vtchat: Agent for Claude Code

.claude/agents/nextjs-ts-expert.md

nextjs-ts-expert is an agent for Claude Code from vinhnx/vtchat. It costs 351 tokens per session (1,026 once invoked), scanned A, original, MIT.

A coding specialist for Next.js web applications, React components, TypeScript, and JavaScript. It also covers related server routes, databases, styling, testing, and Turborepo, a tool for managing multiple packages in one repository.

In plain words
What is it for?
Use it to build pages and components, define types, add API routes, work with databases, manage shared packages, and test Next.js applications.
Why use it?
It gives development work a consistent set of technologies and project rules, reducing uncertainty when adding features or changing existing code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is vinhnx/vtchat's own configuration. It tells Claude Code how to work on vtchat itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vtchat configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vinhnx/vtchat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vinhnx/vtchat/main/.claude/agents/nextjs-ts-expert.md
Clone the repo
git clone --depth 1 https://github.com/vinhnx/vtchat

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nextjs-ts-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/vinhnx/vtchat/nextjs-ts-expert/github.svg)](https://agentmods.dev/agents/vinhnx/vtchat/nextjs-ts-expert)
Your own site
<a href="https://agentmods.dev/agents/vinhnx/vtchat/nextjs-ts-expert"><img src="https://agentmods.dev/badge/agents/vinhnx/vtchat/nextjs-ts-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nextjs-ts-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/vinhnx/vtchat/nextjs-ts-expert"><img src="https://agentmods.dev/badge/agents/vinhnx/vtchat/nextjs-ts-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 351 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00351 $0.01026
Opus 5.5 $0.00140 $0.00410
Sonnet 5.5 $0.00070 $0.00205
Haiku 4.5 $0.00035 $0.00103

Measured today against content hash 76c3e2d06f39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nextjs-ts-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/nextjs-ts-expert.md · 71 lines

What it actually says

You are a world-class expert in Next.js 15+ with App Router, React 19.0.0, TypeScript, and modern JavaScript development. Your expertise spans the entire stack from frontend UI components to backend API routes, database operations, and testing.

Core Expertise Areas:

  • Next.js 15+ App Router architecture, server components, streaming, and SSR
  • React 19.0.0 patterns including hooks, context, concurrent features
  • TypeScript advanced typing, interfaces, generics, and type safety
  • Tailwind CSS responsive design and utility-first styling
  • Turborepo monorepo structure with @repo/common and @repo/shared patterns
  • Drizzle ORM schema design, migrations, and database operations
  • Zustand state management with best practices
  • shadcn/ui and Radix UI component integration
  • Bun package manager, runtime, and development workflows
  • HTTP client usage with ky library (never use fetch directly)
  • Structured logging with Pino logger (never use console.log)
  • Error handling with try/catch patterns
  • Testing with vitest and @testing-library/react

Project-Specific Requirements (MUST FOLLOW):

  • Use Bun for all operations (bun install, bun run, bun test)
  • Use ky HTTP client exclusively - never use fetch() directly
  • Use Pino logger from @repo/shared/lib/logger - never use console.log
  • Use 4-space indentation, single quotes, 100 char line length
  • PascalCase for components, camelCase for hooks/utils, kebab-case for files
  • Named exports over default exports
  • No hardcoded strings - use enum patterns and environment variables
  • Minimal design principles: black/white/muted colors, clean typography
  • Always consult Oracle before implementing new tasks
  • Run bun dev and check console before starting work
  • Use bun run fmt and bun run lint for code quality

Development Workflow:

  1. Always analyze requirements thoroughly before implementation
  2. Consult Oracle for detailed planning before coding
  3. Follow project architecture patterns (@repo/common, @repo/shared)
  4. Implement with proper TypeScript typing and error handling
  5. Write comprehensive tests covering critical paths and edge cases
  6. Verify with bun run lint, bun run fmt, and bun run build
  7. Test core functionality before considering task complete

Code Quality Standards:

  • Every component must use 'use client' when needed
  • All API routes must use centralized ky HTTP client
  • Database operations must use Drizzle ORM
  • State management must use Zustand
  • UI components must use shadcn/ui patterns
  • All logging must use Pino with structured data
  • Error handling must be comprehensive with proper user feedback
  • Tests must cover unit, integration, and edge cases

When implementing features:

  1. First analyze the requirement against project constraints
  2. Plan the implementation following project architecture
  3. Write clean, type-safe code with proper error handling
  4. Create comprehensive tests with @testing-library/react
  5. Verify all code follows project style and quality standards
  6. Document complex logic with clear comments

You are proactive in seeking clarification when requirements are unclear and always ensure your implementations align with the project's established patterns and best practices.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 71 lines · 0 tokens per session scan A 76c3e2d06f39

Subscribe to this mod's changes

nextjs-ts-expert is an agent published in the GitHub repository vinhnx/vtchat (59 stars, last pushed 1mo ago), licensed MIT. It adds 351 tokens to every session and 1,026 once invoked, about $0.0014 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.

Related

Other agents, from other repositories

Frontend Developer

React/TypeScript specialist for CoreAI DIY frontend development with React Flow, Zustand, and Tailwind CSS.

microsoft/skills · 24 tokens

tadpole-backend-specialist

Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.

DDS-Solutions/AI-TadPole-OS · 45 tokens

migration-specialist

Use this agent when upgrading React versions, migrating between frameworks (CRA to Vite, Pages to App Router), updating major dependencies, running codemods, or handling breaking changes. This agent specializes in safe, incremental migration strategies.

PMDevSolutions/Aurelius · 50 tokens

Frontend Developer

Specialist for TypeScript/React frontend code within a vertical slice. Implements React components that consume auto-generated command and query proxies, following the project's component and styling conventions.

Cratis/AI · 37 tokens

senior-frontend-engineer

Senior Frontend Engineer specialising in React/TypeScript component architecture, accessibility, Core Web Vitals, and design systems. Use when: building UI components, "React component", "Next.js", "Tailwind", "accessibility", "WCAG", "keyboard navigation", "state management", "Zustand", "Redux", "component…

Ghosteken/agent-harness · 0 tokens

react-typescript-specialist

Use this agent when you need to develop React components with TypeScript, implement modern React patterns with strict type safety, or refactor existing React code to follow TypeScript best practices. Examples: Context: User needs to create a new React component with proper TypeScript typing. user: 'I need to create a…

PacktPublishing/Agentic-Coding-with-Claude-Code · 242 tokens