What is brilliant_sdk AGENTS.md?

A development guide for building apps with Brilliant Labs smart glasses such as Halo and Frame. It explains how a computer program and a Lua program running on the glasses communicate through the Brilliant SDK.

Use it to connect to the glasses, upload and start device apps, exchange messages, handle device responses, and verify app behavior without physical hardware where supported by the guide.

It helps an agent understand the project's two-part design and find the right files without reading the entire large codebase.

How brilliantlabsAR/brilliant_sdk configures Codex and OpenCode

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/AGENTS.md

Clone the repo

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

Made for: Codex, OpenCode.

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/brilliantlabsar/brilliant_sdk/agents-md/github.svg)](https://agentmods.dev/instructions/brilliantlabsar/brilliant_sdk/agents-md)

Your own site

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

Per session 1,779 This file is loaded in full into every session.

When invoked 1,779 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	$0.01779	$0.01779
Opus 5.5	$0.00712	$0.00712
Sonnet 5.5	$0.00356	$0.00356
Haiku 4.5	$0.00178	$0.00178

Measured 14d ago against content hash 2fe03c06ce69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brilliant_sdk 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 14d 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.

AGENTS.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brilliant SDK — agent guide

Host-side SDK for Brilliant Labs smart glasses (Halo and Frame) in three parallel implementations: python/ (PyPI: brilliant-ble / brilliant-msg / brilliant-sdk), flutter/ (pub.dev: brilliant_ble / brilliant_msg / brilliant_sdk / simple_brilliant_app) and webbluetooth/ (npm: brilliant-ble / brilliant-msg / brilliant-sdk). The glasses run user apps in an on-device Lua 5.4 VM exposing a frame.* API; the SDK provides the BLE transport (*_ble), the message protocol (*_msg), and meta-packages (*_sdk). Start with README.md for the architecture diagram.

The whole tree is ~55k lines — do not read broadly. Use the reading paths and indexes below.

How an app works (the pattern behind everything)

Every non-trivial app is two programs: a host program (Python/Dart/TS) and a device-side Lua app, coupled by single-byte message codes that must match on both sides. The canonical lifecycle, identical in all three SDKs (camelCase in Dart/TS):

connect() → upload_stdlua_libs([...]) → upload_frame_app(...) →
start_frame_app() → send_message(code, packed) / attach rx handlers → stop

Host side packs typed messages (TxSprite, TxPlainText, RxPhoto, …).
Device side: each message type has a paired Lua library in the *_msg package (data.lua + one per type) that reassembles and renders.
Examples follow the naming convention <name>.py + lua/<name>_frame_app.lua.

For quick one-off device control you can skip all of this and send raw Lua strings to the REPL with *_ble alone (see python/packages/brilliant_ble/examples/hello_world.py).

Minimal reading paths

"Show text on the glasses" (Python): README.md → python/packages/brilliant_msg/README.md (annotated sprite example = the canonical lifecycle) → python/packages/brilliant_msg/examples/plain_text.py

examples/lua/plain_text_frame_app.lua. That's ~300 lines total; the same path exists in each SDK.

Per-area entry points:

Read the full file on GitHub · 132 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.

14d ago Changed · -2 lines · -38 tokens per session 2fe03c06ce69
2mo ago First seen · 134 lines · 1,817 tokens per session scan A 2e5acc1b1e40

Subscribe to this mod's changes

brilliant_sdk AGENTS.md is an instructions file published in the GitHub repository brilliantlabsAR/brilliant_sdk (127 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 1,779 tokens to every session, about $0.0071 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.

Hardware and IoT

brilliant_sdk AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
brilliant_sdk AGENTS.mdbrilliantlabsAR/brilliant_sdk	Instructions file	127	2d ago	BSD-3-Clause	A	1,779	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

brilliant_sdk: Instructions file for Codex