ck:tanstack

Guidance for building full-stack React applications with TanStack Start, managing forms with TanStack Form, and adding streaming or chat features with TanStack AI.

In plain words
What is it for?
Use it to create TanStack projects, add routes and server functions, build validated forms, or add AI chat and streaming.
Why use it?
It helps keep routing, server code, form validation, and AI interactions organized when working with TanStack tools.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/manhvann/codexkit/tanstack
Any agent
npx skills add manhvann/codexkit --skill tanstack
Clone the repo
git clone --depth 1 https://github.com/manhvann/codexkit

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,182 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00055 $0.01182
Opus 5 $0.00028 $0.00591
Sonnet 5 $0.00011 $0.00236
Haiku 4.5 $0.00006 $0.00118

Measured 2d ago against content hash 3143ede9939f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ck:tanstack 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 2d 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.

.agents/skills/tanstack/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TanStack

Build full-stack React apps with TanStack Start, manage forms with TanStack Form, and add AI features with TanStack AI.

When to Activate

  • User mentions TanStack Start, TanStack Form, or TanStack AI
  • Building full-stack React app with file-based routing + server functions
  • Creating forms with type-safe validation (Zod/Valibot)
  • Adding AI chat/streaming to a TanStack app
  • Comparing TanStack Start vs Next.js/Remix

Quick Start — TanStack Start

npm create @tanstack/start@latest    # create project
npm run dev                          # dev server :3000
npm run build                        # production build

Project Structure

src/
├── routes/
│   ├── __root.tsx          # root layout (required)
│   ├── index.tsx           # /
│   └── posts.$postId.tsx   # /posts/:postId
├── router.tsx              # createRouter config
├── routeTree.gen.ts        # AUTO-GENERATED — never edit
└── start.ts                # global middleware
app.config.ts               # Nitro/Start config

Server Function

import { createServerFn } from '@tanstack/react-start'
import { z } from 'zod'

const getUser = createServerFn({ method: 'GET' })
  .validator(z.object({ id: z.string() }))
  .handler(async ({ data }) => db.user.findUnique({ where: { id: data.id } }))

Route with Loader

export const Route = createFileRoute('/posts/$postId')({
  loader: ({ params }) => getPost({ data: { id: params.postId } }),
  component: PostComponent,
})
function PostComponent() {
  const post = Route.useLoaderData()
  return <div>{post.title}</div>
}

Middleware

import { createMiddleware } from '@tanstack/react-start'
export const authMiddleware = createMiddleware()
  .server(async ({ next, context }) => {
    const session = await getSession(context.request)
    return next({ context: { user: session.user } })
  })

TanStack Form

Headless, type-safe form library. Detailed API: references/tanstack-form.md

import { useForm } from '@tanstack/react-form'
import { zodValidator } from '@tanstack/zod-form-adapter'

const form = useForm({
  defaultValues: { email: '', age: 0 },
  validatorAdapter: zodValidator,
  onSubmit: async ({ value }) => { await saveUser(value) },
})

// JSX: <form.Field name="email" validators={{ onChange: z.string().email() }}>
//   {(f) => <input value={f.state.value} onChange={e => f.handleChange(e.target.value)} />}
// </form.Field>

Read the full file on GitHub · 142 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 142 lines · 55 tokens per session scan A 3143ede9939f

Subscribe to this mod's changes

ck:tanstack is a skill published in the GitHub repository manhvann/codexkit (88 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,182 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens