next-app-i18n-starter: Instructions file for Codex

AGENTS.md

next-app-i18n-starter AGENTS.md is an instructions file for Codex, OpenCode from s0vers/next-app-i18n-starter. It costs 1,418 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding assistants working on a Next.js starter project with translations, right-to-left language support, themes, and search-engine settings.

In plain words
What is it for?
Use them when changing this project so code follows its structure, translation files stay consistent, secrets remain protected, and builds and checks are run after substantial changes.
Why use it?
They give the assistant project-specific rules, such as which package manager and navigation methods to use, and which files must be updated together.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is s0vers/next-app-i18n-starter's own configuration. It tells Codex and OpenCode how to work on next-app-i18n-starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything next-app-i18n-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to s0vers/next-app-i18n-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/s0vers/next-app-i18n-starter/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/s0vers/next-app-i18n-starter

Made for: Codex, OpenCode.

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 next-app-i18n-starter AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/s0vers/next-app-i18n-starter/agents-md/github.svg)](https://agentmods.dev/instructions/s0vers/next-app-i18n-starter/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/s0vers/next-app-i18n-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/s0vers/next-app-i18n-starter/agents-md/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 next-app-i18n-starter AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/s0vers/next-app-i18n-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/s0vers/next-app-i18n-starter/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,418 This file is loaded in full into every session.
When invoked 1,418 The same file — it is already loaded in full.
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 $0.01418 $0.01418
Opus 5.5 $0.00567 $0.00567
Sonnet 5.5 $0.00284 $0.00284
Haiku 4.5 $0.00142 $0.00142

Measured 1mo ago against content hash e7cebc03af5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

next-app-i18n-starter 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 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.

AGENTS.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository instructions

These instructions apply to coding assistants of any model or editor. Read this file first, then read the nearest AGENTS.md for the files you change. User instructions take priority. When documentation conflicts with the code or configuration, verify the behavior and update the stale documentation in the same change.

Project facts

  • Next.js 16 App Router, React 19, next-intl 4, Tailwind CSS 4, and shadcn/ui.
  • Bun is the package manager; bun.lock is the lockfile. Node.js 24 is required.
  • The app supports English, Arabic, Chinese, Spanish, and Japanese. English is the default locale.

Shared rules

  • Keep changes focused on the requested outcome. Inspect the relevant code and current Git status first, reuse existing patterns, and avoid dependencies or abstractions without a concrete need.
  • Protect credentials and user data. Never read, edit, or commit .env files. Put new variable names and safe example values in .env.example; never place real credentials there.
  • Use @/i18n/navigation for links and navigation that should preserve locale. Use Next.js navigation APIs directly when the operation is not locale-aware, such as notFound().
  • dictionary/en.json defines translation message types. Add or rename message keys in every dictionary/*.json file. Keep locale copy accurate and have fluent speakers review production translations.
  • Locale routes live under src/app/[locale]/. Validate route locales with hasLocale before using them. The locale reaches server code through next/root-params in src/i18n/request.ts, so pages do not call setRequestLocale, which next-intl deprecated in 4.13.5.
  • Build locale URLs with helpers from src/lib/site.ts. Routing uses localePrefix: "as-needed": English uses /, and other locales use /{locale}. Automatic locale detection is disabled so cookies and browser language do not redirect the default URL.
  • Use createLocalizedMetadata for page metadata and keep canonical, alternate-language, sitemap, and Open Graph URLs aligned. Follow SEO.md and the nextjs-seo-* skills in .agents/skills/. Add structured data only when it describes visible page content; render JSON-LD in a Server Component and escape < in its serialized value.
  • Prefer Server Components. Add "use client" only for client state, event handlers, or browser APIs. Theme initialization uses the existing cookie-based SSR implementation.
  • Follow the component, styling, accessibility, and RTL conventions in src/components/AGENTS.md when changing UI.
  • Keep documentation and instructions consistent with the implementation when changing a convention, route, locale, or environment variable.

Read the full file on GitHub · 65 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. 1mo ago Changed · +15 lines · +788 tokens per session e7cebc03af5d
  2. 2mo ago First seen · 50 lines · 630 tokens per session scan A 9924d6797307

Subscribe to this mod's changes

next-app-i18n-starter AGENTS.md is an instructions file published in the GitHub repository s0vers/next-app-i18n-starter (66 stars, last pushed 6d ago), licensed MIT. It adds 1,418 tokens to every session, about $0.0057 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 2026-08-30.

Related

next-app-i18n-starter AGENTS.md compared with instructions from other repositories

next-app-i18n-starter AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
next-app-i18n-starter AGENTS.mds0vers/next-app-i18n-starterInstructions file666d agoMITA1,418Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode