What is tao-finetune-cosmos-embed?

A model guide for Cosmos-Embed1, which converts video and text into comparable numerical representations called embeddings. These representations help match, classify, compare, and remove duplicate videos by meaning.

Use it to find videos from text descriptions, search with another video, classify videos without task-specific training, detect semantic duplicates, fine-tune the model, or export it.

It provides the model-specific actions and rules needed for training, evaluation, inference, and export without routing the work through unsupported automation paths.

tao-finetune-cosmos-embed — Skill for Claude Code by NVIDIA-TAO

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-TAO/tao-skill-bank --skill tao-finetune-cosmos-embed

Clone the repo

git clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bank

Made for: Claude Code.

Or install tao-skills, the plugin that ships this one along with the rest of its 82 skills.

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/nvidia-tao/tao-skill-bank/tao-finetune-cosmos-embed/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-finetune-cosmos-embed)

Your own site

<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-finetune-cosmos-embed"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-finetune-cosmos-embed/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/nvidia-tao/tao-skill-bank/tao-finetune-cosmos-embed"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-finetune-cosmos-embed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,633 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 7 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 79
Potential security issue detected. Manual review is recommended.

Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
medium MCP Rug Pull · line 48
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123
medium MCP Rug Pull · line 107
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123
medium MCP Rug Pull · line 114
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123
medium MCP Rug Pull · line 121
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123
medium MCP Rug Pull · line 131
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123
medium MCP Rug Pull · line 141
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123

How audits are shown

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	$0.00126	$0.04633
Opus 5.5	$0.00050	$0.01853
Sonnet 5.5	$0.00025	$0.00927
Haiku 4.5	$0.00013	$0.00463

Measured 4d ago against content hash 70a69e1509b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tao-finetune-cosmos-embed 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 4d 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.

skills/models/tao-finetune-cosmos-embed/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cosmos-Embed

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

Cosmos-Embed1 is a joint video-text embedder for text-to-video retrieval, video-to-video search, zero-shot/kNN classification, and semantic deduplication. The packaged CLI is cosmos-embed1 and supports train, evaluate, inference, and export.

Container image and per-action commands are in references/skill_info.yaml. Compact starting specs are in references/spec_template_*.yaml; the LoRA fine-tuning recipe on chunk manifests is in references/lora-finetune-physicalai.md with references/spec_template_train_lora.yaml.

Release note: the pinned 7.3.0-cosmos-embed image is the first that trains ViT LoRA adapters, accepts caption_mode, label_mode, and train.grad_accum_iter, scores the in-training retrieval_benchmark, and validates large ONNX exports by file path. On 7.1.0-cosmos-embed the ViT adapters silently stay at zero and the vision ONNX export exits 1 after writing valid files.

Train Action Policy

AutoML is not packaged for this model skill (no Cosmos-Embed schemas under schemas/). Use the direct train, evaluate, inference, and export actions even when a higher-level request includes automl_policy: on; the per-run override does not change model metadata, and non-train and deploy flows stay in this skill.

Quick Start

Use the published container pinned below (also declared in references/skill_info.yaml); do not build from the Cosmos-Embed1 source tree for normal skill use.

COSMOS_EMBED_IMAGE_DEFAULT=nvcr.io/nvidia/tao/tao-toolkit:7.3.0-cosmos-embed  # versions-key: images.tao_toolkit.cosmos_embed
COSMOS_EMBED_IMAGE="${COSMOS_EMBED_IMAGE:-$COSMOS_EMBED_IMAGE_DEFAULT}"
docker pull "$COSMOS_EMBED_IMAGE"

Expected local workspace layout:

workspace/
├── data/
│   ├── msrvtt_test_1k.json
│   └── video/
│       ├── video7020.mp4
│       └── ...
├── model/
│   └── Cosmos-Embed1-224p/        # optional if using HF repo id
├── specs/
│   ├── train.yaml                 # or train_lora.yaml from references/
│   ├── evaluate.yaml
│   ├── inference.yaml
│   ├── export_onnx.yaml
│   └── export_hf.yaml
└── results/

Read the full file on GitHub · 276 lines

Files

What ships with it

14 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.

4d ago Changed · -47 lines · +47 tokens per session 70a69e1509b5
12d ago Changed eadfc7db2b48
14d ago Changed · +20 lines 3c95b2f117d2
1mo ago First seen · 303 lines · 79 tokens per session scan A 46ec7fc320eb

Subscribe to this mod's changes

tao-finetune-cosmos-embed is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (97 stars, last pushed 5d ago), licensed Apache-2.0. It adds 126 tokens to every session and 4,633 once invoked, about $0.0005 per session on Opus 5.5. 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.

Data and AI LoRA Multimodal cosmos embedding fine-tuning retrieval video vision-language vlm

tao-finetune-cosmos-embed

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Cosmos-Embed

Train Action Policy

Quick Start

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

llama-factory

llama-factory

kilocode-multimodal

minimax-multimodal

llama-factory

llama-factory