agent when the task is not clearly frontend or backend — scripts, configuration, CLI tools, DevOps, utilities, refactoring, or cross-cutting changes. General-purpose fallback for code work that doesn't fit frontend-dev or backend-dev. Context: A build or deployment script needs to be created user: "Write a…
Agent
Use this agent when a task needs to be analyzed, decomposed into subtasks, and organized into an execution plan. It reads source and test files without modifying them and writes only the normative execution plan under docs/. Context: A complex feature request needs to be broken down before implementation user: "Plan…
Agent
Use this agent when requirements need to be formalized before design or implementation — extracting functional requirements, non-functional requirements, user stories, constraints, and acceptance criteria from a user's request. This agent creates the PRD (Product Requirements Document) that all other agents reference…
Agent
Use this agent when tests need to be written, run, or analyzed. Handles unit tests, integration tests, and end-to-end tests. Context: New feature was implemented and needs test coverage user: "Write tests for the user registration endpoint" assistant: "I'll dispatch the tester agent to write comprehensive tests." Test…
Agent
Use this agent when a user interface needs to be designed before implementation — screen layouts, user flows, component hierarchy, interaction patterns, and information architecture. This is a read-only designer that produces specifications, not code. Context: A new feature needs UX design before building user…