agent-skills AGENTS.md

agent-skills AGENTS.md is an instructions file for Codex, OpenCode from neondatabase/agent-skills. It costs 4,095 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for coding agents working on a Neon plugin package. They explain the repository layout, packaging rules, and where skills and MCP settings belong.

In plain words
What is it for?
Use them when editing the repository, especially its plugin manifest, MCP configuration, skills, publishing process, or marketplace integrations.
Why use it?
They give agents the project context and prevent them from putting configuration in the wrong place or breaking the package format.

Instructions file for CodexOpenCode

About the project

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.

neondatabase/agent-skills · 85 stars · on GitHub

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/neondatabase/agent-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/neondatabase/agent-skills

Made for: Codex, OpenCode.

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 agent-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/neondatabase/agent-skills/agents-md.svg)](https://agentmods.dev/instructions/neondatabase/agent-skills/agents-md)
Your own site
<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>
Per session 4,095 This file is loaded in full into every session.
When invoked 4,095 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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 8a0be516b4d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

AGENTS.md · 264 lines

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.json schema is closed. Only $schema, name, version, description, author, homepage, repository, license, keywords, and extensions are allowed. Client fields such as skills, mcpServers, hooks, or logo are nonconforming at the top level — MCP servers go in mcp.json, skills are discovered from skills/, and anything else client-specific goes under a reverse-domain extensions namespace owned by the client.
  • mcp.json transports are stdio, streamable-http, or sse. Note that this differs from plugins/neon-postgres/mcp.json, which uses Claude/Cursor's http spelling; the two files are intentionally not identical.
  • Only immediate children of skills/ are discovered, and each SKILL.md frontmatter name must match its directory.
  • Hooks, agents, commands, LSP servers, and the marketplace.json catalogs are not portable v1 components. Hooks and the rest belong inside a plugin under plugins/; the catalogs stay at the repo root in .claude-plugin/ and .cursor-plugin/, where Claude Code and Cursor look for them, and point back into plugins/. v1 only claims plugin.json, mcp.json, and skills/, so conforming clients ignore those extra root directories.
  • kimi.plugin.json is Kimi Code's own manifest and is not a v1 component either, so the closed-schema rule above does not apply to it. It declares skills and mcpServers inline — nonconforming at the top level of a v1 manifest, but necessary because Kimi does not read mcp.json — and it points at the same skills/ directory, so it needs no vendoring. Conforming v1 clients ignore it, the same way they ignore the catalogs.

Read the full file on GitHub · 264 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. 5d ago First seen · 264 lines · 4,095 tokens per session scan A 8a0be516b4d2

Subscribe to this mod's changes

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.

Related

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.

openai/codex · 5,182 tokens

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

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.

github/spec-kit · 7,104 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens