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.
npx skills add smicolon/ai-kit --skill start-patternsgit clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/skills/smicolon/ai-kit/start-patterns)<a href="https://agentmods.dev/skills/smicolon/ai-kit/start-patterns"><img src="https://agentmods.dev/badge/skills/smicolon/ai-kit/start-patterns/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.
<a href="https://agentmods.dev/skills/smicolon/ai-kit/start-patterns"><img src="https://agentmods.dev/badge/skills/smicolon/ai-kit/start-patterns.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.00789 |
| Opus 5.5 | $0.00015 | $0.00316 |
| Sonnet 5.5 | $0.00007 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
start-patterns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TanStack Start Full-Stack Patterns
Patterns for building full-stack SSR and streaming React applications using TanStack Start (powered by TanStack Router).
1. Architecture Overview
TanStack Start turns TanStack Router into a full-stack framework with:
- Server Functions (
createServerFn): Type-safe RPC between client and server without manual fetch endpoints. - SSR & Streaming: Instant HTML shells with streamed data loaders.
- Nitro Engine Deployment: Deploy to Cloudflare Workers, Vercel, Node, Bun, or Netlify with zero code changes.
app/
├── routes/
│ ├── __root.tsx # HTML document shell (Head, Scripts, Outlet)
│ ├── index.tsx # Home page
│ └── posts.$id.tsx # Loader with server function
├── router.tsx # Router factory for SSR hydration
├── client.tsx # Client hydration entrypoint
└── ssr.tsx # Server rendering entrypoint
2. Server Functions (createServerFn)
Server functions run purely on the server and are callable directly from loaders, mutations, or React components:
// app/features/users/server.ts
import { createServerFn } from '@tanstack/start'
import { z } from 'zod'
import { db } from '@/server/db'
export const getUserServerFn = createServerFn({ method: 'GET' })
.validator((id: string) => z.string().uuid().parse(id))
.handler(async ({ data: id }) => {
const user = await db.user.findUnique({ where: { id } })
if (!user) throw new Error('User not found')
return user
})
export const updateUserNameServerFn = createServerFn({ method: 'POST' })
.validator((payload: { id: string; name: string }) =>
z.object({ id: z.string(), name: z.string().min(2) }).parse(payload)
)
.handler(async ({ data }) => {
return await db.user.update({
where: { id: data.id },
data: { name: data.name },
})
})
3. Route Loader Integration
Call server functions seamlessly inside route loaders:
// app/routes/users.$userId.tsx
import { createFileRoute } from '@tanstack/react-router'
import { getUserServerFn } from '@/features/users/server'
export const Route = createFileRoute('/users/$userId')({
loader: async ({ params }) => {
return await getUserServerFn({ data: params.userId })
},
component: UserProfilePage,
})
function UserProfilePage() {
const user = Route.useLoaderData()
return <div><h1>{user.name}</h1></div>
}
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.
- 1mo ago First seen · 105 lines · 37 tokens per session scan A 58ae348ce8b1
start-patterns is a skill published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 789 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
nodejs-backend-patterns
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures.
neon-postgres
Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related…
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
middlewares
Create and compose tRPC middleware with t.procedure.use(), extend context via opts.next({ ctx }), build reusable middleware with .concat() and .unstablepipe(), define base procedures like publicProcedure and authedProcedure. Access raw input with getRawInput(). Logging, timing, OTEL tracing patterns.
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).