Neon Agent Skills is a collection of agent instructions, scripts, and resources for working with Neon’s cloud backend services built around Lakebase Postgres. Developers, startups, and agent platforms use it to guide work with databases, branches, authentication, storage, functions, and AI Gateway services.
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/neondatabase/agent-skills/agents-mdgit clone --depth 1 https://github.com/neondatabase/agent-skillsWrote 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/neondatabase/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/neondatabase/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/neondatabase/agent-skills/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 5.1 | $0.04095 | $0.04095 |
| Opus 5 | $0.02048 | $0.02048 |
| Sonnet 5 | $0.00819 | $0.00819 |
| Haiku 4.5 | $0.00409 | $0.00409 |
Grade A, and why
agent-skills AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with code in this repository.
For the complete Agent Skills specification, see: https://agentskills.io/specification
Repository Overview
A collection of skills for coding agents for working with Neon. Skills are packaged instructions and documentation that extend the agent's capabilities.
The repo root is a portable Agent Plugins v1 package
The root plugin.json and mcp.json make this repository directly installable by any client that implements the Agent Plugins v1 specification. Everything the portable format defines lives at the root: the manifest, the MCP configuration, and the skills as immediate children of skills/.
Rules to keep in mind when touching these files:
- The
plugin.jsonschema is closed. Only$schema,name,version,description,author,homepage,repository,license,keywords, andextensionsare allowed. Client fields such asskills,mcpServers,hooks, orlogoare nonconforming at the top level — MCP servers go inmcp.json, skills are discovered fromskills/, and anything else client-specific goes under a reverse-domainextensionsnamespace owned by the client. mcp.jsontransports arestdio,streamable-http, orsse. Note that this differs fromplugins/neon-postgres/mcp.json, which uses Claude/Cursor'shttpspelling; the two files are intentionally not identical.- Only immediate children of
skills/are discovered, and eachSKILL.mdfrontmatternamemust match its directory. - Hooks, agents, commands, LSP servers, and the
marketplace.jsoncatalogs are not portable v1 components. Hooks and the rest belong inside a plugin underplugins/; the catalogs stay at the repo root in.claude-plugin/and.cursor-plugin/, where Claude Code and Cursor look for them, and point back intoplugins/. v1 only claimsplugin.json,mcp.json, andskills/, so conforming clients ignore those extra root directories. kimi.plugin.jsonis Kimi Code's own manifest and is not a v1 component either, so the closed-schema rule above does not apply to it. It declaresskillsandmcpServersinline — nonconforming at the top level of a v1 manifest, but necessary because Kimi does not readmcp.json— and it points at the sameskills/directory, so it needs no vendoring. Conforming v1 clients ignore it, the same way they ignore the catalogs.
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.
- 5d ago First seen · 264 lines · 4,095 tokens per session scan A 8a0be516b4d2
agent-skills AGENTS.md is an instructions file published in the GitHub repository neondatabase/agent-skills (85 stars, last pushed today), licensed Apache-2.0. It adds 4,095 tokens to every session, about $0.0205 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).