agentmods.dev

Unity-Phanto copilot-instructions.md

Project instructions for a Meta Quest and Horizon OS sample called Unity-Phanto. They point developers to the project's main guidance and recommended tools for device, build, deployment, debugging, and performance work.

In plain words
What is it for?
Working on the Unity-Phanto sample, including building, deploying to Meta Quest devices, debugging, reading logs, and investigating performance on Horizon OS.
Why use it?
They help an agent use the project's intended tools and follow its platform-specific guidance instead of applying generic Unity or Android assumptions.

Instructions file for GitHub Copilot

272 3mo ago A scan 111 tokens copy · 100% MIT
View the source file oculus-samples/Unity-Phanto
Install

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.

agentmods
npx agentmods add instructions/oculus-samples/unity-phanto/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/oculus-samples/Unity-Phanto

Made for: GitHub Copilot.

Per session 111 This file is loaded in full into every session.
When invoked 111 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00111 $0.00111
Opus 5 $0.00056 $0.00056
Sonnet 5 $0.00022 $0.00022
Haiku 4.5 $0.00011 $0.00011

Measured 2d ago against content hash df904f7b34dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Unity-Phanto copilot-instructions.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 2d 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.

Origin

This is a copy

100% identical to Unity-TheWorldBeyond copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/copilot-instructions.md · 16 lines

What it actually says

This is a Meta Quest / Horizon OS sample.

Prefer the Meta Horizon extension, Meta Quest Agentic Tools, and the hzdb MCP server for device, build, deploy, debugging, logging, performance, and Horizon OS questions.

Read AGENTS.md for the canonical agent instructions.

Recommended VS Code extension:

https://marketplace.visualstudio.com/items?itemName=meta.meta-vr-dev

Recommended MCP setup for VS Code:

npx -y @meta-quest/hzdb mcp install vscode
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. 2d ago First seen · 16 lines · 111 tokens per session scan A df904f7b34dc

Subscribe to this mod's changes

Unity-Phanto copilot-instructions.md is an instructions file published in the GitHub repository oculus-samples/Unity-Phanto (272 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Unity-TheWorldBeyond copilot-instructions.md, differing in 0 lines, and is treated as a copy.

DebuggingDevOps and cloudGame developmentshowcase
Related

Other instructions, from other repositories

Unity-TheWorldBeyond copilot-instructions.md

Instructions for oculus-samples/Unity-TheWorldBeyond: This is a Meta Quest / Horizon OS sample.

oculus-samples/Unity-TheWorldBeyond · 111 tokens

Unity-TheWorldBeyond GEMINI.md

Instructions for oculus-samples/Unity-TheWorldBeyond, a project described as: Presence Platform showcase demonstrating usage of Scene, Passthrough, Interaction, Voice, and Spatializer. The Oculus SDK and other supporting material is subject to the Oculus proprietary license. Multiple licenses may apply.

oculus-samples/Unity-TheWorldBeyond · 79 tokens

Unity-TheWorldBeyond AGENTS.md

Instructions for oculus-samples/Unity-TheWorldBeyond, covering agent instructions — the world beyond, quest / horizon-specific notes and meta quest tooling.

oculus-samples/Unity-TheWorldBeyond · 745 tokens

Unity-TheWorldBeyond meta-quest.instructions.md

Instructions for oculus-samples/Unity-TheWorldBeyond: For this repository, prefer Meta Quest Agentic Tools, the Meta Horizon VS Code/Cursor extension, and the hzdb MCP server.

oculus-samples/Unity-TheWorldBeyond · 62 tokens

Claw3D AGENTS.md

Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.

iamlukethedev/Claw3D · 608 tokens

GameDesignOS AGENTS.md

Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.

DY-2026/GameDesignOS · 972 tokens