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 skills add facebookresearch/projectaria-plugins --skill cloud-streaminggit clone --depth 1 https://github.com/facebookresearch/projectaria-pluginsWrote 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/skills/facebookresearch/projectaria-plugins/cloud-streaming)<a href="https://agentmods.dev/skills/facebookresearch/projectaria-plugins/cloud-streaming"><img src="https://agentmods.dev/badge/skills/facebookresearch/projectaria-plugins/cloud-streaming/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.
<a href="https://agentmods.dev/skills/facebookresearch/projectaria-plugins/cloud-streaming"><img src="https://agentmods.dev/badge/skills/facebookresearch/projectaria-plugins/cloud-streaming.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00083 | $0.01530 |
| Opus 5.5 | $0.00033 | $0.00612 |
| Sonnet 5.5 | $0.00017 | $0.00306 |
| Haiku 4.5 | $0.00008 | $0.00153 |
Grade B, and why
cloud-streaming scanned grade B with 2 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Copy `subscriber.pem` and `subscriber-key.pem` to a secure path on the cloud server (e.g. `/etc/aria-certs/`, with `chmod 600`). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| No data reaches server | Glasses not on internet WiFi, server unreachable, or wrong URL | Verify WiFi connection from the Companion App or `aria_gen2 device wifi …`; test the URL from another machine with `curl -k http How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aria Cloud Streaming
Remote (cloud) streaming sends Aria Gen 2 data straight to your internet-reachable HTTPS server, bypassing the default local USB / same-network WiFi streaming. The glasses POST data over HTTPS to whatever URL you supply.
Reference: https://facebookresearch.github.io/projectaria_tools/gen2/ark/client-sdk/remote-streaming For local USB / same-network streaming: use the
client-sdkskill.
When to use
- Field deployments — collect data without carrying a laptop.
- Centralized collection — many devices → one cloud server.
- Cloud processing — feed real-time pipelines (decoders, indexers, alerters) in the cloud.
- Remote monitoring — observe device streams from anywhere.
If your collection point is on the same WiFi as the glasses, plain local streaming via the Client SDK is simpler — use that.
Architecture
Aria Glasses ──(WiFi → internet)──► Your HTTPS Server :6768
HTTPS POST (decode / store / forward)
The glasses open an HTTPS connection to a URL you provide and POST sensor data chunks. The server uses Aria's streaming TLS certificates so the connection is mutually trusted.
Setup (one-time per server)
1. Prerequisites
- Client SDK installed and device authenticated (
aria_gen2 auth pair) — see theclient-sdkskill. - Glasses on a WiFi network with internet access.
- A server reachable from the public internet on port 6768.
2. Copy streaming certificates to the server
The certificates were generated when the SDK was first set up. They live on the PC where the SDK was installed at:
~/.aria/streaming-certs/persistent/
├── subscriber.pem # server cert (PEM)
├── subscriber-key.pem # server private key
└── root_ca.pem
Copy subscriber.pem and subscriber-key.pem to a secure path on the cloud server (e.g. /etc/aria-certs/, with chmod 600).
3. Open inbound port 6768
Open TCP port 6768 in the server's firewall and any cloud-provider security group. Restrict the source to known IP ranges if you can; otherwise allow 0.0.0.0/0.
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.
- 1mo ago First seen · 135 lines · 83 tokens per session scan B 1f8bb5f190bb
cloud-streaming is a skill published in the GitHub repository facebookresearch/projectaria-plugins (14 stars, last pushed 6d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,530 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ruview-cli-api
Use the RuView wifi-densepose CLI binary (incl. MAT scan/status/zones/survivors/alerts/export subcommands), the REST API (wifi-densepose-api, Axum), and the browser/WASM build (wifi-densepose-wasm, wifi-densepose-wasm-edge). Use when integrating RuView into another program, scripting it from the shell, exposing it…
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
jetson-customize-pcie
Per-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lane allocation or endpoint-mode bring-up.
deepep-to-cam-converter
A code migration skill for replacing DeepEP communication operations with CAM operations when moving mixture-of-experts code from CUDA/NCCL to Ascend NPUs.
telnyx-iot-curl
Manage IoT SIM cards, eSIMs, data plans, and wireless connectivity. Use when building IoT/M2M solutions. This skill provides REST API (curl) examples.