agentmods.dev

AFK: Skill for Claude Code

.cursor/skills/eye/SKILL.md

eye is a skill for Claude Code, Cursor from LilMGenius/AFK. It costs 37 tokens per session (261 once invoked), scanned A, original, MIT.

An internal skill for reading the current state of a browser game from its page. It is used by other gaming skills and is not intended to be called directly.

In plain words
What is it for?
Use it as part of an automated game-playing system to inspect the board, controls, and current game state.
Why use it?
It gives the gaming agent the information needed to choose its next action, including a fallback when the page structure is unclear.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/.

This is LilMGenius/AFK's own configuration. It tells Claude Code and Cursor 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 37 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/.cursor/skills/eye/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LilMGenius/AFK

Made for: Claude Code, Cursor.

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 eye

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lilmgenius/afk/eye"><img src="https://agentmods.dev/badge/skills/lilmgenius/afk/eye.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 261 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00037 $0.00261
Opus 5.5 $0.00015 $0.00104
Sonnet 5.5 $0.00007 $0.00052
Haiku 4.5 $0.00004 $0.00026

Measured 2mo ago against content hash 66173c5ef23b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eye 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.

.cursor/skills/eye/SKILL.md · 24 lines

What it actually says

Eye: Read Game State

Internal skill. Called by afk-play and afk-coach. Reads the current game board from the browser.

Tool Priority

  1. mcp__chrome_devtools__evaluate_script — run the Eye Script from games/<game>.md (fastest, most accurate)
  2. mcp__chrome_devtools__take_snapshot — get accessibility tree with element UIDs
  3. mcp__chrome_devtools__take_screenshot — visual fallback for canvas/WebGL only

Rules

  • Always use the Eye Script from games/<game>.md first
  • Extract only what is needed for the next decision — no full DOM dumps
  • If DOM returns empty: check document.readyState — page may still be loading
  • If selectors don't match: use take_snapshot to find actual structure, then update games/<game>.md
  • DOM first. Screenshot only when DOM has no game state (canvas games).
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 · 24 lines · 37 tokens per session scan A 66173c5ef23b

Subscribe to this mod's changes

eye is a skill published in the GitHub repository LilMGenius/AFK (5 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 261 once invoked, about $0.0001 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

eye compared with skills from other repositories

eye next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
eyeLilMGenius/AFKSkill57mo agoMITA37Claude Code, Cursor
blender-motion-state-inspectionDekaPrayoga/AurixAgentSkill623mo agononeA43Claude Code, Codex
develop-web-gamenetease-youdao/LobsterAISkill6.2kyesterdayMITA64Codex
sable-game-art-opsmakecindy/cindySkill9.3kyesterdayApache-2.0A89Claude Code, Codex
threejs-fundamentalscalesthio/OpenMontageSkill77k3d agoAGPL-3.0A51Claude Code, Codex
threejs-geometrycalesthio/OpenMontageSkill77k3d agoAGPL-3.0A46Claude Code, Codex
threejs-world-generationcalesthio/OpenMontageSkill77k3d agoAGPL-3.0A100Codex