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)

Search across agents, skills, and tools to find relevant capabilities.

Manage precision_fetch service registry (add, remove, test, auth)

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".

External services specialist for payment processing (Stripe, LemonSqueezy, Paddle), email services (Resend, SendGrid, Postmark, React Email), CMS platforms (Sanity, Contentful, Strapi, Payload, Directus), and file uploads (UploadThing, Cloudinary, S3). Use PROACTIVELY when user mentions: payment, Stripe, checkout, subscription, billing, invoice, LemonSqueezy, Paddle, email, Resend, SendGrid, Postmark, React Email, transactional email, newsletter, CMS, Sanity, Contentful, Strapi, Payload, Directus, headless CMS, blog, content management, upload, UploadThing, Cloudinary, S3, media, image optimization, file upload. Triggers on: "integrate payments", "setup Stripe", "accept payments", "subscription billing", "send emails", "email templates", "setup CMS", "content management", "upload files", "image upload", "media management".

State management, forms with validation, and real-time features specialist. Use PROACTIVELY when user mentions: state, store, global state, client state, server state, cache, Zustand, Redux, Jotai, TanStack Query, React Query, SWR, form, validation, schema, Zod, Yup, React Hook Form, Formik, real-time, WebSocket, Socket.IO, Pusher, Ably, Liveblocks, collaborative, live updates, subscriptions. Also trigger on: "manage state", "create store", "add form", "validate input", "real-time sync", "live collaboration", "optimistic update", "cache invalidation".

GoodVibes planning expert. Use PROACTIVELY when designing implementation strategies, breaking down complex tasks, planning batch operations, orchestrating multi-agent workflows, or when the user needs a detailed execution plan. Triggers on plan, strategy, breakdown, orchestrate, design approach, batch planning, workflow design, execution plan, parallel execution, agent coordination.

Code review specialist enforcing enterprise-grade standards. Use PROACTIVELY when reviewing PRs, auditing code changes, performing quality assessments, or when user needs direct feedback on code correctness, security, performance, and adherence to project patterns.

Creates high-quality Agent Skills and Claude Code slash commands. Use PROACTIVELY when users want to create, update, or improve skills/slash commands that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Testing specialist for comprehensive test coverage. Use PROACTIVELY when: writing tests (unit, integration, E2E), improving test coverage, fixing failing tests, setting up test infrastructure, mocking APIs/data, debugging flaky tests, or when user mentions Vitest, Jest, Playwright, Cypress, Testing Library, MSW, coverage, TDD, fixtures, snapshots, or assertions. Enforces 100% coverage goal with no skips and no auto-pass.

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).

Load PROACTIVELY when task involves designing or building UI components. Use when user says "build a component", "create a form", "add a modal", "design the layout", or "refactor this page". Covers component composition and hierarchy, prop design and typing, render optimization (memo, useMemo, useCallback), compound component patterns, controlled vs uncontrolled forms, file organization, and accessibility for React, Vue, and Svelte.

Load PROACTIVELY when task involves database design, schemas, or data access. Use when user says "set up the database", "create a schema", "add a migration", "write a query", or "set up Prisma". Covers schema design and normalization, ORM setup (Prisma, Drizzle), migration workflows, connection pooling, query optimization, indexing strategies, seeding, and transaction patterns for PostgreSQL, MySQL, SQLite, and MongoDB.

Load PROACTIVELY when task involves deploying, hosting, or CI/CD pipelines. Use when user says "deploy this", "set up CI/CD", "add Docker", "configure Vercel", or "set up monitoring". Covers platform-specific deployment (Vercel, Railway, Fly.io, AWS), Dockerfile creation, environment variable management, CI/CD pipeline configuration (GitHub Actions), preview deployments, health checks, rollback strategies, and production monitoring setup.

Load PROACTIVELY when task involves payments, billing, or subscriptions. Use when user says "add payments", "integrate Stripe", "set up subscriptions", "add a checkout flow", or "handle billing webhooks". Covers Stripe, LemonSqueezy, and Paddle integration, checkout sessions, subscription lifecycle management, webhook verification and handling, customer portal, metered billing, refunds, and PCI compliance considerations.

Load PROACTIVELY when task involves connecting external services or third-party APIs. Use when user says "add email sending", "integrate a CMS", "set up file uploads", "add analytics", or "connect to S3". Covers email services (Resend, SendGrid), CMS platforms (Sanity, Contentful, Payload), file upload solutions (UploadThing, Cloudinary, S3), analytics integration, webhook handling, error recovery, and credential management.

Load PROACTIVELY when task involves application state, data fetching, or form handling. Use when user says "manage state", "add data fetching", "set up Zustand", "handle form validation", or "add React Query". Covers server state (TanStack Query with caching, optimistic updates), client state (Zustand stores), form state (React Hook Form with Zod validation), URL state (search params, routing), and choosing between state solutions.

Load PROACTIVELY when task involves CSS architecture, theming, or visual design systems. Use when user says "set up Tailwind", "add dark mode", "create a design system", "make it responsive", or "configure the theme". Covers Tailwind configuration and custom plugins, design token systems, responsive breakpoint strategies, dark mode implementation, component variant patterns (CVA/class-variance-authority), CSS-in-JS alternatives, and animation patterns.

Load PROACTIVELY when task involves writing tests, improving coverage, or test infrastructure. Use when user says "add tests", "write unit tests", "set up E2E testing", "improve coverage", or "add mocks". Covers Vitest/Jest unit tests, React Testing Library component tests, Playwright E2E tests, MSW API mocking, test organization and naming, fixture management, coverage targets and thresholds, snapshot testing, and CI integration.

ALWAYS load before starting any task. Defines systematic recovery procedures when things go wrong during execution. Covers tool failures, build errors, test failures, type errors, and unexpected runtime results. Includes tiered escalation (retry, fallback, memory-informed diagnosis, orchestrator escalation) and post-recovery logging to prevent recurrence.

MANDATORY before starting any task. Enforces the GPA execution loop that prevents tool call sprawl. G: GATHER phase combines discover queries + memory reads + file reads into one phase. P: Plan in text with zero tool calls. A: APPLY all writes/edits/verification in one phase. One call per tool type per phase — batch all same-type operations together. Covers dependency analysis, batch opportunities, scope estimation, and loop-back triggers.

ALWAYS load before starting any task. Provides persistent cross-session memory for learning from past work. Read memory at task start to avoid repeating mistakes; write memory at task end to record what worked. Covers decisions.json (architectural choices), patterns.json (proven approaches), failures.json (past errors and fixes), preferences.json (project conventions), and session activity logs.

ALWAYS load before starting any task. Maximizes token efficiency for all file operations, searches, and command execution. Covers extract modes (content, outline, symbols, ast, lines), verbosity tuning, multi-file batching, and discover tool orchestration. Ensures agents spend tokens on outcomes, not overhead.

ALWAYS load before starting any task. Provides the 10-dimension weighted scoring rubric (0-10 scale) used to evaluate all implementations in WRFC loops. Dimensions include correctness, completeness, error handling, type safety, security, performance, maintainability, testing, accessibility, and documentation. Includes deterministic validation scripts and score thresholds for pass/revise/reject decisions.

Load PROACTIVELY when task involves accessibility compliance or inclusive design. Use when user says "check accessibility", "audit for WCAG", "fix screen reader issues", "add keyboard navigation", or "check color contrast". Covers WCAG 2.1 AA compliance across semantic HTML, ARIA patterns, keyboard navigation, screen reader support, color contrast ratios, form accessibility, media alternatives, and focus management. Produces structured audit reports with severity ratings.

Load PROACTIVELY when task involves reviewing code, auditing quality, or validating implementations. Use when user says "review this code", "check this PR", "audit the codebase", or "score this implementation". Covers the 10-dimension weighted scoring rubric (correctness, security, performance, architecture, testing, error handling, type safety, maintainability, accessibility, documentation), automated pattern detection for anti-patterns, and structured review output with actionable findings.

Load PROACTIVELY when task involves investigating errors, diagnosing failures, or tracing unexpected behavior. Use when user says "debug this", "fix this error", "why is this failing", "trace this issue", or "it's not working". Covers error message and stack trace analysis, runtime debugging, network request inspection, state debugging, performance profiling, type error diagnosis, build failure resolution, and root cause analysis with memory-informed pattern matching against past failures.

Load PROACTIVELY when task involves optimizing speed, reducing bundle size, or improving responsiveness. Use when user says "make it faster", "reduce bundle size", "fix slow queries", "optimize rendering", or "check Core Web Vitals". Covers bundle analysis and tree-shaking, database query optimization (N+1, indexing), React rendering performance (re-renders, memoization), network waterfall optimization, memory leak detection, server-side performance, and Core Web Vitals (LCP, FID, CLS) improvement.

Load PROACTIVELY when starting work on an unfamiliar codebase or setting up a new project. Use when user says "help me understand this codebase", "onboard me", "what does this project do", "set up my environment", or "map the architecture". Covers codebase structure analysis, architecture mapping, dependency auditing, convention and pattern detection, developer environment setup, and documentation of findings for rapid productive contribution.

Load PROACTIVELY when task involves improving code structure without changing behavior. Use when user says "refactor this", "clean up this code", "remove dead code", "reduce duplication", "reorganize the files", or "extract this into a function". Covers extract function/component, rename symbol, simplify conditionals, improve type safety, dependency inversion, dead code removal, circular dependency resolution, and database query refactoring with automated safety validation (typecheck, tests) at each step.

Load PROACTIVELY when task involves security review, vulnerability assessment, or hardening. Use when user says "check for security issues", "audit for vulnerabilities", "scan for secrets", "review auth security", or "check OWASP compliance". Covers authentication and session security, authorization and access control, input validation and injection prevention, data protection and encryption, dependency vulnerability scanning, API security (CORS, rate limiting, headers), and infrastructure hardening. Produces structured reports with severity ratings.

14 hooks across 10 events

typescript-language-server