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/tensorrt-model-connect/submit-github-bug-issuenpx skills add NVIDIA/TensorRT-Model-Connect --skill submit-github-bug-issuegit clone --depth 1 https://github.com/NVIDIA/TensorRT-Model-ConnectWhat 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 | $0.00082 | $0.01506 |
| Opus 5 | $0.00041 | $0.00753 |
| Sonnet 5 | $0.00016 | $0.00301 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
submit-github-bug-issue 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit GitHub Bug Issue
Purpose
File actionable QA findings as GitHub issues in the active repository:
NVIDIA/TensorRT-Model-Connect.
Use this skill for bug issue submission only. Use $submit-github-pr for pull
requests and $write-git-messages for commit, PR, squash, or rebase messages.
Ground Rules
- Treat GitHub as the active repository:
https://github.com/NVIDIA/TensorRT-Model-Connect.git. - Use the local
githubremote when Git operations are needed. - Do not push branches or change repository files unless the user explicitly asks for code or skill edits.
- Do not create duplicate issues. Search first and reuse an existing issue when it already captures the same root cause.
- Keep claims evidence-based. Do not invent repro results, labels, issue numbers, hardware, CI behavior, severity, or suspected code locations.
- Prefer English issue text for GitHub unless the user explicitly requests another language.
- Never read, print, transform, or replay tokens/passwords from Git credential
helpers. Use an already authenticated
ghsession.
Workflow
1. Authenticate And Resolve The Repository
gh auth status
gh repo view NVIDIA/TensorRT-Model-Connect \
--json nameWithOwner,url,defaultBranchRef
git remote get-url github
If gh is unavailable, unauthenticated, or cannot read the repository, stop
and ask the user to authenticate outside the sandbox. Do not fall back to
extracting credentials or unauthenticated REST calls for this private
repository.
2. Gather Evidence
Read the source artifact before drafting. For QA reports, extract:
- finding ID and severity
- concise symptom
- exact repro command or test case
- observed exit code, output, logs, or artifact path
- expected behavior
- affected model, strategy, command, or component
- environment details
- evidence count or case IDs
- suspected source path only when the evidence supports it
If the finding is too vague to create an actionable issue, ask for the missing critical detail instead of filing a weak report.
What ships with it
1 file 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.
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 · 213 lines · 82 tokens per session scan A 279cf3dfe268
submit-github-bug-issue is a skill published in the GitHub repository NVIDIA/TensorRT-Model-Connect (188 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 1,506 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
graphsignal-profiler
Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.
weights-and-biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform.
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
perf-host-analysis
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify…
perf-host-optimization
Profiles and optimizes TensorRT-LLM host/CPU overhead using lineprofiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.