einbiogpt AGENTS.md

Project instructions for an einbiogpt application built with Next.js, TypeScript, React, Tailwind CSS, and shadcn/ui. They describe the project structure, commands, language, and coding conventions.

In plain words
What is it for?
Use them when developing, building, starting, cleaning, or running Docker for the application, and when following its import and TypeScript rules.
Why use it?
They give AI coding agents the context needed to build and run the project consistently, including its Persian right-to-left interface.

Instructions file for CodexOpenCode

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/ehsanghaffar/einbiogpt/agents-md
Clone the repo
git clone --depth 1 https://github.com/ehsanghaffar/einbiogpt

Made for: Codex, OpenCode.

Per session 885 This file is loaded in full into every session.
When invoked 885 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 $0.00885 $0.00885
Opus 5 $0.00443 $0.00443
Sonnet 5 $0.00177 $0.00177
Haiku 4.5 $0.00089 $0.00089

Measured yesterday against content hash 40b7f87be12b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

einbiogpt 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 yesterday.

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 · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Coding Guidelines for AI Agents

Project Overview

  • Framework: Next.js 14+ with App Router
  • Language: TypeScript 4.9.4
  • UI: React 18.2.0 + Tailwind CSS 3.2.4
  • Components: shadcn/ui (Radix UI primitives)
  • Package Manager: Yarn 1.22.22
  • Language: Persian/Farsi (RTL direction)

Build/Development Commands

# Development server
yarn dev

# Production build
yarn build

# Start production server
yarn start

# Clean and reinstall dependencies
yarn run clean

# Docker commands (via Makefile)
make build          # Build Docker containers
make start          # Start containers in detached mode
make logs           # View container logs
make stop           # Stop containers

Note: No lint, test, or format commands are currently configured.

Code Style Guidelines

TypeScript Configuration

  • Target: ES5
  • Strict mode enabled
  • Module resolution: Node
  • Path alias: @/* maps to root directory
  • JSX: preserve (Next.js handles compilation)

Import Order

  1. React/Next.js imports
  2. Third-party libraries
  3. Internal UI components (@/components/ui/*)
  4. Other internal components (@/components/*)
  5. Utilities (@/lib/utils)
  6. Types
  7. Styles

Naming Conventions

  • Components: PascalCase (e.g., BioGenerator, Header)
  • Hooks: camelCase starting with use (e.g., useState)
  • Utilities: camelCase (e.g., cn, errorHandler)
  • Types/Interfaces: PascalCase (e.g., ButtonProps)
  • Files: kebab-case for utilities, PascalCase for components

Component Structure

"use client"; // If client component (before imports)

import { useState } from "react"; // React imports first
import { motion } from "framer-motion"; // Third-party
import { Button } from "@/components/ui/button"; // UI components
import { cn } from "@/lib/utils"; // Utilities

// Types
interface Props {
  // ...
}

// Component
export const ComponentName = ({ prop }: Props) => {
  // Hooks
  const [state, setState] = useState();
  
  // Handlers
  const handleClick = () => {};
  
  // Render
  return <div>...</div>;
};

export default ComponentName;

Read the full file on GitHub · 132 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. yesterday First seen · 132 lines · 885 tokens per session scan A 40b7f87be12b

Subscribe to this mod's changes

einbiogpt AGENTS.md is an instructions file published in the GitHub repository ehsanghaffar/einbiogpt (19 stars, last pushed 7d ago), licensed MIT. It adds 885 tokens to every session, about $0.0044 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.