indie-stack

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation.

Execute plan in batches with review checkpoints

Create detailed implementation plan with bite-sized tasks

Use this agent to review Supabase backend code including Edge Functions, RLS policies, database schema, and TypeScript/Deno patterns. Examples: <example>Context: User has written a new Edge Function. user: "The grade-pour edge function is ready for review" assistant: "Let me use the backend-reviewer agent to check the TypeScript patterns, error handling, and security" <commentary>Edge Functions need review for error handling, request validation, and proper Supabase client usage.</commentary></example> <example>Context: User has added new RLS policies. user: "I've set up the RLS policies for the pours table" assistant: "I'll have the backend-reviewer verify the security policies are correct and complete" <commentary>RLS policies are security-critical and need careful review for coverage and correctness.</commentary></example>

Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Great work! Now let me use the code-reviewer agent to review the implementation against our plan and coding standards" <commentary>Since a major project step has been completed, use the code-reviewer agent to validate the work against the plan and identify any issues.</commentary></example> <example>Context: User has completed a significant feature implementation. user: "The API endpoints for the task management system are now complete - that covers step 2 from our architecture document" assistant: "Excellent! Let me have the code-reviewer agent examine this implementation to ensure it aligns with our plan and follows best practices" <commentary>A numbered step from the planning document has been completed, so the code-reviewer agent should review the work.</commentary></example>

Use this agent to review Swift/SwiftUI code for iOS platform best practices, Swift 6 concurrency correctness, and Apple platform patterns. Examples: <example>Context: User has implemented a new SwiftUI view. user: "I've finished the SettingsView implementation" assistant: "Let me use the ios-reviewer agent to check the SwiftUI patterns and Swift concurrency usage" <commentary>SwiftUI code needs platform-specific review for state management and Swift 6 concurrency.</commentary></example> <example>Context: User has written a new service actor. user: "The SyncService actor is complete with async/await patterns" assistant: "I'll have the ios-reviewer check the actor isolation and Sendable conformance" <commentary>Swift 6 strict concurrency requires careful review of actor boundaries and data flow.</commentary></example>

Use this agent to review user experience and UI quality. Catches issues that technical reviewers miss: confusing flows, missing feedback states, accessibility gaps, and inconsistent patterns. Examples: <example>Context: User has implemented a new feature flow. user: "The capture flow is complete with camera, preview, and result screens" assistant: "Let me use the ux-reviewer agent to evaluate the user experience and identify any UX issues" <commentary>Multi-screen flows need UX review for clarity, feedback, and consistency.</commentary></example> <example>Context: User has added a destructive action. user: "I've added the delete pour functionality" assistant: "I'll have the ux-reviewer check for proper confirmation dialogs and undo options" <commentary>Destructive actions require careful UX review for safeguards.</commentary></example>

MUST use before building features, creating components, adding functionality, or designing new behavior. Use when user says 'build', 'create', 'add feature', 'implement', 'design', or describes something new to build. Explores requirements through questions before writing code.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when executing implementation plans with independent tasks. Features 3-stage review: spec compliance, code quality, then UX.

1 hook across 1 event