tao-launch-workflow

tao-launch-workflow is a skill for Claude Code from NVIDIA-TAO/tao-skill-bank. It costs 131 tokens per session (4,024 once invoked), scanned A, original, Apache-2.0.

A mandatory pre-launch checklist and execution contract for TAO workflows, including model training, evaluation, inference, export, TensorRT engine creation, and DEFT applications. TAO is NVIDIA's toolkit for training and deploying AI models.

In plain words
What is it for?
Use it before launching any TAO model or data action to select the execution platform, confirm access and images, and follow the required workflow commands.
Why use it?
It checks the platform, credentials, container image, and other requirements before an action that could change files or start a workload.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Part of the tao-skill-bank plugin — 85 skills, 1 hook shipped together

Good fit Use it before launching any TAO model or data action to select the execution platform, confirm access and images, and follow the required workflow commands.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nvidia-tao/tao-skill-bank/tao-launch-workflow
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-launch-workflow
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bank

Made for: Claude Code.

Or install tao-skill-bank, the plugin that ships this one along with the rest of its 85 skills, 1 hook.

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 tao-launch-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-launch-workflow/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-launch-workflow)
Your own site
<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-launch-workflow"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-launch-workflow/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 tao-launch-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-launch-workflow"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-launch-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,024 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: 1 finding, 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 253
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00131 $0.04024
Opus 5 $0.00066 $0.02012
Sonnet 5 $0.00026 $0.00805
Haiku 4.5 $0.00013 $0.00402

Measured 11d ago against content hash 43304974f48e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tao-launch-workflow 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 11d 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/core/tao-launch-workflow/SKILL.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TAO Workflow Launch Intake

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).

Use this skill before launching any TAO workflow or model action.

Quick Start

Run the platform helper, ask for platform and monitoring preferences, then run the selected platform detail helper before asking for credentials.

Non-Negotiable Launch Gate

This gate is model-agnostic. Apply it to every TAO model, data action, and application workflow before launching side-effecting work.

Do not create runner scripts, launch scripts, compatibility shims, workspace folders, state files, logs, or dependency-install side effects until the launch preflight passes.

Preflight passes only after all of these are true:

  1. The execution platform is selected from the packaged platform helper.
  2. Platform credentials and required credential groups are satisfied.
  3. Model-specific credentials are satisfied.
  4. The default container image is resolved from packaged model/action metadata, shown to the user, and either confirmed or replaced by an explicit image=<override>.
  5. The platform access check succeeds from the launch host.
  6. Dataset inputs are mapped to concrete spec keys and verified from the selected platform's point of view.
  7. Required compute shape fields from the model/workflow skill are known.
  8. Required local tools for the selected data/platform path are present, or the user approved installing the smallest missing dependency and preflight was rerun.
  9. A launch review with image, platform, datasets, compute shape, expected runtime, and any generated/default configuration changes has been shown and confirmed by the user. For AutoML, the launch review must explicitly state recommendation count/budget, max concurrency, algorithm, metric, direction, and searched parameters/ranges even when defaults are used.

If any item is missing, ask for the missing input and stop before generating artifacts. This applies to AutoML, normal train/eval/infer/export/TRT, and DEFT/application workflows.

Read the full file on GitHub · 364 lines

Files

What ships with it

8 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. 11d ago First seen · 364 lines · 131 tokens per session scan A 43304974f48e

Subscribe to this mod's changes

tao-launch-workflow is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 131 tokens to every session and 4,024 once invoked, about $0.0007 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

data-engineering

A guide to data engineering, the work of collecting, moving, processing, and checking data. It covers workflow tools such as Airflow, Dagster, and Prefect, plus streaming and data-quality tools.

fengshao1227/ccg-workflow · 53 tokens

trulens-evaluation-workflow

Systematically evaluate your LLM application with TruLens.

truera/trulens · 18 tokens

ai

An index of skills for AI and language-model work, including agent development, security, retrieval-augmented generation, prompting, and evaluation. Retrieval-augmented generation gives a model relevant information from a knowledge base before it answers.

fengshao1227/ccg-workflow · 45 tokens

config-evals

Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…

n8n-io/n8n · 80 tokens

vs-crawler

Crawl websites (news, blogs, papers, GitHub, product docs, RSS feeds) into a fixed-schema JSONL file, then create a dataset and a searchable application in Viking AI Search. Supports one-time crawl and scheduled recurring crawl with automatic incremental sync.

volcengine/SearchCLI · 57 tokens

using-model-endpoint

Call a registered model endpoint over its native HTTP API from the endpoint's scoped inference kernel (BASEURL preloaded). Load once a task needs predictions from a registered model endpoint.

UnicomAI/wanwu · 40 tokens