mps

A guide to Machine Perception Services, a cloud service that processes Aria glasses recordings into spatial and hand-related data.

In plain words
What is it for?
Use it to process one or multiple recording sequences and obtain SLAM trajectories, semi-dense point clouds, hand tracking, and online calibration results.
Why use it?
It explains how to submit VRS recordings, retrieve processed results, and work with their formats and lifecycle.

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

Made for: Claude Code, Codex.

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,618 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 $0.00107 $0.01618
Opus 5 $0.00053 $0.00809
Sonnet 5 $0.00021 $0.00324
Haiku 4.5 $0.00011 $0.00162

Measured 2d ago against content hash 618ccca39c1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mps 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/mps/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Machine Perception Services (MPS)

MPS is a cloud-based post-processing service for Aria recordings. You submit VRS files via the aria_mps CLI, MPS runs proprietary Spatial AI algorithms, and you download the derived outputs (trajectories, point clouds, hand tracking). The data is only used to serve requests — not accessible to Meta researchers.

How to Use This Skill

This skill teaches concepts and capabilities. For details, use the authoritative sources:

Installation

  • Install: pip install projectaria-mps (automatically includes projectaria-tools and projectaria-vrs-health-check)
  • CLI command: aria_mps
  • Auth: On first run, authenticate with your Project Aria account. Tokens are cached in the system keychain for subsequent runs.
  • Configuration: $HOME/.projectaria/mps.ini — concurrency, chunk sizes, retry logic.
  • Docs: https://facebookresearch.github.io/projectaria_tools/gen2/ark/mps/start

Capabilities Overview

Services

MPS provides three services. Services are independent — you can request any combination. VRS health check runs automatically before processing.

  • SLAM: 6DoF trajectory (open-loop VIO + closed-loop bundle-adjusted, both at 1kHz), semi-dense point cloud, time-varying sensor calibration. Requires CV cameras + IMU.
  • Multi-SLAM: Processes multiple recordings of the same physical space together to produce outputs in a shared coordinate frame. Use when you need spatially aligned trajectories and point clouds across devices.
  • Hand Tracking: 21 hand landmark positions, 6DoF hand-to-device transform, wrist and palm normals, per-frame confidence. Requires CV cameras ≥10fps + IMU.

Read the full file on GitHub · 97 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 · 97 lines · 107 tokens per session scan A 618ccca39c1f

Subscribe to this mod's changes

mps is a skill published in the GitHub repository facebookresearch/projectaria-plugins (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,618 once invoked, about $0.0005 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

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

overleaf-sync

Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens

mixed-precision

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

aiming-lab/AutoResearchClaw · 25 tokens