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 rules/neondatabase/ai-rules/neon-get-startedgit clone --depth 1 https://github.com/neondatabase/ai-rulesWrote 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/rules/neondatabase/ai-rules/neon-get-started)<a href="https://agentmods.dev/rules/neondatabase/ai-rules/neon-get-started"><img src="https://agentmods.dev/badge/rules/neondatabase/ai-rules/neon-get-started.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 | $0.00000 | $0.02223 |
| Opus 5 | $0.00000 | $0.01111 |
| Sonnet 5 | $0.00000 | $0.00445 |
| Haiku 4.5 | $0.00000 | $0.00222 |
Grade A, and why
neon-get-started 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.
This is a copy
94% identical to neon-get-started-kiro — 92 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neon Database Guidelines
Overview
This guide provides steps to help a user get started with Neon in their project. It sets up their Neon project (with a connection string) and connects their database to their code by understanding the context within the codebase.
Use Case
These guidelines only apply to users getting started with the Neon integration (through the command 'Get started with Neon' or 'Get started with Neon using the MCP resource'). The user's codebase may be mature (with existing database connections) or have little to no code and the guidelines should apply to both cases.
Communication Style
Keep all responses succinct:
- ✅ Tell the user what you did: "Created users table with 3 columns"
- ✅ Ask direct questions when needed: "Which database should I use?"
- ❌ Avoid verbose explanations of what you're about to do
- ❌ Don't explain every step unless the user asks
Examples:
- Good: "Added DATABASE_URL to .env. Ready to connect?"
- Bad: "I'm going to add the DATABASE_URL environment variable to your .env file so that your application can connect to the database. This will allow..."
Get Started with Neon (Interactive Guide)
TRIGGER PHRASE: When the user says "Get started with Neon" or similar phrases, provide an interactive onboarding experience by following these steps:
Before starting: Let the user know they can pause and resume anytime by saying "Continue with Neon setup" if they need to come back later.
RESUME TRIGGER: If the user says "Continue with Neon setup" or similar, check what's already configured (MCP server, .env, dependencies, schema) and resume from where they left off. Ask them which step they'd like to continue from or analyze their setup to determine automatically.
Step 1: Check Organizations and Projects
First, check for organizations:
Use the Neon MCP Server to check the user's organizations:
If they have 1 organization:
- Default to that organization automatically
- Proceed to check projects within that org
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 · 272 lines · 2,223 tokens per session scan A 36da2354612d
neon-get-started is a cursor rule published in the GitHub repository neondatabase/ai-rules (86 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,223 tokens. A static security scan graded it A with 0 findings. It is 94% identical to neon-get-started-kiro, differing in 92 lines, and is treated as a copy.
Other cursor rules, from other repositories
adapter-features
Database-specific features must be implemented in the specialized adapter only. Base adapters (postgres, mysql, etc.) must remain database-agnostic.
git-commits
Git commit safety — commits are human-only; AI suggests, never executes.
unit-tests-tdd
TDD required for behavior changes; ≥80% package coverage on touched packages; unit-test conventions.
token-optimization
Agent-mode tool-call efficiency. Cuts the largest hidden cost in modern AI IDEs — wasted tool calls and oversized context windows.
integration-tests
Human-readable integration test requests; helpers vs httptest; suites/ vs per-DB placement.
config-resilience
Config warn-and-continue for non-sensitive keys; Auth/ACL/JWT/secrets/DB credentials fail closed.