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/suvadityamuk/eye/agents-mdgit clone --depth 1 https://github.com/suvadityamuk/eyeWrote 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/suvadityamuk/eye/agents-md)<a href="https://agentmods.dev/instructions/suvadityamuk/eye/agents-md"><img src="https://agentmods.dev/badge/instructions/suvadityamuk/eye/agents-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 | $0.01501 | $0.01501 |
| Opus 5 | $0.00750 | $0.00750 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
eye 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI Agent Reference for EYE
This document helps AI coding agents understand the EYE 3D viewer codebase for modification, debugging, and extension.
Overview
EYE is a zero-build, single-page 3D object viewer served as static files via Nginx. It uses Three.js (r170) loaded via ES module import maps — there is no bundler, no transpiler, and no node_modules.
Architecture
┌─────────────────────────────────────────────────────┐
│ index.html (single page, all UI structure) │
│ ┌───────────────────────────────────────────────┐ │
│ │ app.js — Main orchestrator │ │
│ │ ├── SceneManager (scene-manager.js) │ │
│ │ ├── FileLoader (file-loader.js) │ │
│ │ ├── ComparisonMode (comparison-mode.js) │ │
│ │ ├── MaterialPanel (material-panel.js) │ │
│ │ ├── LightingPanel (lighting-panel.js) │ │
│ │ ├── AnimationPanel (animation-panel.js) │ │
│ │ └── HistoryPanel (history-panel.js) │ │
│ │ └── HistoryStore (history-store.js) │ │
│ └───────────────────────────────────────────────┘ │
│ style.css (complete design system) │
└─────────────────────────────────────────────────────┘
Key Files
src/js/app.js
- Entry point. Instantiates all modules.
_handleFiles(files)— Central file routing. When comparison mode is active, routes toComparisonMode.loadToSlot(). Otherwise loads into the mainSceneManager._bindSidebarToggles()— Responsive sidebar drawer logic.- All UI event bindings: file upload, drag-and-drop, keyboard shortcuts, panel toggles.
src/js/scene-manager.js
- Manages a single Three.js scene: renderer, camera, controls, lights, grid/axes helpers.
setModel(object, clips)— Replaces current model, auto-fits camera._resize()— Called every frame in_animate(), accounts for pixel ratio and 0-dimension guards._fitCameraToModel(object)— Centers camera on model bounding box.- Constructor takes a
<canvas>element and sets up the full rendering pipeline.
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.
- 3d ago First seen · 125 lines · 1,501 tokens per session scan A dfd855bf44cf
eye AGENTS.md is an instructions file published in the GitHub repository suvadityamuk/eye (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,501 tokens to every session, about $0.0075 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
3d-resources CLAUDE.md
Claude Code instructions for devanshutak25/3d-resources, covering 3dresources — project rules, project.md (mandatory), controlled vocabulary (entry tags), validation and writing style (user-facing text).
Unity-AI-ProBuilder CLAUDE.md
Instructions for IvanMurzak/Unity-AI-ProBuilder, covering claude.md, what this is, build / run, critical invariants and find detail in.
Three.js-Claude-Skill-Package CLAUDE.md
Instructions for Impertio-Studio/Three.js-Claude-Skill-Package, covering three.js skill package — claude.md, standing orders — read this first, identity, privacy protocol (p-000a) and workspace setup protocol (p-000b).
blender-agent-studio AGENTS.md
Instructions for ifBars/blender-agent-studio, a project described as: Codex plugin for reproducible Blender modeling, validation, animation, MCP tooling, and agent benchmarking.
chisel AGENTS.md
Instructions for EYamanS/chisel, covering chisel — contributor guide, where things live, conventions and commands.
BlenderToRive3D CLAUDE.md
Claude Code instructions for pencilpark/BlenderToRive3D, covering blender to rive 3d export — universal guide, workflow orchestration, 1. plan mode default, 2. subagent strategy to keep main context window clean and 3. mandatory: self-improvement loop mandatory.