What is llm-rules CLAUDE.md?

A set of instructions for Claude Code, an AI coding assistant, describing a web application's technology choices, structure, and coding rules. It covers a monorepo, which is one repository containing multiple related packages or applications.

Use it when working on this Next.js and TypeScript application, especially for server-rendered pages, reusable components, authentication, database access, translations, logging, and tests.

It gives the coding assistant consistent project context, reducing guesswork about where code belongs and how new code should be written.

llm-rules CLAUDE.md — Instructions file for coding agents by ryanrawlingswang: A set of instructions for Claude Code, an AI…

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 instructions/ryanrawlingswang/llm-rules/claude-md

Clone the repo

git clone --depth 1 https://github.com/ryanrawlingswang/llm-rules

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ryanrawlingswang/llm-rules/claude-md.svg)](https://agentmods.dev/instructions/ryanrawlingswang/llm-rules/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ryanrawlingswang/llm-rules/claude-md"><img src="https://agentmods.dev/badge/instructions/ryanrawlingswang/llm-rules/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,810 This file is loaded in full into every session.

When invoked 1,810 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.01810	$0.01810
Opus 5	$0.00905	$0.00905
Sonnet 5	$0.00362	$0.00362
Haiku 4.5	$0.00181	$0.00181

Measured 4d ago against content hash a6cb6700a60c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-rules CLAUDE.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.

CLAUDE.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Stack

Monorepo: pnpm workspaces + Turborepo
Web app: Next.js 15 (App Router), TypeScript strict, Tailwind CSS v4
Auth: Better Auth (email/password, session cookies)
API: tRPC v11 with publicProcedure / protectedProcedure
DB: PostgreSQL + Drizzle ORM (packages/db)
Testing: Vitest + Testing Library + Playwright (e2e)
Logging: packages/logger (structured logging — prefer over console.log)
i18n: packages/i18n (translations via next-intl)

Architecture Principles

Server-first rendering

Pages are Server Components by default. Only add "use client" to leaf components that need interactivity — browser APIs, event handlers, or hooks.
Do server-side data fetching in RSC via getSession(), tRPC server caller, or server actions. Pass results down as props — do not re-fetch on the client what was already fetched on the server.
Protect pages at the RSC level (getSession() → redirect) and in middleware. Both layers.

Small, composable components

One component = one responsibility. If a component has more than ~150 lines, it's doing too much.
Prefer pure presentational components that receive props over components that fetch their own data.
Compose complex UIs from small primitives (Button, Input, Card) rather than building monolithic page components.
Co-locate page-specific components in _components/ next to their route. Shared components go in src/components/.
Follow DRY: extract reusable logic, components, and utilities. On the backend, share via tRPC procedures or shared libraries. On the frontend, share via hooks, components, and utility functions.

Separation of concerns

src/
  app/              ← routing, layouts, pages (thin — orchestrate, don't compute)
    _components/    ← page-scoped components (not shared)
  components/ui/    ← design system primitives (stateless, no data fetching)
  server/api/       ← tRPC routers (application logic, auth, validation — call services)
  server/services/  ← service layer (pure business logic, DB access)
  lib/              ← shared utilities, auth config, constants
  db/               ← DB client + re-exports from packages/db

Read the full file on GitHub · 149 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.

4d ago First seen · 149 lines · 1,810 tokens per session scan A a6cb6700a60c

Subscribe to this mod's changes

llm-rules CLAUDE.md is an instructions file published in the GitHub repository ryanrawlingswang/llm-rules (17 stars, last pushed 2mo ago), licensed MIT. It adds 1,810 tokens to every session, about $0.0090 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.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

llm-rules CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Claude Code Instructions

Stack

Architecture Principles

Server-first rendering

Small, composable components

Separation of concerns

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

spec-kit AGENTS.md

codex AGENTS.md

langchain AGENTS.md

vscode oss-third-party-notices.instructions.md

next.js AGENTS.md