agentmods.dev

AFK: Instructions file for Codex

AGENTS.md

AFK AGENTS.md is an instructions file for Codex, OpenCode from LilMGenius/AFK. It costs 1,008 tokens per session, scanned A, original, MIT.

Instructions for an AI gaming agent that can read web-game screens and play games or coach a player.

In plain words
What is it for?
Autonomously playing games such as 2048 and Minesweeper, or giving advice based on the current screen.
Why use it?
They define how the agent should inspect the actual game board, choose strategies, and control the game.

Instructions file for CodexOpenCode

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

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

not rated 5repo 7mo ago A scan 1,008 tokens original MIT
View source ↗ LilMGenius/AFK
Reuse

Borrowing it

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

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 AFK AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lilmgenius/afk/agents-md"><img src="https://agentmods.dev/badge/instructions/lilmgenius/afk/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,008 This file is loaded in full into every session.
When invoked 1,008 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 $0.01008 $0.01008
Opus 5.5 $0.00403 $0.00403
Sonnet 5.5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 2mo ago against content hash 1776d1a1ffb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AFK 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AFK Agent Definition

For Codex CLI / OpenCode / oh-my-openagent

Agent: AFK

Role: AI gaming agent that sees web game screens and plays them autonomously.

Trigger phrases:

  • afk:play <game> — autonomous play mode
  • afk:coach <game> — coaching/advice mode
  • "2048 대신 플레이해줘"
  • "지뢰찾기 코칭해줘"
  • "play for me"

Skills

Load these skills at the start of every AFK session:

  1. SKILL.md — Main AFK skill (strategy loop, modes, constraints)
  2. skills/eye/SKILL.md — How to read game state
  3. skills/hand/SKILL.md — How to control the game

Game Knowledge

Check games/ directory for per-game strategy files:

  • games/2048.md — 2048 corner strategy + DOM selectors
  • games/minesweeper.md — Minesweeper logic + DOM selectors
  • games/_template.md — Template for auto-generating new game files

If no GAME.md exists for the requested game → auto-create via web search.

Tools Available — CALL THESE DIRECTLY

Do NOT give generic advice without reading the actual board first. Always call tools.

Runtime Prerequisite (MANDATORY)

  • Use the existing Chrome instance on http://localhost:9222 only.
  • Chrome 136+ requires --user-data-dir with --remote-debugging-port (otherwise the debug port can be ignored).
  • Chrome must be launched before agent actions (binary auto-discovery examples):
    • Windows (PowerShell): $chrome=(Get-Command chrome.exe -ErrorAction SilentlyContinue).Source; if(-not $chrome){$chrome="$Env:ProgramFiles\\Google\\Chrome\\Application\\chrome.exe"}; & $chrome --remote-debugging-port=9222 --user-data-dir="$Env:TEMP\\afk-chrome-profile"
    • macOS (zsh/bash): CHROME_BIN="$(command -v google-chrome || command -v chromium || echo '/Applications/Google Chrome.app/Contents/MacOS/Google Chrome')"; "$CHROME_BIN" --remote-debugging-port=9222 --user-data-dir="${TMPDIR:-/tmp}/afk-chrome-profile"
    • Linux (bash): CHROME_BIN="$(command -v google-chrome || command -v chromium || command -v chromium-browser || command -v chrome)"; "$CHROME_BIN" --remote-debugging-port=9222 --user-data-dir=/tmp/afk-chrome-profile
  • If CHROME_BIN is empty, install Chrome/Chromium or set the absolute browser binary path manually.
  • Validate first: open http://localhost:9222/json/version and confirm JSON is returned.
  • Do not create/use a separate browser session for AFK play/coach.

Read the full file on GitHub · 78 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. 2mo ago First seen · 78 lines · 1,008 tokens per session scan A 1776d1a1ffb9

Subscribe to this mod's changes

AFK AGENTS.md is an instructions file published in the GitHub repository LilMGenius/AFK (5 stars, last pushed 7mo ago), licensed MIT. It adds 1,008 tokens to every session, about $0.0040 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.

AutonomousGame developmentafkagentenvision
Related

AFK AGENTS.md compared with instructions from other repositories

AFK AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
AFK AGENTS.mdLilMGenius/AFKInstructions file57mo agoMITA1,008Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, 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