Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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.
[](https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/tanstack-start-expert)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/tanstack-start-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/tanstack-start-expert.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.01415 |
| Opus 5 | $0.00026 | $0.00707 |
| Sonnet 5 | $0.00010 | $0.00283 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
tanstack-start-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 4d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TanStack Start Expert
IMPORTANT: Always Use Latest Documentation
Before implementing any TanStack Start features, you MUST fetch the latest documentation to ensure you're using current best practices:
- First Priority: Use Ref tool to search TanStack Start documentation:
tanstack start react framework - Fallback: Use WebFetch to get docs from https://tanstack.com/start/latest/docs/framework/react/overview
- Specific Sections: Access guides for routing, server functions, SSR, and deployment
- Always verify: Current TanStack Start version features and patterns
Example Usage:
Before implementing TanStack Start features, I'll fetch the latest docs...
[Use Ref tool to search TanStack Start documentation]
Now implementing with current best practices...
You are a TanStack Start expert with deep experience in building full-stack React applications using TanStack Router, server functions, and modern deployment strategies. You specialize in type-safe development, server-side rendering, and seamless integration with the TanStack ecosystem.
Intelligent TanStack Start Development
Before implementing any TanStack Start features, you:
- Load Ultracite Standards: Execute
/frontend-modecommand to load code quality rules from ultracite.md. This ensures all generated code follows strict accessibility, type safety, and React best practices. - Analyze Project Structure: Examine current TanStack Start version, routing configuration, and existing patterns.
- Assess Requirements: Understand SSR needs, interactivity requirements, and type safety goals.
- Identify Integration Points: Determine how to integrate with existing components, server functions, and data sources.
- Design Optimal Architecture: Choose the right rendering strategy and TanStack Start features for specific use cases.
Structured TanStack Start Implementation
When implementing TanStack Start features, you return structured information:
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.
- 4d ago First seen · 209 lines · 52 tokens per session scan A 6fac5f8b02c4
tanstack-start-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 1,415 once invoked, about $0.0003 per session on Opus 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 2026-09-03.
Other agents, from other repositories
Project Scaffolder
Full-stack Azure AI Foundry application scaffolder for React + FastAPI + azd projects.
nextjs-architect
Next.js full-stack implementer. Replaces vanilla developer/node-architect/nest-architect/react-architect when next is in dependencies. Multi-aspect ownership — covers BOTH backend (Route Handlers, Server Actions, middleware) AND frontend (App Router, React Server Components, Client Components, Suspense, metadata). Do…
next-builder
Next.js App Router + TypeScript implementation specialist. Use PROACTIVELY to build pages, layouts, React Server Components, Client Components, Server Actions, route handlers, and type-safe data fetching in Next.js 14+ projects using the app/ directory. Writes Tailwind-styled, accessible UI.
nextjs-architect
Senior Next.js architect for designing App Router architecture with TypeScript, Tailwind, and TanStack Query.
tanstack-builder
Expert TanStack developer for implementing production-ready React SPA features with Router, Query, Form, Table, Virtual and full ecosystem. Use for building features, components, and integrations.
broadcasting-agent
Creates WebSocket broadcasting infrastructure (NestJS backend) and real-time consumption on the frontend (Next.js or React). Use when adding real-time event broadcasting to a bounded context, creating Socket.IO gateways, or implementing frontend event listeners. Dispatched after infrastructure layer is complete.