better-drizzle: Instructions file for Codex

AGENTS.md

better-drizzle AGENTS.md is an instructions file for Codex, OpenCode from almeidazs/better-drizzle. It costs 5,413 tokens per session, scanned A, original, Apache-2.0.

Architecture and design notes for Better-Drizzle, a Bun and TypeScript workspace that extends Drizzle ORM, a library for working with databases. It covers the core package, plugins, benchmarks, examples, and documentation site.

In plain words
What is it for?
Use it when changing the core library, adding or updating plugins, running benchmarks, editing examples, or maintaining the documentation.
Why use it?
It explains how the packages fit together and records rules intended to keep the library compatible and efficient compared with Drizzle ORM.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Gemini CLI.

This is almeidazs/better-drizzle's own configuration. It tells Codex and OpenCode how to work on better-drizzle 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 better-drizzle configures →

Reuse

Borrowing it

Nothing to install: this file belongs to almeidazs/better-drizzle. 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/almeidazs/better-drizzle/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/almeidazs/better-drizzle

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 better-drizzle AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/almeidazs/better-drizzle/agents-md/github.svg)](https://agentmods.dev/instructions/almeidazs/better-drizzle/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/almeidazs/better-drizzle/agents-md"><img src="https://agentmods.dev/badge/instructions/almeidazs/better-drizzle/agents-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 better-drizzle AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/almeidazs/better-drizzle/agents-md"><img src="https://agentmods.dev/badge/instructions/almeidazs/better-drizzle/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,413 This file is loaded in full into every session.
When invoked 5,413 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 $0.05413 $0.05413
Opus 5 $0.02707 $0.02707
Sonnet 5 $0.01083 $0.01083
Haiku 4.5 $0.00541 $0.00541

Measured 9d ago against content hash 2d3e99536e0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

better-drizzle 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 9d 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 · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Better-Drizzle Repository – Agent Field Notes

Meta note: This is the primary agent knowledge base file for this repository. When learning something about the codebase that will help with future tasks, update this file directly.

  • Repository scope: better-drizzle is a small Bun/TypeScript workspace focused on a single core package, packages/core, plus a benchmark suite used to measure API-parity performance and memory overhead against raw Drizzle ORM.
  • Workspace layout:
    • packages/core: the published library
    • packages/rules: official runtime rules/guardrails plugin
    • packages/eslint: official ESLint plugin for static Better Drizzle guardrails
    • packages/soft-delete: official soft delete plugin
    • packages/timestamps: official timestamps plugin
    • packages/zod: official Zod schema generation and validation plugin
    • benchmark: Bun + SQLite benchmark suite
    • examples: Markdown-only example catalog and usage guides
    • apps/web: Next.js + Fumadocs documentation/marketing site
    • README.md: project-level documentation
    • packages/core/README.md: package-level documentation, currently intentionally kept in sync with the root README
  • Package manager and runtime: Bun is the primary runtime for local commands and benchmarks. The workspace is configured as a TypeScript ESM monorepo.
  • Package publishing/build:
    • all published workspace libraries now build to dist/
    • each package emits dist/index.js (ESM), dist/index.cjs (CommonJS), and dist/index.d.ts
    • root build entrypoint is scripts/build.ts, powered by Bun.build plus tsc declaration emit
    • keep package bundle minification disabled in scripts/build.ts; the published 0.1.0 minified Bun build produced broken export footers (dist/index.js/dist/index.cjs) with unresolved symbols at import time
    • package manifests publish only dist, README.md, and LICENSE
    • published package manifests now use conditional type exports: ESM reads dist/index.d.ts and CJS reads dist/index.d.cts
    • scripts/build.ts post-processes emitted declarations after all package builds: relative specifiers are rewritten for NodeNext compatibility (directory imports become .../index.js), .d.cts copies are generated, and declaration-only internal modules get tiny ESM stub .js files so TypeScript can resolve the declaration graph from published tarballs
  • Top-level scripts:
    • bun run bench: run the time benchmark suite
    • bun run bench:memory: run the memory/overhead benchmark suite
    • bun run bench:all: run both benchmark suites
  • Core dependencies:
    • drizzle-orm as a peer dependency
    • typescript as a peer dependency
    • mitata for benchmarking
    • @biomejs/biome for formatting and linting
    • the published compatibility floor is drizzle-orm@^0.30.0; 0.29.5 failed the workspace typecheck, while 0.30.0 passed typecheck plus the core/plugin test suites

Read the full file on GitHub · 344 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. 9d ago First seen · 344 lines · 5,413 tokens per session scan A 2d3e99536e0a

Subscribe to this mod's changes

better-drizzle AGENTS.md is an instructions file published in the GitHub repository almeidazs/better-drizzle (304 stars, last pushed 7d ago), licensed Apache-2.0. It adds 5,413 tokens to every session, about $0.0271 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