nextjs-agent-first

nextjs-agent-first is a skill for Claude Code, Codex from S3YED/appie-kit. It costs 44 tokens per session (683 once invoked), scanned A, original, MIT.

A guide to Next.js 16.3+ features built for AI coding agents, including project instructions, installable skills, browser inspection, and clearer errors.

In plain words
What is it for?
Building and debugging Next.js applications with AI agents, including browser feedback loops, React component inspection, and cache-related route work.
Why use it?
It helps agents use current project documentation and inspect what the app is doing instead of relying on outdated assumptions.

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/s3yed/appie-kit/nextjs-agent-first
Any agent
npx skills add S3YED/appie-kit --skill nextjs-agent-first
Clone the repo
git clone --depth 1 https://github.com/S3YED/appie-kit

Made for: Claude Code, Codex.

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 nextjs-agent-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/s3yed/appie-kit/nextjs-agent-first.svg)](https://agentmods.dev/skills/s3yed/appie-kit/nextjs-agent-first)
Your own site
<a href="https://agentmods.dev/skills/s3yed/appie-kit/nextjs-agent-first"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/nextjs-agent-first.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 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 $0.00044 $0.00683
Opus 5 $0.00022 $0.00342
Sonnet 5 $0.00009 $0.00137
Haiku 4.5 $0.00004 $0.00068

Measured yesterday against content hash 04715a223b38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nextjs-agent-first 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 yesterday.

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.

skills/design/nextjs-agent-first/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Next.js Agent-First Features

Next.js 16.3+ is the first framework designed explicitly for AI-agent-driven development.

Key Features

AGENTS.md (auto-generated docs)

  • next dev auto-writes version-matched docs pointers into AGENTS.md
  • Agents read actual docs instead of guessing from training data
  • Opt-out via agentRules: false in next.config.ts

First-Party Skills (npx-installable)

Install via npx skills add vercel/next.js:

Skill Purpose
next-dev-loop Full dev feedback loop: drive browser, read console, inspect React tree, follow network requests
next-cache-components-adoption Incremental or direct adoption of Cache Components ("use cache")
next-cache-components-optimizer Optimize routes for instant navigation by growing the static shell

Agent Browser React Introspection

agent-browser v0.27+ can run React DevTools commands from CLI:

# Launch with React DevTools
agent-browser --enable react-devtools

# Inspect component tree
agent-browser react tree
agent-browser react inspect <fiber-id>
agent-browser react renders start
agent-browser react suspense --only-dynamic --json

Actionable Errors (Instant Insights)

Error overlay shows labeled fixes (Stream / Cache / Block) with a "Copy prompt" button that copies a paste-ready agent prompt.

Streamlined MCP Server

Two new tools: get_compilation_issues and compile_route — check compilation without full next build.

Turbopack Improvements (16.3)

  • ~90% less memory (21.5GB → 2GB for vercel.com)
  • ~2.3x faster cached builds
  • Experimental Rust React Compiler (20-50% faster)
  • import.meta.glob API support
  • ~15% faster dev cold start

Usage

When building or debugging Next.js projects with an AI agent:

  1. Enable AGENTS.md: Ensure next dev runs in the project so docs are auto-generated
  2. Use next-dev-loop skill: Load it when you need browser-based verification
  3. Run agent-browser with React: agent-browser --enable react-devtools for component inspection
  4. Copy actionable error prompts: Use the error overlay's "Copy prompt" button for instant fixes
  5. Cache Components optimizer: Run after building to optimize routes for instant nav

Read the full file on GitHub · 69 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. yesterday First seen · 69 lines · 44 tokens per session scan A 04715a223b38

Subscribe to this mod's changes

nextjs-agent-first is a skill published in the GitHub repository S3YED/appie-kit (7 stars, last pushed 9d ago), licensed MIT. It adds 44 tokens to every session and 683 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 skills, from other repositories

dagre-react-flow

Automatic graph layout using dagre with React Flow (@xyflow/react). Use when implementing auto-layout, hierarchical layouts, tree structures, or arranging nodes programmatically. Triggers on dagre, auto-layout, automatic layout, getLayoutedElements, rankdir, hierarchical graph.

Aniket-a14/SRA · 60 tokens

nextjs-development

Next.js 16.2.4 with TypeScript — App Router, Server Components, use cache directive, Turbopack dev, Server Actions, ISR, SSR, SSG, MCP devtools, metadata API, route handlers, instrumentation.

PracticalSwan/agent-skills · 54 tokens

react-best-practices

React development guidelines with hooks, component patterns, state management, and performance optimization.

myths-labs/muse · 22 tokens

vercel-react-best-practices

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code in StarMapper — especially MapLibre components, data fetching, and bundle optimization.

FlorianBruniaux/starmapper · 51 tokens

vercel-react-best-practices

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…

Aniket-a14/SRA · 67 tokens

vercel-react

React/Next.js performance — 70 rules (waterfalls, bundle, re-renders). Use when reviewing or writing React/Next.js code.

martineserios/thebrana · 34 tokens