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/commitnpx skills add NVIDIA-NeMo/DataDesigner --skill commitgit 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 | $0.00011 | $0.00787 |
| Opus 5 | $0.00005 | $0.00394 |
| Sonnet 5 | $0.00002 | $0.00157 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
commit 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Changes
Commit the current staged/unstaged changes with a well-crafted commit message.
Arguments
$ARGUMENTS can be used for special instructions, such as:
- Guiding the message: "emphasize the breaking change"
- Adding context: "this fixes issue #123"
- Requesting amend: "amend the previous commit"
Step 1: Gather Information
Run these commands in parallel to understand the changes:
- Git status:
git status --porcelain(check for staged/unstaged changes) - Staged diff:
git diff --cached(what will be committed if there are staged changes) - Unstaged diff:
git diff(what's modified but not staged) - Recent commits:
git log -5 --oneline(to match existing commit style)
Important checks:
- If no changes exist (nothing staged or unstaged), inform the user there's nothing to commit
- If there are unstaged changes but nothing staged, stage all changes with
git add -A(or ask user if they want to selectively stage) - If there are both staged and unstaged changes, ask user if they want to include unstaged changes
Step 2: Analyze Changes
Review the diff to understand:
- What changed (files, functions, features)
- Why it changed (bug fix, new feature, refactor, etc.)
- Impact (breaking changes, dependencies, configuration)
Step 3: Generate Commit Message
Message Guidelines
-
Subject line:
- Use imperative mood ("add feature" not "added feature")
- Keep under 50 characters (hard limit: 72)
- Don't end with a period
- Use lowercase for the first letter
-
Body (if needed for complex changes):
- Separate from subject with blank line
- Wrap at 72 characters
- Explain what and why, not how
- Use bullet points for multiple items
-
Footer (if needed):
- Reference issues:
Fixes #123,Closes #456
- Reference issues:
Examples
Simple change:
add user authentication endpoint
Change with body:
add rate limiting to public endpoints
- Implement token bucket algorithm
- Add configurable limits per endpoint
- Include rate limit headers in responses
Closes #234
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 · 113 lines · 11 tokens per session scan A f4d88974c7d8
commit is a skill published in the GitHub repository NVIDIA-NeMo/DataDesigner (2,194 stars, last pushed 2d ago), licensed Apache-2.0. It adds 11 tokens to every session and 787 once invoked, about $0.0001 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.