It helps inspect canvas visuals, browser logs, and exceptions while developing or debugging games and other browser applications.

It helps an agent understand what a browser application actually displays and why it fails, instead of relying only on source code or text logs.

How monteslu/vibe-eyes configures Claude Code

Q: What is vibe-eyes CLAUDE.md?

A project guide for Vibe-Eyes, an MCP server that gives coding agents visual and debugging information from browser games and applications. It captures canvas output, logs, and errors, then makes that context available to the agent.

Reuse

Borrowing it

Nothing to install: this file belongs to monteslu/vibe-eyes. 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/monteslu/vibe-eyes/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/monteslu/vibe-eyes

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/monteslu/vibe-eyes/claude-md/github.svg)](https://agentmods.dev/instructions/monteslu/vibe-eyes/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/monteslu/vibe-eyes/claude-md"><img src="https://agentmods.dev/badge/instructions/monteslu/vibe-eyes/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/monteslu/vibe-eyes/claude-md"><img src="https://agentmods.dev/badge/instructions/monteslu/vibe-eyes/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,489 This file is loaded in full into every session.

When invoked 1,489 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.

Model	Per session	Once invoked
Fable 5.1	$0.01489	$0.01489
Opus 5.5	$0.00596	$0.00596
Sonnet 5.5	$0.00298	$0.00298
Haiku 4.5	$0.00149	$0.00149

Measured 2mo ago against content hash e24cbb723322, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vibe-eyes 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 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.

CLAUDE.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Vibe-Eyes Project Guide

Vibe-Eyes focuses on providing visual context and debug information to LLMs during vibe coding sessions.

Vibe-Eyes uses a client-server architecture where a lightweight browser client captures canvas content and debug information, sends it to a Node.js server via WebSockets, which then vectorizes the images into compact SVG representations and makes them available to LLMs through the Model Context Protocol (MCP).

Project Overview

Vibe-Eyes is an MCP server that gives LLMs (like yourself) an approximation of canvas output and debug information from browser games and applications. It enables more effective "vibe coding" sessions by letting you see what's happening in the application.

flowchart LR
    A["Game/App"] -->|"Canvas<br/>Logs<br/>Exceptions"| B["Client.js"]
    B -->|"WebSocket"| C["MCP Server"]
    C -->|"getGameDebug()"| D["Claude/LLM"]
    D -->|"Debugging Help"| A
    
    classDef default color:#000,font-weight:bold
    classDef edgeLabel color:#333,font-size:12px
    
    style A fill:#c0e0ff,stroke:#000,stroke-width:2px
    style B fill:#ffe0a0,stroke:#000,stroke-width:2px
    style C fill:#b0e0a0,stroke:#000,stroke-width:2px
    style D fill:#ffb0d0,stroke:#000,stroke-width:2px

Project Structure

vectorizer.js - Core SVG vectorization library
mcp.js - MCP server that receives canvas captures and exposes them to LLMs
Browser client - Available at vibe-eyes-client repository for capturing canvas and console output
cli.js - Standalone CLI tool for vectorization (not central to main functionality)

Key Commands

Install: npm install
Start MCP server: npm run server (or node mcp.js)
Use vectorizer CLI: vibe-eyes-vectorize input.png output.svg

MCP Tool Usage

Vibe-Eyes provides a single, powerful MCP tool called getGameDebug that gives you visual and debug insight into what's happening in the user's browser:

Read the full file on GitHub · 143 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.

2mo ago First seen · 143 lines · 1,489 tokens per session scan A e24cbb723322

Subscribe to this mod's changes

vibe-eyes CLAUDE.md is an instructions file published in the GitHub repository monteslu/vibe-eyes (54 stars, last pushed 9mo ago), licensed MIT. It adds 1,489 tokens to every session, about $0.0060 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.

Browser automation Debugging LLM ai canvas claude game-development

vibe-eyes CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vibe-eyes CLAUDE.mdmonteslu/vibe-eyes	Instructions file	54	9mo ago	MIT	A	1,489	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

vibe-eyes: Instructions file for Claude Code