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 custom-profilegit 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/custom-profile)<a href="https://agentmods.dev/skills/facebookresearch/projectaria-plugins/custom-profile"><img src="https://agentmods.dev/badge/skills/facebookresearch/projectaria-plugins/custom-profile/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/custom-profile"><img src="https://agentmods.dev/badge/skills/facebookresearch/projectaria-plugins/custom-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00134 | $0.04621 |
| Opus 5.5 | $0.00054 | $0.01848 |
| Sonnet 5.5 | $0.00027 | $0.00924 |
| Haiku 4.5 | $0.00013 | $0.00462 |
Grade A, and why
custom-profile 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 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.
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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom Profile Authoring
A profile is JSON that fixes which Aria Gen 2 sensors run, at what rate, resolution, and encoding. One profile serves both recording and streaming; the "recording profile" name is historical.
Default to a pre-defined profile. Write a custom one only when none fits.
Don't write a custom profile when
- The user is new to Aria.
- The data goes to MPS — custom profiles risk incompatibility.
- The data must be shareable or comparable across studies.
- A pre-defined profile hasn't been tried yet.
1. Start from a device profile
Sources on device: native (firmware), cloud (server-pushed), user (yours — the only writable one).
Pull a base off the device and edit it. Never transcribe one from docs, and never start blank. A pull returns what the firmware actually runs.
Client SDK does list / pull / add / remove. Commands are in the client-sdk skill — don't guess them.
add is non-destructive, takes one profile, and won't overwrite. To iterate: remove, then add.
| Profile | Use for | Notable |
|---|---|---|
profile8 |
General-purpose recording | RGB 10 Hz @ 2560×1920, SLAM 30 Hz, all environmental sensors on |
profile9 |
General-purpose streaming | RGB 5 Hz CBR (8 Mbps + blur filter), no GPS / BLE / WiFi / ET cameras |
profile10 |
High-frame-rate RGB | RGB 30 Hz @ 2016×1512, otherwise like profile8 |
mp_streaming_demo |
Machine-perception streaming demo | Streaming-only, lighter encoding, no ALS / baro / mag / GPS / BLE / WiFi |
Catalog: https://facebookresearch.github.io/projectaria_tools/gen2/technical-specs/device/profile
2. Hard rules — breaking these stops the session
| Rule | Failure |
|---|---|
| Every field name spelled exactly; no unknown fields | Upload rejected |
name non-empty and unique across all three sources |
Upload rejected |
imus / magnetometer / barometer / gps rate on the allow-list |
Rejected |
Camera rate_hz ≤ 90 |
Rejected |
RGB rate_hz within the ceiling for its resolution (24 at 4032×3024, else 30) |
Rejected |
cqp.qp in 0–51 |
Stream won't start |
fixed_exposure.gain positive and inside the camera's range |
Rejected |
encoding: YUV only on rgb_camera |
Rejected |
Valid enum values everywhere, including wifi.scan_mode |
Rejected |
rgb_camera.resolution recognised |
Dataflow service aborts |
ALS exposure_time_us + 6000 ≤ sample period |
Rejected |
ALS exposure_mode: FIXED requires exposure_time_us |
Rejected |
Never enable ML ET and ht together |
Session won't start |
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.
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 Changed · -77 lines · -10 tokens per session 648272495498
- 1mo ago First seen · 397 lines · 144 tokens per session scan A 92856473f824
custom-profile is a skill published in the GitHub repository facebookresearch/projectaria-plugins (14 stars, last pushed 6d ago), licensed Apache-2.0. It adds 134 tokens to every session and 4,621 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
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…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.