NVIDIA Trustworthy AI is a repository of documentation templates, example cards, and community tools for making AI systems and their data, models, agents, and skills easier to describe and govern. It serves NVIDIA, its customers and partners, and the wider AI community. The catalogue includes a skill from the repository for generating governance skill cards.
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.
git clone --depth 1 https://github.com/NVIDIA/Trustworthy-AIWrote 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/commands/nvidia/trustworthy-ai/bbq-analysis)<a href="https://agentmods.dev/commands/nvidia/trustworthy-ai/bbq-analysis"><img src="https://agentmods.dev/badge/commands/nvidia/trustworthy-ai/bbq-analysis/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/commands/nvidia/trustworthy-ai/bbq-analysis"><img src="https://agentmods.dev/badge/commands/nvidia/trustworthy-ai/bbq-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00183 |
| Opus 5.5 | $0.00000 | $0.00073 |
| Sonnet 5.5 | $0.00000 | $0.00037 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
bbq-analysis 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 today.
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.
What it actually says
BBQ result analysis
Use only scores and model metadata supplied for the current analysis. Do not infer private model results or use hardcoded competitive reference bands.
Filter to ambiguous context when requested. Compare a candidate to a baseline
with matching dataset, prompt, parser, model size and quantization, and disclose
any mismatches. acc_bias is a signed score: examine magnitude and direction;
a positive value alone does not establish a better model. A mean can hide
opposing category effects, so present per-category results as well.
The CLI writes category results to results/bbq_metrics.csv and a pooled score
to results/bbq_metrics_overall.csv. The pooled score is computed from records;
it is not the unweighted mean of category scores or a mean across models.
Use user-provided model results to compute reference bands and state their membership and sample sizes.
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.
- today First seen · 18 lines · 0 tokens per session scan A c396387a3442
bbq-analysis is a command published in the GitHub repository NVIDIA/Trustworthy-AI (67 stars, last pushed today), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 183 tokens. 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 2026-10-16.
Other commands, from other repositories
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.
vlm-ocr-evaluation
Run the vlm-ocr skill in its evaluate phase: compare candidate OCR systems against a stratified human-transcribed ground-truth sample and pick a model on measured CER/WER before committing to a bulk run.