A guide for building apps for Brilliant Labs Halo or Frame smart glasses. Each app has a host program and a Lua program running on the glasses, communicating over Bluetooth.

Use it to build or debug glasses apps in Python, Flutter, or web TypeScript, including camera, audio, display, sensor, and interaction features.

It explains how to pair the two programs and choose the right SDK path for device access or a full glasses app.

How brilliantlabsAR/brilliant_sdk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to brilliantlabsAR/brilliant_sdk. 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/brilliantlabsAR/brilliant_sdk/main/.claude/skills/glasses-app/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/brilliantlabsAR/brilliant_sdk

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/skills/brilliantlabsar/brilliant_sdk/glasses-app/github.svg)](https://agentmods.dev/skills/brilliantlabsar/brilliant_sdk/glasses-app)

Your own site

<a href="https://agentmods.dev/skills/brilliantlabsar/brilliant_sdk/glasses-app"><img src="https://agentmods.dev/badge/skills/brilliantlabsar/brilliant_sdk/glasses-app/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/skills/brilliantlabsar/brilliant_sdk/glasses-app"><img src="https://agentmods.dev/badge/skills/brilliantlabsar/brilliant_sdk/glasses-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,270 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00063	$0.01270
Opus 5	$0.00032	$0.00635
Sonnet 5	$0.00013	$0.00254
Haiku 4.5	$0.00006	$0.00127

Measured 11d ago against content hash 71c55e0bad23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

glasses-app 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 11d 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/skills/glasses-app/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building a glasses app

Every app is two programs: a host program (Python / Dart / TypeScript) and a device-side Lua app running in the glasses' Lua 5.4 VM. They exchange messages over BLE, identified by a single-byte message code that must match on both sides. Get this pairing right and everything else is bookkeeping.

Choose the path

Just poking the device (show text, read battery, run a Lua snippet)? Use the *_ble layer alone and send raw Lua to the REPL — no Lua app needed. See python/packages/brilliant_ble/examples/hello_world.py.
A real app (camera, audio, sprites, IMU, interaction)? Use the *_msg layer and the lifecycle below.
Copy an existing example rather than starting blank — indexes: python/packages/brilliant_msg/examples/EXAMPLES.md, flutter/packages/simple_brilliant_app/example/EXAMPLES.md, webbluetooth/packages/brilliant-msg/example/EXAMPLES.md.

Per-SDK minimal working apps with file-by-file explanations:

On-device API: references/frame-api.md (condensed frame.* reference and Halo/Frame differences).

The canonical lifecycle (identical in all SDKs; camelCase in Dart/TS)

connect()
upload_stdlua_libs(['data', <per-message-type libs>])   # e.g. 'plain_text', 'camera'
upload_frame_app('lua/<name>_frame_app.lua')            # your device-side app
attach_print_response_handler()                         # see device print()/errors
start_frame_app()                                       # runs it; blocks until it prints ready
send_message(code, msg.pack()) / attach Rx receivers    # the app conversation
stop_frame_app(); disconnect()

The data Lua lib is always needed: it reassembles BLE-chunked messages into data.app_data[code] (or raw items) on the device. Each Tx*/Rx* message class has a same-named Lua lib that parses/renders it — upload the ones you use. While the frame app runs, the REPL is busy: no more raw send_lua() without a break signal.

Read the full file on GitHub · 102 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

11d ago First seen · 102 lines · 63 tokens per session scan A 71c55e0bad23

Subscribe to this mod's changes

glasses-app is a skill published in the GitHub repository brilliantlabsAR/brilliant_sdk (101 stars, last pushed 15d ago), licensed BSD-3-Clause. It adds 63 tokens to every session and 1,270 once invoked, about $0.0003 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 2026-08-30.

Hardware and IoT Mobile

developer-device-platform-basics

Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.

google/skills · 57 tokens

camerax

Provide technical guidance for Android camera development with CameraX. Use when implementing camera features, handling asynchronous recording lifecycles, wiring low-level hardware interop using CameraX, or integrating ML Kit or Media3 effects.

android/skills · 47 tokens

mobile-platform-native-capabilities-integrate

Build a Salesforce LWC that uses native mobile device capabilities — barcode scanner, biometrics, location, NFC, calendar, contacts, document scanner, geofencing, AR space capture, app review, and payments. Use this skill when the user asks for an LWC that scans a barcode, captures a photo of a document, reads…

forcedotcom/sf-skills · 174 tokens

brilliant_sdk: Skill for Claude Code