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/paulrberg/next-template/agents-mdgit clone --depth 1 https://github.com/PaulRBerg/next-templateWrote 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/paulrberg/next-template/agents-md)<a href="https://agentmods.dev/instructions/paulrberg/next-template/agents-md"><img src="https://agentmods.dev/badge/instructions/paulrberg/next-template/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 | $0.00694 | $0.00694 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
next-template 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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Instructions
Validation
After changing code, run applicable checks in this order:
na biome lint <files>for changed JavaScript, TypeScript, JSON, CSS, or GraphQL files.na eslint <files>for changed TypeScript files; ESLint owns Tailwind CSS validation and React Hooks dependencies.na tsgo --noEmitfor the entire project.
For the first two commands, pass explicit paths when fewer than 10 files changed. With 10 or more changed files, omit
Biome's paths and pass . to ESLint. Fix only failures caused by your changes.
Use just to discover broader workflows. For dependencies, use ni, ni <package>, ni -D <package>, and
nun <package> so the Bun-backed package manager is selected consistently.
Code Conventions
Names and Types
- Use
kebab-casefor directories and non-component files,PascalCasefor component files, andcamelCasefor hooks. - Prefer
typeoverinterface,satisfiesfor type-safe constants, andunknownoverany. - Use
nullfor known-empty in-memory UI or domain state. Omit boundary values withundefinedin URLs, storage, network payloads, and configuration; preserve existing JSON omission semantics.
React and Next.js
- Use Server Components by default. Add
"use client"only for hooks, event handlers, or browser APIs; add"use server"for Server Actions. Useserver-onlyandclient-onlyimports for environment-specific modules. Place directives before imports. - Use named exports except where Next.js requires a default export.
- Lazy-load heavy components with
next/dynamicfromComponent.lazy.tsxfiles. - Do not add
useMemooruseCallback; React Compiler is enabled. Wrap unstable external-library values used by an effect inuseEffectEventwhen they would otherwise cause resubscriptions or loops. - Treat
refas a normal React 19 prop. UseforwardRefonly withuseImperativeHandle. - Prefer Actions with
useActionStateoruseFormStatus, and use<form action>for server mutations. - Render every image with
SmartImagefrom@/ui/SmartImage, which supplies inferredsizesand fallback alt text. - Do not wrap JSX conditions in
Boolean(...); use the underlying condition directly.
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 · 56 lines · 694 tokens per session scan A 715a5a4d2062
next-template AGENTS.md is an instructions file published in the GitHub repository PaulRBerg/next-template (21 stars, last pushed 23d ago), licensed MIT. It adds 694 tokens to every session, about $0.0035 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
opencode-vibe AGENTS.md
AGENTS.md instructions for joelhooks/opencode-vibe, covering agents.md, ⚠️ critical: chrome devtools = subagent only, project overview, tech stack and development commands.
opencode-vibe CLAUDE.md
Use Bun instead of Node.js, npm, pnpm, or vite.
agent-thread AGENTS.md
AGENTS.md instructions for amalshaji/agent-thread, covering agent instructions, tooling, project commands, release workflow and architecture.
velocity CLAUDE.md
Claude Code instructions for OptimiLabs/velocity, covering velocity — project guidelines, tech stack, key architecture, conventions and tables.
agent-thread CLAUDE.md
Use Bun instead of Node.js, npm, pnpm, or vite.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.