ncore

ncore is a skill for Claude Code, Codex from NVIDIA/nurec-skills. It costs 273 tokens per session (14,942 once invoked), scanned A, original, Apache-2.0.

A guide for converting recordings from cameras, LiDAR, radar, motion sensors, depth sensors, stereo cameras, or other sources into NVIDIA NCore V4 data stores. These stores can be read by NVIDIA tools such as NuRec and Asset Harvester.

In plain words
What is it for?
Use it to convert datasets such as Waymo, PandaSet, NuScenes, PAI, COLMAP, ScanNet++, or ROS 2 bags, or to create a converter for an unsupported format.
Why use it?
It removes the need to manually reshape different sensor-data formats into the structure those NVIDIA tools accept. It also helps diagnose conversion and data-quality validation failures.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

NVIDIA NuRec Skills is a set of agent instructions for running neural reconstruction and rendering workflows in NVIDIA Omniverse NuRec. It targets autonomous-vehicle and robotics simulation, guiding agents across the public containers, repositories, and artifacts that make up the NuRec stack.

NVIDIA/nurec-skills · 35 stars · on GitHub

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/nvidia/nurec-skills/ncore
Any agent
npx skills add NVIDIA/nurec-skills --skill ncore
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/nurec-skills

Made for: Claude Code, Codex.

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.

agentmods badge for ncore

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia/nurec-skills/ncore.svg)](https://agentmods.dev/skills/nvidia/nurec-skills/ncore)
Your own site
<a href="https://agentmods.dev/skills/nvidia/nurec-skills/ncore"><img src="https://agentmods.dev/badge/skills/nvidia/nurec-skills/ncore.svg" alt="Measured on agentmods" height="20"></a>
Per session 273 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 14,942 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 5.1 $0.00273 $0.14942
Opus 5 $0.00137 $0.07471
Sonnet 5 $0.00055 $0.02988
Haiku 4.5 $0.00027 $0.01494

Measured 6d ago against content hash 78f7fc493a18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ncore 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 6d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (ncore_template/__init__.py, ncore_template/impl/__init__.py, ncore_template/impl/data_converter/__init__.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/ncore/SKILL.md · 1,059 lines

How it starts

The opening of the file, as written. The whole thing — 1,059 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NCore V4 Data Conversion

Purpose

Convert any sensor recording (cameras, LiDAR, radar, IMU, depth, stereo, COLMAP/SfM, ROS 2 bag) into a valid NVIDIA NCore V4 store so it can be consumed by NuRec / Asset Harvester / ncore_vis, or wired into a robotics-to-sim ("r2s") pipeline. Drive the existing in-tree converters (PAI, Waymo, COLMAP/ScanNet++) or author a new converter from ncore_template/.

Use this skill when: the user has raw sensor data (any rig) that NuRec or Asset Harvester needs to ingest, or when an existing converter is failing validate.py / producing NuRec data-quality complaints.

Do NOT use this skill when:

  • The user is already on V4 and only wants to train or render (use the nre skill).
  • The user wants per-object 3D assets from sparse views (use asset-harvester).
  • The user only needs to browse / pick an existing NVIDIA dataset (use physical-ai-datasets).

This skill teaches an agent to take any sensor dataset and produce a valid NCore V4 store that NuRec / Asset Harvester / ncore_vis will accept. It covers both driving the existing in-tree converters (PAI, Waymo, COLMAP/ScanNet++) and writing a new one for unsupported formats (PandaSet, NuScenes, KITTI, stereo, mono+depth, mono+lidar, custom robotics rigs).

Table of Contents

  1. When to use which path
  2. Install & references
  3. Mental model — the V4 store
  4. Path A — drive an existing in-tree converter
  5. Path B — author a new converter from the template
  6. V4 conventions you must obey
  7. Format recipes (AV)
  8. Format recipes (non-AV / sensor-only)
  9. Robotics pipeline shards (r2s)
  10. Validation & end-to-end NuRec
  11. Common failure modes (and the fix file)
  12. Additional resources

Read the full file on GitHub · 1,059 lines

Files

What ships with it

5 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.

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. 6d ago First seen · 1,059 lines · 273 tokens per session scan A 78f7fc493a18

Subscribe to this mod's changes

ncore is a skill published in the GitHub repository NVIDIA/nurec-skills (35 stars, last pushed 3d ago), licensed Apache-2.0. It adds 273 tokens to every session and 14,942 once invoked, about $0.0014 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 2026-08-30.

Related

Other skills, from other repositories

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

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…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

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…

NVIDIA/skills · 236 tokens

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…

SnailSploit/Claude-Red · 113 tokens

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…

NVIDIA/skills · 94 tokens