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.
npx skills add NVIDIA-TAO/tao-skill-bank --skill tao-finetune-cosmos-embedgit clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bankWrote 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.
[](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-finetune-cosmos-embed)<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.
<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>- NVIDIA SkillSpector warn
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
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 | $0.00079 | $0.03663 |
| Opus 5 | $0.00039 | $0.01832 |
| Sonnet 5 | $0.00016 | $0.00733 |
| Haiku 4.5 | $0.00008 | $0.00366 |
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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 303 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-setupskill 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.
Train Action Policy
AutoML is not packaged for this model skill because there are no Cosmos-Embed schemas under schemas/. Always use the direct model skill actions for train, evaluate, inference, and export, even when a higher-level request includes automl_policy: on. Do not route Cosmos-Embed through workflow or AutoML skills until model-specific train schemas and templates are added.
Non-train actions such as evaluate, inference, export, and deploy flows stay in this model skill. The per-run automl_policy override does not change model metadata.
Quick Start
Use the published Cosmos-Embed container pinned below (also declared in
references/skill_info.yaml). Do not build from the private
Cosmos-Embed1 source tree for normal skill use; build from source only when
developing the container itself.
COSMOS_EMBED_IMAGE_DEFAULT=nvcr.io/nvidia/tao/tao-toolkit:7.1.0-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
│ ├── evaluate.yaml
│ ├── inference.yaml
│ ├── export_onnx.yaml
│ └── export_hf.yaml
└── results/
What ships with it
10 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.
- BENCHMARK.md 3.9 KB
- evals/evals.json 804 B
- references/skill_info.yaml 2.8 KB
- references/spec_template_evaluate.yaml 1.1 KB
- references/spec_template_export_hf.yaml 755 B
- references/spec_template_export_onnx.yaml 827 B
- references/spec_template_inference.yaml 1.1 KB
- references/spec_template_train.yaml 2.2 KB
- skill-card.md 4.0 KB
- skill.oms.sig 6.0 KB
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.
- 12d ago First seen · 303 lines · 79 tokens per session scan A 46ec7fc320eb
tao-finetune-cosmos-embed is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 3,663 once invoked, about $0.0004 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.
Other skills, from other repositories
kilocode-multimodal
Verify tool execution using text, audio, and VLM checks across PMOVES services on the KiloCode GLM lane. Use when validating multimodal outputs, capturing verification evidence, or binding verification to task/run IDs.
minimax-multimodal
Verify tool execution using text, audio, and VLM checks across PMOVES services. This skill should be used when validating multimodal outputs, capturing verification evidence, or binding verification to task/run IDs.
blip-2-vision-language
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
nemotron-retrieval-recipes
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.