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/meta-quest/horizon-platform-sdk-samples/agents-mdgit clone --depth 1 https://github.com/meta-quest/horizon-platform-sdk-samplesWrote 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/meta-quest/horizon-platform-sdk-samples/agents-md)<a href="https://agentmods.dev/instructions/meta-quest/horizon-platform-sdk-samples/agents-md"><img src="https://agentmods.dev/badge/instructions/meta-quest/horizon-platform-sdk-samples/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 | $0.00727 | $0.00727 |
| Opus 5 | $0.00364 | $0.00364 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
horizon-platform-sdk-samples 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 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — VR Platform SDK Android Sample Apps
Collection of standalone Android sample apps, one per public VR Platform SDK API, showing how to integrate a single Platform SDK feature on Meta Quest devices running Horizon OS.
Source-of-truth files (read these first, do not duplicate their contents in this file)
For setup, build steps, SDK versions, and project layout, read:
README.md— official setup and instructions<sample>/build.gradle.kts+<sample>/gradle/libs.versions.toml— Android Gradle / SDK versions for each sample<sample>/app/src/main/AndroidManifest.xml— package id, permissions, target APILICENSE— license terms
Quest / Horizon-specific notes
- Each top-level directory (
abusereport/,achievements/,users/, etc.) is its own independent Gradle root with its own version catalog — treat them as separate projects rather than a multi-module build. - Every sample requires a real Application ID from the Meta Quest developer dashboard; the placeholder
APPLICATION_IDconstant inMainActivity.ktmust be replaced before the Platform SDK calls will work end-to-end. - The PSDK artifacts use the
-kotlinsuffix (e.g.core-kotlin,users-kotlin) — do not silently swap to Java variants. - Each sample ships a shared dev signing key at
app/testapps.keystore; preserve it when refactoring build files.
Meta Quest tooling
This is a Meta Quest / Horizon OS sample. The bespoke intro above is the source of truth for what this project is and how it's built — use it (and the files it points at) instead of restating facts from memory.
When the user asks anything about Quest device behavior, build / deploy / debug / capture flows, on-device performance, or Horizon OS APIs, reach for these tools instead of generic Android answers:
hzdb— Quest-aware ADB wrapper (device list, install / launch / stop, logs, screenshots, Perfetto traces, on-device docs search). Already wired up as an MCP server via.mcp.json,.vscode/mcp.json, and.cursor/mcp.json. Also runnable directly:npx -y @meta-quest/hzdb <subcommand>.- Meta Quest Agentic Tools — the full skill set, including Android-specific skills: https://github.com/meta-quest/agentic-tools. Install per your client (Claude Code:
/plugin install meta-vr@meta-quest; Gemini CLI:gemini extensions install https://github.com/meta-quest/agentic-tools; Cursor / VS Code: install the Meta Horizon extension from the Marketplace).
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 · 36 lines · 727 tokens per session scan A 8a52dde9f4ba
horizon-platform-sdk-samples AGENTS.md is an instructions file published in the GitHub repository meta-quest/horizon-platform-sdk-samples (2 stars, last pushed 1mo ago), licensed MIT. It adds 727 tokens to every session, about $0.0036 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
Meta-Spatial-SDK-Samples GEMINI.md
Gemini CLI instructions for meta-quest/Meta-Spatial-SDK-Samples, a project described as: The Meta Spatial SDK Samples is a collection of code samples and projects that demonstrate the capabilities of the Meta Spatial SDK. Meta Spatial SDK enables mobile developers to build Meta Horizon OS experiences using familiar…
Meta-Spatial-SDK-Samples AGENTS.md
AGENTS.md instructions for meta-quest/Meta-Spatial-SDK-Samples, covering meta spatial sdk — samples and docs.
Meta-Spatial-SDK-Samples meta-quest.instructions.md
Instructions for meta-quest/Meta-Spatial-SDK-Samples: For this repository, prefer Meta Quest Agentic Tools, the Meta Horizon VS Code/Cursor extension, and the hzdb MCP server.
Meta-Spatial-SDK-Samples copilot-instructions.md
Copilot instructions for meta-quest/Meta-Spatial-SDK-Samples: This is a Meta Quest / Horizon OS sample.
Unity-CompositorLayers meta-quest.instructions.md
Instructions for oculus-samples/Unity-CompositorLayers: For this repository, prefer Meta Quest Agentic Tools, the Meta Horizon VS Code/Cursor extension, and the hzdb MCP server.
MobiAI-Core CLAUDE.md
Claude Code instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.