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.
npx agentmods add instructions/lilmgenius/afk/claude-mdgit clone --depth 1 https://github.com/LilMGenius/AFKWrote 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.
[](https://agentmods.dev/instructions/lilmgenius/afk/claude-md)<a href="https://agentmods.dev/instructions/lilmgenius/afk/claude-md"><img src="https://agentmods.dev/badge/instructions/lilmgenius/afk/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00523 | $0.00523 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
AFK CLAUDE.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 5d 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.
What it actually says
AFK — Claude Code Project
Eyes & Hands for AI Agents. You go AFK. AI opens its eyes, grabs your mouse.
What This Project Is
AFK gives Claude Code (and any CLI agent) the ability to see web game screens and control them autonomously.
- Eye (
skills/eye/SKILL.md): How to read game state via DOM/CDP - Hand (
skills/hand/SKILL.md): How to control games via CDP/keyboard - Brain: That's YOU, Claude. The CLI is the brain. Don't build another one.
How to Use
Load the main skill and start playing:
# Coach mode (advise only)
Read SKILL.md, then: afk:coach 2048
# Play mode (autonomous)
Read SKILL.md, then: afk:play 2048
Project Structure
afk/
├── SKILL.md ← Main AFK skill (start here)
├── skills/
│ ├── eye/SKILL.md ← How to see
│ └── hand/SKILL.md ← How to act
├── games/ ← Per-game strategy files
│ ├── _template.md ← Template for new games
│ ├── 2048.md
│ └── minesweeper.md
├── chrome-extension/ ← Visual overlay (Play badge + Coach panel)
└── server.js ← WebSocket server (CLI ↔ Extension)
Core Principles
- Brain = CLI: Claude IS the brain. No separate AI module.
- Code = Minimal: Chrome Extension ~100 lines. Everything else is Markdown.
- GAME.md = Plugin: Each game file is a plugin. Community can contribute.
- DOM First: Read DOM before taking screenshots. Faster, cheaper, more accurate.
Starting a Session
- Read
SKILL.mdfor the full AFK skill - Read
skills/eye/SKILL.mdandskills/hand/SKILL.md - Check
games/for the target game's strategy file - Start the strategy loop
WebSocket Server (Optional)
For Chrome Extension overlay:
node server.js
# Starts WebSocket on ws://localhost:38377
# Load chrome-extension/ in Chrome for visual overlay
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.
- 5d ago First seen · 63 lines · 523 tokens per session scan A 3a0deeee429f
AFK CLAUDE.md is an instructions file published in the GitHub repository LilMGenius/AFK (5 stars, last pushed 5mo ago), licensed MIT. It adds 523 tokens to every session, about $0.0026 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 2026-08-31.
Other instructions, from other repositories
nanobrowser CLAUDE.md
Instructions for nanobrowser/nanobrowser, covering claude.md, project overview, development commands, workspace tips and architecture.
browser-control AGENTS.md
Instructions for keon/browser-control: Use this project as a tiny browser pipe, not an agent framework.
agent-zero AGENTS.md
AGENTS.md instructions for agent0ai/agent-zero, covering agent zero dox, purpose, project, root ownership and project-wide contracts.
barebrowse CLAUDE.md
Claude Code instructions for hamr0/barebrowse, covering dev rules and project specifics.
worbrow AGENTS.md
AGENTS.md instructions for noisystreet/worbrow, covering agents.md, project identity, hard constraints (revert on violation), modifying architecture docs and commit conventions.
ai-auto-work CLAUDE.md
Claude Code instructions for chaohong-ai/ai-auto-work, covering gamemaker - ai native 游戏创作平台, 项目简介, ai 工作目录约定 and 按需加载（不默认装载）.