Next-js-Boilerplate is a ready-made starting project for building Next.js applications with TypeScript, Tailwind CSS, routing, authentication, databases, testing, and development tools. Developers use it to create new web applications without assembling the foundation from scratch. Its catalogue instructions guide coding agents working in this starter project.
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/ixartz/next-js-boilerplate/agents-mdgit clone --depth 1 https://github.com/ixartz/Next-js-BoilerplateWrote 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/ixartz/next-js-boilerplate/agents-md)<a href="https://agentmods.dev/instructions/ixartz/next-js-boilerplate/agents-md"><img src="https://agentmods.dev/badge/instructions/ixartz/next-js-boilerplate/agents-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 | $0.00881 | $0.00881 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
Next-js-Boilerplate AGENTS.md 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Principles
- Clarity and consistency over cleverness. Minimal changes. Match existing patterns.
- Keep components/functions short; break down when it improves structure.
- TypeScript everywhere; no
anyunless isolated and necessary. - No unnecessary
try/catch. Avoid casting; use narrowing. - Named exports only (no default exports, except Next.js pages).
- Absolute imports via
@/unless same directory. - Follow existing ESLint setup; don't reformat unrelated code.
- Zod type-only:
import type * as z from 'zod';. - Let compiler infer return types unless annotation adds clarity.
- Options object for 3+ params, optional flags, or ambiguous args.
- Hypothesis-driven debugging: 1-3 causes, validate most likely first.
Token efficiency
- Skip recaps unless the result is ambiguous or you need more input.
Commands
Only these bun run scripts: build-local, lint, check:types, check:deps, check:i18n, test, test:e2e.
Git Commits
Conventional Commits: type: summary without scope. The summary should be a short, specific sentence that explains what changed and where or why, not a vague phrase. Types: feat|fix|docs|style|refactor|perf|test|build|ci|chore|revert. BREAKING CHANGE: footer when needed.
Env
All env vars validated in Env.ts; never read process.env directly.
Styling
Tailwind v4 utility classes. Reuse shared components. Responsive. No unnecessary classes.
React
- No
useMemo/useCallback(React compiler handles it). AvoiduseEffect. - Single
propsparam with inline type; access asprops.foo(no destructuring). - Use
React.ReactNode, notReactNode. - Inline short event handlers; extract only when complex.
Pages
- Default export name ends with
Page. Props alias (if reused) ends withPageProps. - Locale pages:
props: { params: Promise<{ locale: string }> }→await props.params→setRequestLocale(locale). - Escape glob chars in shell commands for Next.js paths.
- Dashboard pages (sit behind auth); define meta once in layout, not in each page.
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.
- 5d ago First seen · 68 lines · 881 tokens per session scan A 944926e3fc7a
Next-js-Boilerplate AGENTS.md is an instructions file published in the GitHub repository ixartz/Next-js-Boilerplate (13,065 stars, last pushed 2d ago), licensed MIT. It adds 881 tokens to every session, about $0.0044 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.
Other instructions, from other repositories
turbo-start-sanity CLAUDE.md
Claude Code instructions for robotostudio/turbo-start-sanity, covering claude.md, project overview, commands, development (both apps) and individual apps.
Tackl AGENTS.md
Instructions for 12-Studio/Tackl, covering agents.md, the one rule that trips agents up most, imports & aliases, writing a component and file layout & comments.
Tackl CLAUDE.md
Instructions for 12-Studio/Tackl: Instructions for Claude Code live in the tool-agnostic AGENTS.md.
ForgeStart AGENTS.md
Instructions for Onurlulardan/ForgeStart, covering agents.md, project identity, current stack, architecture map and development workflow.
agentic-coding-starter-kit CLAUDE.md
Claude Code instructions for Eipi-Tong/agentic-coding-starter-kit, covering claude.md, session start, role, core rules and skills available.
nextarter-tailwind AGENTS.md
AGENTS.md instructions for agustinusnathaniel/nextarter-tailwind, covering next.js: always read docs before coding, ai agent guidance: nextarter-tailwind, 1. mental model for agents, implementation delegation and tooling strategy.