query-create

query-create is a command for Claude Code from smicolon/ai-kit. It costs 16 tokens per session (2,029 once invoked), scanned A, original, MIT.

A command for creating TanStack Query data-fetching code, including reusable queries, changes to server data, and hooks.

In plain words
What is it for?
It helps scaffold list, detail, create, update, delete, and infinite-query features in a React project.
Why use it?
It gives related API code and cache keys a consistent structure, reducing repeated setup and mistakes when data changes.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { {Feature}, Create{Feature}Input, Update{Feature}Input, {Feature}Filters } from '../types'.

Good fit It helps scaffold list, detail, create, update, delete, and infinite-query features in a React project.

Compare 6 commands 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 commands/smicolon/ai-kit/query-create

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 query-create

README.md
[![agentmods](https://agentmods.dev/badge/commands/smicolon/ai-kit/query-create/github.svg)](https://agentmods.dev/commands/smicolon/ai-kit/query-create)
Your own site
<a href="https://agentmods.dev/commands/smicolon/ai-kit/query-create"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/query-create/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 query-create

Your own site · 80×15
<a href="https://agentmods.dev/commands/smicolon/ai-kit/query-create"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/query-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,029 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 $0.00016 $0.02029
Opus 5 $0.00008 $0.01014
Sonnet 5 $0.00003 $0.00406
Haiku 4.5 $0.00002 $0.00203

Measured 6d ago against content hash 2e64f29fc50d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

query-create 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 6d 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/commands/query-create.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create TanStack Query

Create query options, mutations, and hooks following the factory pattern.

Instructions

  1. Gather Information (if not provided via args):

    • Ask for the feature name (e.g., posts, users)
    • Ask for the query type: query, mutation, or infinite query
    • Ask for the operation (e.g., list, detail, create, update, delete)
  2. Create Feature Directory Structure (if new feature):

    src/features/{feature}/
    ├── api/
    │   └── {feature}Api.ts
    ├── queries/
    │   ├── {feature}Queries.ts
    │   └── index.ts
    ├── hooks/
    │   ├── use{Operation}{Feature}.ts
    │   └── index.ts
    ├── types.ts
    └── index.ts
    
  3. Create/Update Query Keys in src/lib/query-keys.ts:

    export const queryKeys = {
      {feature}: {
        all: () => ['{feature}'] as const,
        lists: () => [...queryKeys.{feature}.all(), 'list'] as const,
        list: (filters: {Feature}Filters) => [...queryKeys.{feature}.lists(), filters] as const,
        details: () => [...queryKeys.{feature}.all(), 'detail'] as const,
        detail: (id: string) => [...queryKeys.{feature}.details(), id] as const,
      },
    } as const
    
  4. Create API Functions in src/features/{feature}/api/{feature}Api.ts:

    import { apiClient } from '@/lib/api-client'
    import type { {Feature}, Create{Feature}Input, Update{Feature}Input, {Feature}Filters } from '../types'
    
    export const {feature}Api = {
      get{Feature}s: async (filters?: {Feature}Filters): Promise<{Feature}[]> => {
        const response = await apiClient.get('/{feature}', { params: filters })
        return response.data
      },
    
      get{Feature}: async (id: string): Promise<{Feature}> => {
        const response = await apiClient.get(`/{feature}/${id}`)
        return response.data
      },
    
      create{Feature}: async (input: Create{Feature}Input): Promise<{Feature}> => {
        const response = await apiClient.post('/{feature}', input)
        return response.data
      },
    
      update{Feature}: async ({ id, ...input }: Update{Feature}Input): Promise<{Feature}> => {
        const response = await apiClient.patch(`/{feature}/${id}`, input)
        return response.data
      },
    
      delete{Feature}: async (id: string): Promise<void> => {
        await apiClient.delete(`/{feature}/${id}`)
      },
    }
    

Read the full file on GitHub · 264 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. 6d ago First seen · 264 lines · 16 tokens per session scan A 2e64f29fc50d

Subscribe to this mod's changes

query-create is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 2,029 once invoked, about $0.0001 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.