goodvibes

Quick access to GoodVibes analytics-engine features. Tracks token usage, cost, cache performance, file operations, command execution, and agent activity across your Claude session.

Full codebase review with parallel goodvibes agent remediation. Analyzes 10 quality dimensions, generates master report, creates prioritized remediation plan, executes fixes with max 6 parallel goodvibes background agents (one task per agent, fresh context).

Load a skill's full content into context

GoodVibes plugin management commands (update, status, config)

Toggle precision-engine path sandboxing (allow/restrict external paths)

Meta-agent that creates specialized Claude Code subagents. Use when you need to build a new agent for a specific domain. Researches thoroughly, applies SDK patterns, and generates production-ready agent files. For skills, delegates to skill-factory.

Architecture and planning specialist. Use PROACTIVELY when designing system architecture, planning implementation strategies, breaking down complex tasks, identifying dependencies and risks, or making architectural decisions.

Deployment and DevOps specialist. Use PROACTIVELY when deploying applications, configuring CI/CD pipelines, setting up Docker/containerization, deploying to cloud platforms (Vercel, AWS, Railway, Fly.io), configuring environment variables, or setting up monitoring and error tracking. Triggers on: deploy, deployment, hosting, CI/CD, pipeline, Docker, container, Kubernetes, production, staging, environment variables, secrets, monitoring, Sentry, infrastructure.

Unified full-stack engineer for backend and frontend implementation. Use PROACTIVELY when user mentions: API, REST, GraphQL, tRPC, endpoint, route, database, SQL, Prisma, Drizzle, PostgreSQL, MongoDB, Redis, authentication, auth, login, JWT, OAuth, middleware, server, backend, validation, schema, migration, CRUD, component, React, Vue, Svelte, Next.js, Nuxt, Remix, Astro, frontend, page, layout, navigation, modal, form, button, card, table, responsive, CSS, Tailwind, styling, theme, dark mode, shadcn, Radix, animation, Framer Motion, accessibility, SSR, SSG, hydration. Also trigger on: "build an API", "create component", "add authentication", "implement feature", "fix bug", "add page", "build form", "connect database", "style this", "make responsive".

AI and LLM integration specialist for chat interfaces, streaming responses, RAG pipelines, embeddings, vector search, and tool/function calling. Use PROACTIVELY when user mentions: AI, LLM, ChatGPT, Claude, OpenAI, Anthropic, Vercel AI SDK, streaming, chat, completions, embeddings, RAG, vector, Pinecone, Weaviate, pgvector, function calling, tool use, AI agents. Triggers on: "integrate AI", "add chat", "LLM feature", "streaming responses", "RAG pipeline", "vector search", "embeddings", "AI chat interface", "function calling", "tool use".

Load PROACTIVELY when task involves building a complete feature across multiple layers. Use when user says "build a feature", "add user profiles", "create a dashboard", or any request spanning database, API, UI, and tests. Orchestrates multi-agent work sequentially: schema and migrations, API endpoints, UI components, tests, and review. The runtime engine handles WRFC chains automatically via <gv> directives. Handles dependency ordering and cross-layer type sharing.

Load PROACTIVELY when decomposing a user request into parallel agent work. Use when user says "build this", "implement this feature", or any request requiring multiple agents working concurrently. Guides task decomposition into parallelizable units, agent assignment with skill matching, dependency graph construction, and result aggregation. The runtime engine handles WRFC chain coordination automatically via <gv> directives.

Load PROACTIVELY when task involves AI, LLM, or machine learning features. Use when user says "add AI chat", "implement streaming responses", "build a RAG pipeline", "add embeddings", or "integrate OpenAI". Covers chat interfaces, streaming with Vercel AI SDK, retrieval-augmented generation, vector search, embeddings pipelines, tool/function calling, and provider abstraction for OpenAI, Anthropic, and local models.

Load PROACTIVELY when task involves building or modifying API endpoints. Use when user says "build an API", "add an endpoint", "create a REST route", "set up GraphQL", or "add tRPC procedures". Covers route design and file organization, request validation with Zod, response formatting, error handling patterns, middleware composition, authentication guards, rate limiting, pagination, and API documentation generation.

Load PROACTIVELY when task involves user identity, login, or access control. Use when user says "add authentication", "set up login", "add OAuth", "protect these routes", "implement RBAC", or "add sign-up". Covers session management, JWT tokens, OAuth2 flows, password reset, email verification, protected route middleware, role-based access control, and security hardening (CSRF, rate limiting, token rotation).

14 hooks across 10 events

typescript-language-server