aria-knowledge

A knowledge guide to Project Aria Gen 2 and the Aria Research Kit, the hardware and software used to collect and process smart-glasses sensor data. It explains concepts such as calibration, coordinate systems, recordings, and outputs from perception systems.

In plain words
What is it for?
Learning how Aria sensors, data formats, time domains, localisation, point clouds, and hand tracking fit together before using the related development tools.
Why use it?
It gives developers the background needed to understand Aria data and points them to current documentation or source code when details may change.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/facebookresearch/projectaria-plugins/aria-knowledge
Any agent
npx skills add facebookresearch/projectaria-plugins --skill aria-knowledge
Clone the repo
git clone --depth 1 https://github.com/facebookresearch/projectaria-plugins

Made for: Claude Code, Codex.

Per session 234 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00234 $0.05184
Opus 5 $0.00117 $0.02592
Sonnet 5 $0.00047 $0.01037
Haiku 4.5 $0.00023 $0.00518

Measured 2d ago against content hash b1ebcabca63f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aria-knowledge 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 2d 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.

projectaria_ark_plugin/skills/aria-knowledge/SKILL.md · 420 lines

How it starts

The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aria Knowledge

This skill is the knowledge index for Project Aria Gen 2 and the Aria Research Kit (ARK). It encodes the high-level concepts that are stable across releases, and for specifics that drift (sensor specs, CSV column lists, exact API signatures, CLI flags) it tells you where the source-of-truth lives so you can fetch a current answer rather than guess.

How to use this skill

Question type                         → Action
─────────────────────────────────────────────────────────────────────────
What is X? / How does Y work?         → Answer from this skill
Specific numeric value / schema       → Read the public doc page this skill
                                        names (under `DOCS_BASE` below)
Exact API call / API signature        → Read the code (see corresponding
                                        skill for header locations)
Exact CLI flag                        → Run `<cmd> --help`
Hands-on workflow                     → Defer to the matching plugin skill
                                        (listed at the end of each section)

Source-of-truth rule. Anything that may change with a release — sample rates, profile JSON, stream IDs, calibration model parameters, MPS service versions, API names, CSV columns — lives in the docs or the source code. This skill repeats only the conceptual definitions that are unlikely to evolve.

Where to look (source-of-truth map)

Source URL
DOCS_BASE — Aria Gen 2 public docs https://facebookresearch.github.io/projectaria_tools/gen2
Open-source PAT library https://github.com/facebookresearch/projectaria_tools
VRS file-format library https://github.com/facebookresearch/vrs
Project Aria home https://www.projectaria.com/

Throughout this skill, paths like /technical-specs/device/als are relative to DOCS_BASE — prepend the base to construct a fetchable URL. The four top-level sections of the public docs site:

Section Covers
/ (root) Welcome / Gen 2 platform overview
/ark/... Aria Research Kit user docs (devices, recording, streaming, MPS, companion app, support)
/research-tools/... Open Science Initiative, projectaria-tools (PAT), open datasets, pre-trained models
/technical-specs/... Hardware specs, profiles, calibration, VRS format, MPS data formats, coordinate systems, client SDK reference

Read the full file on GitHub · 420 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.

  1. 2d ago First seen · 420 lines · 234 tokens per session scan A b1ebcabca63f

Subscribe to this mod's changes

aria-knowledge is a skill published in the GitHub repository facebookresearch/projectaria-plugins (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 234 tokens to every session and 5,184 once invoked, about $0.0012 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.

Related

Other skills, from other repositories

lab-hardware-cad

Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…

K-Dense-AI/scientific-agent-skills · 106 tokens

opentrons-integration

Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.

synthetic-sciences/openscience · 66 tokens

pylabrobot

Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…

synthetic-sciences/openscience · 73 tokens

add-instrument-driver

Scaffold a new instrument driver for a vendor/model from its programming reference (SCPI/programming manual/API SDK as a PDF, doc, HTML file, or website URL) and wire it into the repo per AGENTS.md conventions. Use when asked to "add a driver for ", "write a driver from this manual/datasheet", or similar. Produces the…

nominal-io/instro · 102 tokens

aedt-evidence-electromagnetics

Evidence-first Ansys Electronics Desktop and PyAEDT automation for Maxwell, HFSS, Q3D, Icepak, and related electromagnetic workflows. Use when Codex must check AEDT/PyAEDT, create or run a real AEDT design, verify the selected design and solution type, extract fields or matrices, export an .aedt project, or…

Cai-aa/CAE-Agent-Hub · 94 tokens

analyze-power-nets

Analyzes KiCad PCB files to identify power nets by looking up component datasheets via AI. Use when you need to determine which nets are power/ground nets and what track widths to use, especially when KiCad pintype annotations are missing or unreliable.

drandyhaas/KiCadRoutingTools · 57 tokens