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 agentmods add instructions/pruthvinathjv/nextjs-claude-code-kit/claude-mdgit clone --depth 1 https://github.com/pruthvinathJV/nextjs-claude-code-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/instructions/pruthvinathjv/nextjs-claude-code-kit/claude-md)<a href="https://agentmods.dev/instructions/pruthvinathjv/nextjs-claude-code-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/pruthvinathjv/nextjs-claude-code-kit/claude-md.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 | $0.08731 | $0.08731 |
| Opus 5 | $0.04365 | $0.04365 |
| Sonnet 5 | $0.01746 | $0.01746 |
| Haiku 4.5 | $0.00873 | $0.00873 |
Grade A, and why
nextjs-claude-code-kit CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `revalidateTag('x')` with no tagged fetch | Tag the fetch: `fetch(url, { next: { tags: ['x'] } })` | How it starts
The opening of the file, as written. The whole thing — 1,034 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js 15 App Router — Claude Code Configuration
This project uses Next.js 15 App Router. All Pages Router patterns, pre-RSC React conventions, and pre-Next.js 15 fetch caching assumptions are incorrect in this context. When in doubt, prefer server components, server actions, and no-cache defaults. Your training data for Next.js is likely stale. Treat it as unreliable and follow these rules instead.
1. Component Model: Server-First, Client-Boundary-Last
Default: every component is a Server Component.
'use client' is not a neutral annotation. It is an architectural boundary decision that
opts the component and all its children out of the server rendering model. Place it only
when the component requires:
- Browser APIs (
window,document,localStorage) - Event listeners (
onClick,onChange,onSubmiton interactive elements) - React hooks that depend on client state (
useState,useEffect,useReducer,useContextwith a client-side provider)
Push the 'use client' boundary as far down the component tree as possible. If only
a button inside a large component needs interactivity, extract the button into its own
small Client Component. Keep the parent as a Server Component.
Never do this:
// ❌ Entire page becomes client-rendered because one button needs onClick
'use client'
export default function ProductPage({ product }) {
return (
<div>
<h1>{product.name}</h1>
<p>{product.description}</p>
<button onClick={() => addToCart(product.id)}>Add to cart</button>
</div>
)
}
Do this:
// ✅ Only the interactive piece crosses the client boundary
// components/AddToCartButton.tsx
'use client'
export function AddToCartButton({ productId }: { productId: string }) {
return <button onClick={() => addToCart(productId)}>Add to cart</button>
}
// app/products/[id]/page.tsx — Server Component, no 'use client'
export default async function ProductPage({
params,
}: {
params: Promise<{ id: string }>
}) {
const { id } = await params
const product = await getProduct(id)
return (
<div>
<h1>{product.name}</h1>
<p>{product.description}</p>
<AddToCartButton productId={product.id} />
</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.
- 4d ago First seen · 1,034 lines · 8,731 tokens per session scan A e1f1d4b83254
nextjs-claude-code-kit CLAUDE.md is an instructions file published in the GitHub repository pruthvinathJV/nextjs-claude-code-kit (2 stars, last pushed 6mo ago), licensed MIT. It adds 8,731 tokens to every session, about $0.0437 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
CopilotKit AGENTS.md
AGENTS.md instructions for CopilotKit/CopilotKit, covering general guidelines for working with nx, copilotkit, essentials, private agent instructions and internal skills.
CopilotKit CLAUDE.md
Claude Code instructions for CopilotKit/CopilotKit, covering general guidelines for working with nx, copilotkit, essentials and reference (read when relevant to your task).
hackerai AGENTS.md
AGENTS.md instructions for hackerai-tech/hackerai, covering agents.md instructions, worktree dependencies, hackerai product direction, feature rollouts and measurement and pull request review workflow.
hackerai CLAUDE.md
Claude Code instructions for hackerai-tech/hackerai, covering fin-managed content, frontmatter schema, how to add new content, a new article and how to update or delete content.
ai-website-cloner-template copilot-instructions.md
Instructions for JCodesMore/ai-website-cloner-template, covering this is not the next.js you know, website reverse-engineer template, what this is, tech stack and commands.
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.