What is cosmos3-env-troubleshoot?

A troubleshooting guide for setting up and running NVIDIA Cosmos3, a framework for AI models that generate or understand video, on a local or hosted machine.

Use it when Cosmos3 cannot install, download files, access Hugging Face or NGC, use a GPU, start its container, or run inference.

It helps diagnose setup failures involving Python packages, CUDA, Docker, source downloads, credentials, checkpoints, and inference errors without exposing access tokens.

cosmos3-env-troubleshoot — Skill for Claude Code and Codex by nebius

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 nebius/nebius-physical-ai --skill cosmos3-env-troubleshoot

Clone the repo

git clone --depth 1 https://github.com/nebius/nebius-physical-ai

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/cosmos3-env-troubleshoot/github.svg)](https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-env-troubleshoot)

Your own site

<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-env-troubleshoot"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/cosmos3-env-troubleshoot/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-env-troubleshoot"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/cosmos3-env-troubleshoot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,418 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.01418
Opus 5	$0.00024	$0.00709
Sonnet 5	$0.00010	$0.00284
Haiku 4.5	$0.00005	$0.00142

Measured 5d ago against content hash a9b46926a46b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade D, and why

cosmos3-env-troubleshoot scanned grade D with 3 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| Docker `runtime name: nvidia` error | Docker NVIDIA runtime not configured | Run `sudo nvidia-ctk runtime configure --runtime=docker` on the host |

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 -LsSf https://astral.sh/uv/install.sh | sh

Makes network callslowCapability

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

curl -LsSf https://astral.sh/uv/install.sh | sh

skills/atomic/cosmos3-env-troubleshoot/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cosmos3 Environment Troubleshooting

Source And Attribution

Adapted from NVIDIA cosmos-framework skills/atomic/cosmos3-env-troubleshoot/SKILL.md.

When To Use

Use this skill for import errors, missing Python packages, CUDA or torch failures, Docker GPU runtime problems, failed source clones, Hugging Face 401s, NGC credential errors, and inference runtime tracebacks. For "where is this file or config" questions, use skills/atomic/cosmos3-codebase-nav/SKILL.md.

First Rule

Never print or commit secrets. Token-bearing values include GITHUB_TOKEN, HF_TOKEN, HUGGING_FACE_HUB_TOKEN, NGC_API_KEY, AWS keys, and any env var selected through NPA_COSMOS3_*_TOKEN_ENV.

NPA Diagnostic Ladder

Confirm the NPA command surface:
```
npa/.venv/bin/npa workbench cosmos --help
```
check and fetch should be present. skill and skills should not be present.
Run a redacted access check:
```
npa/.venv/bin/npa workbench cosmos check --output json
```
Interpret statuses, not secrets. Expected status labels are configured, missing, reachable, failed, or skipped.

For source-only failure isolation:

npa/.venv/bin/npa workbench cosmos fetch --skip-checkpoint --output json

For inference workflow issues, inspect:

npa/.venv/bin/python - <<'PY'
import yaml
from pathlib import Path
p = Path("workflows/testing/cosmos3-text-to-image.yaml")
doc = yaml.safe_load(p.read_text())
print(doc["metadata"]["name"])
print(doc["states"][doc["initial"]]["toolRef"])
PY

If a SkyPilot run fails on the GPU node, collect logs and env status without dumping token values:

printenv | rg '^(NPA_COSMOS3|COSMOS3|HF_HOME|LD_LIBRARY_PATH)='
python --version
which python
nvidia-smi
python -c "import torch; print(torch.__version__, torch.version.cuda)"

Read the full file on GitHub · 138 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.

5d ago Changed · +16 lines a9b46926a46b
13d ago First seen · 122 lines · 49 tokens per session scan D 9902e2b47709

Subscribe to this mod's changes

cosmos3-env-troubleshoot is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,418 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI DevOps and cloud

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

cosmos3-env-troubleshoot