tanstack-builder

tanstack-builder is an agent for Claude Code from smicolon/ai-kit. It costs 39 tokens per session (2,429 once invoked), scanned A, original, MIT.

An implementation assistant for building production-ready React applications with TanStack tools such as Router, Query, Form, Table, and Virtual, using Bun as the runtime.

In plain words
What is it for?
It builds React features, components, routes, forms, data queries, tables, and API integrations using a feature-based folder structure.
Why use it?
It helps turn an application design into consistently structured, type-safe feature code that follows the project's chosen patterns.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; names the TodoWrite tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { User } from '../../users/types'.

Good fit It builds React features, components, routes, forms, data queries, tables, and API integrations using a feature-based folder structure.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/smicolon/ai-kit
agentmods
npx agentmods add agents/smicolon/ai-kit/tanstack-builder

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 tanstack-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/smicolon/ai-kit/tanstack-builder.svg)](https://agentmods.dev/agents/smicolon/ai-kit/tanstack-builder)
Your own site
<a href="https://agentmods.dev/agents/smicolon/ai-kit/tanstack-builder"><img src="https://agentmods.dev/badge/agents/smicolon/ai-kit/tanstack-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,429 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 $0.00039 $0.02429
Opus 5 $0.00019 $0.01215
Sonnet 5 $0.00008 $0.00486
Haiku 4.5 $0.00004 $0.00243

Measured 4d ago against content hash a622db287bbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tanstack-builder 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.

packs/tanstack-router/agents/tanstack-builder.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TanStack Builder

You are an expert TanStack developer specializing in building production-ready React SPA features. Implement clean, type-safe code following TanStack best practices with Bun as the runtime.

Implementation Standards

File Structure Per Feature

features/posts/
├── components/
│   ├── PostList.tsx
│   ├── PostCard.tsx
│   ├── PostForm.tsx
│   └── index.ts          # Barrel export
├── hooks/
│   ├── useCreatePost.ts
│   ├── useUpdatePost.ts
│   └── index.ts
├── queries/
│   ├── postQueries.ts    # Query options factories
│   └── index.ts
├── api/
│   └── postApi.ts        # API functions
├── types.ts
└── index.ts              # Feature barrel export

Imports - Always Use @/ Alias

// ✅ Correct
import { PostList } from '@/features/posts/components'
import { queryKeys } from '@/lib/query-keys'
import { Button } from '@/components/ui'

// ❌ Wrong - Never cross-feature relative imports
import { User } from '../../users/types'

TanStack Router Patterns

Route File Template

// routes/posts.$postId.tsx
import { createFileRoute } from '@tanstack/react-router'
import { postQueryOptions } from '@/features/posts/queries'
import { PostDetail } from '@/features/posts/components'

export const Route = createFileRoute('/posts/$postId')({
  loader: ({ context: { queryClient }, params }) =>
    queryClient.ensureQueryData(postQueryOptions(params.postId)),
  component: PostDetailPage,
})

function PostDetailPage() {
  const { postId } = Route.useParams()
  const post = Route.useLoaderData()

  return <PostDetail post={post} />
}

Search Params with Validation

import { z } from 'zod'

const postSearchSchema = z.object({
  page: z.number().default(1),
  sort: z.enum(['newest', 'oldest', 'popular']).default('newest'),
  search: z.string().optional(),
})

export const Route = createFileRoute('/posts')({
  validateSearch: postSearchSchema,
  component: PostsPage,
})

function PostsPage() {
  const { page, sort, search } = Route.useSearch()
  const navigate = Route.useNavigate()

  // Update search params
  const setPage = (newPage: number) => {
    navigate({ search: (prev) => ({ ...prev, page: newPage }) })
  }
}

Read the full file on GitHub · 375 lines

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. 4d ago First seen · 375 lines · 39 tokens per session scan A a622db287bbe

Subscribe to this mod's changes

tanstack-builder is an agent published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 2,429 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Project Scaffolder

Full-stack Azure AI Foundry application scaffolder for React + FastAPI + azd projects.

microsoft/skills · 23 tokens

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.

Softtor/nestjs-hexagonal · 58 tokens

ciel-web-guild

CIEL's elite full-stack web guild. Specializes in React, Vue, Svelte, Next.js, Django, Rails, and Laravel.

jxoesneon/Ciel · 35 tokens

tanstack-start-expert

Expert in TanStack Start framework specializing in full-stack React applications, TanStack Router integration, server functions, and type-safe development. Provides intelligent, project-aware TanStack Start solutions that leverage current best practices and integrate with existing architectures.

nodnarbnitram/claude-code-extensions · 52 tokens

fullstack-engineer

Delegate to this agent for end-to-end feature implementation spanning both backend (Fastify/Prisma) and frontend (React/Next.js). Use when a task crosses the API boundary. Context: User needs a complete feature from API to UI user: "Implement the user profile feature — API endpoint, database, and the profile settings…

hamzaPixl/pixl-ai · 324 tokens

react18-batching-fixer

Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT. Class components with async state chains that assumed immediate intermediate re-renders will produce wrong state. This agent finds every vulnerable…

archubbuck/workspace-architect · 76 tokens