ai-rules: Instructions file for Claude Code

CLAUDE.md

ai-rules CLAUDE.md is an instructions file for Claude Code from neondatabase/ai-rules. It costs 2,942 tokens per session, scanned A, original, MIT.

A project instruction document for Neon’s AI development rules. It describes Markdown guidance files and a Claude Code plugin for developers using Neon databases with AI coding assistants.

In plain words
What is it for?
Use it when navigating or maintaining the archived Neon AI rules repository and its context files or plugin components.
Why use it?
It gives an agent background on the repository's documentation, rules and plugin structure. The document also notes that the repository has been archived and its content moved elsewhere.

Instructions file for Claude Code ✓ vendor

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions subagents.

This is neondatabase/ai-rules's own configuration. It tells Claude Code how to work on ai-rules 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 ai-rules configures →

Reuse

Borrowing it

Nothing to install: this file belongs to neondatabase/ai-rules. 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/neondatabase/ai-rules/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/neondatabase/ai-rules

Made for: Claude Code.

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 ai-rules CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/neondatabase/ai-rules/claude-md/github.svg)](https://agentmods.dev/instructions/neondatabase/ai-rules/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/neondatabase/ai-rules/claude-md"><img src="https://agentmods.dev/badge/instructions/neondatabase/ai-rules/claude-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 ai-rules CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/neondatabase/ai-rules/claude-md"><img src="https://agentmods.dev/badge/instructions/neondatabase/ai-rules/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,942 This file is loaded in full into every session.
When invoked 2,942 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 $0.02942 $0.02942
Opus 5.5 $0.01177 $0.01177
Sonnet 5.5 $0.00588 $0.00588
Haiku 4.5 $0.00294 $0.00294

Measured 2mo ago against content hash bdbc0b0345de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-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 2mo 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 · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neon AI Rules - Project Documentation

Note: This repository has been archived. Content has moved to neondatabase/agent-skills.

Project Overview

This repository contains a comprehensive suite of AI-powered development tools for Neon, including:

  1. Context Rules (.mdc files): Markdown Context files that guide AI systems
  2. Claude Code Plugin: Full-featured plugin with guided skills and MCP server integration
  3. Neon SDK Rules: Guidelines for TypeScript and Python SDKs

The primary audience includes AI developers using Claude, Cursor, and other AI-powered code assistants who work with Neon databases.

Repository Structure

.
├── *.mdc                          # Context rule files (16 total)
├── .claude-plugin/
│   └── marketplace.json           # Marketplace metadata
├── neon-plugin/                   # Claude Code plugin
│   ├── .claude-plugin/
│   │   └── plugin.json            # Plugin metadata
│   ├── .mcp.json                  # MCP server configuration
│   ├── evals/                     # Skill evaluation tests
│   └── skills/                    # Guided skills for Claude Code (6 total)
│       ├── add-neon-docs/         # Documentation reference installer
│       ├── neon-auth/             # Neon Auth integration
│       │   ├── guides/            # Setup guides (Next.js, React SPA)
│       │   └── templates/         # Auth client templates
│       ├── neon-drizzle/
│       │   ├── guides/            # Step-by-step workflow guides
│       │   ├── references/        # Technical reference docs
│       │   ├── scripts/           # Utility scripts
│       │   └── templates/         # Code templates
│       ├── neon-js/               # Full Neon JS SDK integration
│       │   ├── guides/            # Setup guides
│       │   └── templates/         # Client templates
│       ├── neon-serverless/
│       └── neon-toolkit/
├── references/                    # Shared technical reference docs (16 files)
│   ├── code-generation-rules.md
│   ├── neon-auth-*.md             # Auth-related references (11 files)
│   │   # Includes: common-mistakes, components, provider-config,
│   │   # setup (general, nextjs, nodejs, react-spa), troubleshooting,
│   │   # ui (general, nextjs, react-spa)
│   └── neon-js-*.md               # Neon JS references (4 files)
│       # Includes: adapters, data-api, imports, theming
├── mcp-prompts/                   # MCP prompt templates
├── .claude/
│   └── settings.local.json        # Local Claude Code settings
├── .serena/                       # Serena code intelligence cache
├── CHANGELOG.md                   # Version history and release notes
├── CONTRIBUTING.md                # Contribution guidelines
├── LICENSE                        # MIT License
├── README.md                      # User-facing documentation
└── CLAUDE.md                      # This file

Read the full file on GitHub · 269 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. 2mo ago First seen · 269 lines · 2,942 tokens per session scan A bdbc0b0345de

Subscribe to this mod's changes

ai-rules CLAUDE.md is an instructions file published in the GitHub repository neondatabase/ai-rules (86 stars, last pushed 5mo ago), licensed MIT. It adds 2,942 tokens to every session, about $0.0118 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

ai-rules CLAUDE.md compared with instructions from other repositories

ai-rules CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ai-rules CLAUDE.mdneondatabase/ai-rulesInstructions file865mo agoMITA2,942Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot