act

Generate or update AGENTS.md for the current project.

Architectural consultation from four specialised advisors — Systems Designer, Technology Strategist, Scalability Consultant, and Risk Analyst.

Generate a CHANGELOG.md entry from git history since the last tag.

Inspect staged changes and create a conventional git commit.

Investigate a bug using root-cause-first methodology.

Use this agent immediately after any code changes are made - including function implementations, class definitions, refactoring work, or new feature additions. The agent proactively reviews recently written code (not the entire codebase unless explicitly requested) for quality, SOLID principles, best practices, and maintainability.\n\nExamples of when to invoke this agent:\n\n<example>\nContext: User has just implemented a new authentication function.\nuser: "Please implement a function that validates JWT tokens and returns the decoded payload"\nassistant: "Here's the JWT validation function:"\n```typescript\nfunction validateJWT(token: string): JwtPayload | null {\n // implementation details...\n}\n```\n<commentary>\nSince a significant piece of code was just written, proactively use the Agent tool to launch the code-reviewer agent to review the implementation for quality, security, and best practices.\n</commentary>\nassistant: "Now let me review this implementation for quality and best practices."\n</example>\n\n<example>\nContext: User has completed refactoring a class structure.\nuser: "I've refactored the UserService class to extract validation logic into a separate Validator class"\nassistant: "Great! Let me review the refactored code to ensure it follows SOLID principles and maintains good design."\n<commentary>\nUse the code-reviewer agent proactively since code changes were completed.\n</commentary>\n</example>\n\n<example>\nContext: User has added a new feature with multiple files.\nuser: "I've added the payment processing module with the PaymentProcessor, PaymentGateway, and TransactionLogger classes"\nassistant: "Excellent! Let me review the new payment processing module for code quality, design patterns, and potential issues."\n<commentary>\nLaunch the code-reviewer agent since new code was added to the codebase.\n</commentary>\n</example>

PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.

End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

Use this agent when you need to architect and plan feature implementations, break down complex requirements into discrete iterations, or create a roadmap for software development tasks. This agent excels at creating concise, actionable plans with clear TDD cycles. Use PROACTIVELY when users request feature implementation, architectural guidance, or complex system design. Active automatically for planning tasks. \n\nExamples:\n\n<example>\nContext: User needs to implement a new authentication system with OAuth support.\nuser: "I need to add OAuth authentication to our Express API"\nassistant: "Let me use the planner agent to create a structured plan for adding OAuth authentication to your API."\n<commentary>\nSince this is a significant feature implementation requiring architecture decisions, use the planner agent to break it down into discrete iterations with TDD cycles.\n</commentary>\n</example>\n\n<example>\nContext: User wants to implement a complex data synchronization feature.\nuser: "We need to sync data between our PostgreSQL database and Elasticsearch"\nassistant: "I'll launch the planner agent to architect a synchronization solution with clear implementation steps."\n<commentary>\nData synchronization requires careful planning of architecture, error handling, and testing strategies. The planner agent will provide a roadmap with discrete iterations.\n</commentary>\n</example>\n\n<example>\nContext: User is starting a new microservice.\nuser: "Create a plan for building a notification microservice"\nassistant: "I'm going to use the planner agent to create an implementation roadmap for the notification microservice."\n<commentary>\nBuilding a new microservice requires architectural decisions and a phased implementation approach. The planner agent will structure this into clear iterations.\n</commentary>\n</example>

Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.

Guide Test-Driven Development workflow (Red-Green-Refactor) for new features, bug fixes, and refactoring. Supports both Python (pytest) and Ruby (RSpec). Use when writing tests, implementing features, or following TDD methodology. **PROACTIVE ACTIVATION**: Auto-invoke when implementing features or fixing bugs in projects with test infrastructure. **DETECTION**: Check for tests/ directory, pytest.ini, pyproject.toml with pytest config, spec/ directory, .rspec file, or *_spec.rb files. **USE CASES**: Writing production code, fixing bugs, adding features, legacy code characterization.

TypeScript expert guidance for type-level programming, performance optimization, migrations, and real-world problem solving. **PROACTIVE ACTIVATION**: Auto-invoke when working with .ts/.tsx files, encountering type errors, discussing types/generics/interfaces, or configuring TypeScript. **DETECTION**: Check for tsconfig.json, .ts/.tsx files, types/ directory, @types/ packages, or TypeScript-related imports. **USE CASES**: Type errors, generics, tsconfig setup, module resolution, JS→TS migration, type performance, monorepo configuration, declaration files, branded types, conditional types, type testing.

Create, optimize, and maintain AGENTS.md and CLAUDE.md files using progressive disclosure. Use when: User wants to create AGENTS.md/CLAUDE.md, optimize existing AI documentation, implement progressive disclosure, detect project structure (monorepo/polyrepo), or prevent documentation bloat. Triggers on: "create agents.md", "update AGENTS.md", "AI documentation", "project context", "monorepo documentation", "progressive disclosure", "Claude Code context", or when AI repeatedly asks the same questions about the project.

Orchestrates a complete software release: pre-flight checks, changelog update, version bump, git tag, and GitHub release. Use when cutting a release, tagging a version, or publishing a new version of the project. **PROACTIVE ACTIVATION**: Invoke when user says 'release', 'cut a release', 'tag a release', 'ship v1.x', 'publish version', or '/release'. **USE CASES**: Tagging main after a sprint, releasing a library version, preparing a versioned deployment.

Docker containerization guide covering Dockerfile authoring, multi-stage builds, image optimization, security hardening, Docker Compose for local development, and .dockerignore best practices. Use PROACTIVELY when creating or editing Dockerfiles, docker-compose.yml files, containerizing an application, or troubleshooting Docker build and runtime issues. **PROACTIVE ACTIVATION**: Invoke on Dockerfile, docker-compose, 'containerize', 'docker build', 'container won't start', or any task involving images, volumes, or container networking. **USE CASES**: New Dockerfile, optimizing image size, adding health checks, setting up multi-service local dev environment, fixing build failures, securing containers.