cosmos3-nim-user

cosmos3-nim-user is a skill for Claude Code, Codex from NVIDIA/cosmos. It costs 59 tokens per session (2,821 once invoked), scanned C, original, no licence file.

A guide for deploying and using Cosmos3 Certified NIM, an NVIDIA service for running an AI model through an endpoint. It covers endpoint checks, examples, compatible hardware, and troubleshooting.

In plain words
What is it for?
Use it for Cosmos3 NIM deployment, API calls, hardware checks, and related troubleshooting.
Why use it?
It helps users operate the service without guessing how to deploy it, call it, or diagnose problems.

Skill for Claude CodeCodex ✓ vendor

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it for Cosmos3 NIM deployment, API calls, hardware checks, and related troubleshooting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nvidia/cosmos/cosmos3-nim-user
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.

Any agent
npx skills add NVIDIA/cosmos --skill cosmos3-nim-user
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/cosmos

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 cosmos3-nim-user

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia/cosmos/cosmos3-nim-user/github.svg)](https://agentmods.dev/skills/nvidia/cosmos/cosmos3-nim-user)
Your own site
<a href="https://agentmods.dev/skills/nvidia/cosmos/cosmos3-nim-user"><img src="https://agentmods.dev/badge/skills/nvidia/cosmos/cosmos3-nim-user/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.

agentmods 80×15 button for cosmos3-nim-user

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia/cosmos/cosmos3-nim-user"><img src="https://agentmods.dev/badge/skills/nvidia/cosmos/cosmos3-nim-user.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,821 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00059 $0.02821
Opus 5 $0.00030 $0.01411
Sonnet 5 $0.00012 $0.00564
Haiku 4.5 $0.00006 $0.00282

Measured 3d ago against content hash abfc015f149e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

cosmos3-nim-user scanned grade C 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 3d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsS "$NIM_URL/v1/metadata" | python3 -m json.tool

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsS "$NIM_URL/v1/health/ready"
cookbooks/cosmos3/nim/.agents/skills/cosmos3-nim-user/SKILL.md · 233 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 3d ago First seen · 233 lines · 59 tokens per session scan C abfc015f149e

Subscribe to this mod's changes

cosmos3-nim-user is a skill published in the GitHub repository NVIDIA/cosmos (11,767 stars, last pushed 4d ago), with no licence file. It adds 59 tokens to every session and 2,821 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

amc-run-rtsp-calibration

Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

NVIDIA/skills · 59 tokens

amc-run-video-calibration

Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.

NVIDIA/skills · 57 tokens