What is agent-guide AGENTS.md?

Repository instructions for production-agent-guide, an npm package and command-line tool that provides reusable rules for AI coding agents. They describe the repository's purpose, layout, key files, and operating rules.

Use them when working on the package, its CLI, its agent instructions, backend or frontend rules, documentation, or publishing setup.

They give coding agents the context and constraints needed to make clear, safe, consistent changes in this repository and in projects using its guidance.

How toybz-creator/agent-guide configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to toybz-creator/agent-guide. 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/toybz-creator/agent-guide/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/toybz-creator/agent-guide

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/toybz-creator/agent-guide/agents-md/github.svg)](https://agentmods.dev/instructions/toybz-creator/agent-guide/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/toybz-creator/agent-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/toybz-creator/agent-guide/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/toybz-creator/agent-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/toybz-creator/agent-guide/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,356 This file is loaded in full into every session.

When invoked 3,356 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.

Model	Per session	Once invoked
Fable 5.1	$0.03356	$0.03356
Opus 5.5	$0.01342	$0.01342
Sonnet 5.5	$0.00671	$0.00671
Haiku 4.5	$0.00336	$0.00336

Measured 2mo ago against content hash 853a64cb9541, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-guide 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 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.

AGENTS.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Purpose

This repository builds production-agent-guide, a reusable rule framework for AI coding agents. The project exists to make coding agents more production-minded, context-aware, safe, thorough, and useful across many downstream software projects.

Agents working here must treat this repository as both:

a normal npm package with a CLI and published files
the source of truth for instructions that other coding agents will follow

Because the package teaches agents how to behave, every change must be unusually clear, explicit, operational, and easy for a future agent to apply from a minimal user prompt.

Repository Map

README.md: public package overview, install instructions, activation snippet, setup flow, expected behavior, customization guidance, and publishing commands.
instructions.md: base operating framework for coding agents. This is the primary behavior document, including the Update harness and skill-command workflows.
backend/backend-rules.md: production backend, API, data, reliability, observability, security, and operations rules.
frontend/frontend-rules.md: production frontend, UI, accessibility, state, integration, performance, and testing rules.
mobile/react-native-rules.md: production React Native and Expo architecture, UX, accessibility, native integration, performance, offline, security, testing, store, and release rules.
computer-use/computer-use-agent-rules.md: browser automation, screenshots, desktop interaction, and UI verification rules.
docs/: packaged library and framework references for supported stacks such as NextJS, NestJS, React, and TypeORM and so on.
scripts/supply-chain-audit.mjs: built-in supply-chain audit scaffold copied into downstream projects.
scripts/codebase-consistency-codemod.mjs: built-in consistency codemod scaffold copied into downstream projects.
bin/pag.mjs: CLI entrypoint for init, doctor, recommend, snippet, and help; it defines required downstream harness/ files, skill templates, and scaffold/doctor behavior.
package.json: npm metadata, package files, binary mapping, scripts, and engine requirement.
ignore.md: reference material that is not part of the active package contract unless the user explicitly asks to inspect it.

Read the full file on GitHub · 270 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.

2mo ago First seen · 270 lines · 3,356 tokens per session scan A 853a64cb9541

Subscribe to this mod's changes

agent-guide AGENTS.md is an instructions file published in the GitHub repository toybz-creator/agent-guide (5 stars, last pushed 3mo ago), licensed MIT. It adds 3,356 tokens to every session, about $0.0134 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 2026-08-31.

agent-guide AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-guide AGENTS.mdtoybz-creator/agent-guide	Instructions file	5	3mo ago	MIT	A	3,356	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

agent-guide: Instructions file for Codex