adminforth: Instructions file for Codex

AGENTS.md

adminforth AGENTS.md is an instructions file for Codex, OpenCode from devforth/adminforth. It costs 1,710 tokens per session, scanned A, original, MIT.

A set of project instructions for devforth and adminforth repositories, covering package management, naming, documentation paths, and engineering rules.

In plain words
What is it for?
Use it when adding packages, plugins, adapters, Docusaurus pages, demos, documentation, or code to these projects.
Why use it?
It helps coding agents follow the repository’s existing conventions instead of making inconsistent package, documentation, or code decisions.

Instructions file for CodexOpenCode

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

This is devforth/adminforth's own configuration. It tells Codex and OpenCode how to work on adminforth 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 adminforth configures →

Reuse

Borrowing it

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

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 adminforth AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/devforth/adminforth/agents-md"><img src="https://agentmods.dev/badge/instructions/devforth/adminforth/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,710 This file is loaded in full into every session.
When invoked 1,710 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 $0.01710 $0.01710
Opus 5.5 $0.00684 $0.00684
Sonnet 5.5 $0.00342 $0.00342
Haiku 4.5 $0.00171 $0.00171

Measured 7d ago against content hash 00c589e7c923, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adminforth 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 7d 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 · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Package manager

All packages and projects in this repo use pnpm and not npm. Howeverer internally (e.g. in codeInjector) adminforth still supports both npm and pnpm style install commands, so users of framework itself can use it with either package manager. But in all dev demo/live demo, plugins, adapters, and documentation, we use pnpm as the standard.

SPA build folder

Never patch anything in spa_tmp (e.g. /tmp/adminforth/<app>/spa_tmp): no file edits, no pnpm install, no own vite or other commands there. codeInjector generates it from adminforth/spa and the custom components of the app and its plugins, a manual install there drops the packages it adds for plugins. After a change in spa/package.json or spa/tailwind.config.js the running app breaks until a restart, tell the user to restart it.

Dev demo login

To log in to the local dev-demo (http://localhost:3123) use agent as username and agent as password. The user is created on start and is exempt from 2FA. Do not use adminforth, it may have 2FA set up in the local database.

Package names rules

All adapters and plugins always have @adminforth/ prefix in their package name, followed by short lowercase kebab-case plugin/adpater slug.

Every plugin has at least one Docusaurus docs page, which should use the path /docs/tutorial/Plugins/<plugin-slug>/.

Same for adapters, but with /docs/tutorial/Adapters/<adapter-slug>/ path.

Page names in docusarus should be human readabale. We should not use AuditLog but instead we should have Audit Log via whitespace.

Design system

UI rules (tokens, af-/afcl- class contract, AFCL first, Lucide icons, moving off flowbite) live in Design concepts, read them before changing UI in core or plugins. States and variants of components are drawn in adminforth/design/system.html, the progress of core and plugins is in adminforth/design/adoption.md.

Commits

Read the full file on GitHub · 246 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. 7d ago Changed · +4 lines · +68 tokens per session 00c589e7c923
  2. 18d ago Changed · +12 lines · +247 tokens per session fa184453577a
  3. 2mo ago First seen · 230 lines · 1,395 tokens per session scan A 6bfb3b96d744

Subscribe to this mod's changes

adminforth AGENTS.md is an instructions file published in the GitHub repository devforth/adminforth (392 stars, last pushed yesterday), licensed MIT. It adds 1,710 tokens to every session, about $0.0068 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 2026-08-30.

Related

adminforth AGENTS.md compared with instructions from other repositories

adminforth AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
adminforth AGENTS.mddevforth/adminforthInstructions file392yesterdayMITA1,710Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode