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 agentmods add skills/nvidia-nemo/datadesigner/datadesigner-docsnpx skills add NVIDIA-NeMo/DataDesigner --skill datadesigner-docsgit clone --depth 1 https://github.com/NVIDIA-NeMo/DataDesignerWhat 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 | $0.00080 | $0.05155 |
| Opus 5 | $0.00040 | $0.02577 |
| Sonnet 5 | $0.00016 | $0.01031 |
| Haiku 4.5 | $0.00008 | $0.00515 |
Grade A, and why
datadesigner-docs 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 yesterday.
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 — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Designer Docs Maintenance
Unified skill for adding, updating, moving, and removing pages on the NeMo Data Designer Fern docs site.
Current URL: docs.nvidia.com/nemo/datadesigner (see instances in fern/docs.yml). Source of truth for everything user-facing is fern/.
Scope Rule
ALL doc prose edits happen under fern/. The remaining docs/ directory is only for notebook source, generated Colab notebooks, docs scripts, and downloadable recipe scripts. docs/notebook_source/*.py remains canonical for notebook code. Concept pages, recipes, plugins, and Dev Notes prose live under fern/versions/latest/pages/.
Versioning Model
main contains only the latest Fern authoring docs. Historical release snapshots live on the CI-managed docs-website branch and must not be edited on main.
fern/versions/
├── latest.yml ← authoring nav file
└── latest/pages/ ← authoring MDX tree
docs.yml on main registers only slug: latest. When you edit docs, edit latest/pages/ and latest.yml.
Dev Notes are patched into the published latest docs by CI. Add new posts to latest/pages/devnotes/posts/ and latest.yml on main.
For future Fern-native releases, do not copy page trees by hand on main. The release workflow snapshots latest into a frozen version on docs-website.
Layout at a Glance
fern/
├── README.md ← maintainer cheat sheet
├── docs.yml ← title, theme, versions:, redirects, custom-domain
├── fern.config.json ← organization + fern-api version pin
├── main.css ← bundled NVIDIA theme CSS
├── assets/ ← logos, favicon, recipe assets, devnote post images (shared)
├── images/ ← /images/* references from MDX
├── styles/ ← per-component CSS (notebook-viewer, authors, metrics-table, …)
├── components/ ← React/JSX MDX components
│ ├── NotebookViewer.tsx ← renders converted .ipynb cells with outputs
│ ├── Authors.tsx ← devnote bylines (uses devnotes/authors-data.ts)
│ ├── MetricsTable.tsx ← benchmark tables w/ best-value highlight
│ ├── TrajectoryViewer.tsx ← multi-turn tool-call traces (research dev notes)
│ ├── BadgeLinks.tsx ← header shields (license, github, etc.)
│ ├── Tag.tsx, CustomCard.tsx, CustomFooter.tsx
│ ├── notebooks/ ← gitignored per-tutorial *.json + *.ts output
│ └── devnotes/ ← .authors.yml, authors-data.ts, per-post trajectory data
├── scripts/
│ └── ipynb-to-fern-json.py ← .ipynb → fern/components/notebooks/*.{json,ts}
└── versions/
├── latest.yml ← authoring navigation tree
└── latest/pages/ ← authoring MDX content
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.
- yesterday First seen · 467 lines · 80 tokens per session scan A 3719bff9a484
datadesigner-docs is a skill published in the GitHub repository NVIDIA-NeMo/DataDesigner (2,194 stars, last pushed 2d ago), licensed Apache-2.0. It adds 80 tokens to every session and 5,155 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
omni-rewriter-promo-pipeline
Build Omni-Rewriter promo films: validated H3 PE chunks, RAW vs PE proof cards with PE audio, designed models finale, and soft-xfade assemble. Use when making or regenerating docs/promo media, promo scripts, or agent workflows that mirror the maintainer promo pipeline.
omni-rewriter-model-contribution
Scaffold and review new Video, Image, or Unified model contributions for Omni-Rewriter. Use when adding a PE profile, task route, validator, renderer, fixture, generation adapter, compatibility claim, or model-support pull request.
omni-rewriter-h3-pe
Extend Omni-Rewriter's validated prompt-expansion framework and its H3 video and Seedream / Qwen-Image image profiles. Use when writing profile rules, RewriteRequest fixtures, PE repairs, renderers, adapters, or raw-vs-expanded comparisons.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
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.
evolve
Start or monitor an evolutionary development loop.