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/doc-syncnpx skills add NVIDIA/TensorRT-Model-Connect --skill doc-syncgit 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 | $0.00065 | $0.03310 |
| Opus 5 | $0.00032 | $0.01655 |
| Sonnet 5 | $0.00013 | $0.00662 |
| Haiku 4.5 | $0.00006 | $0.00331 |
Grade A, and why
doc-sync 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Sync
Purpose
Scan documentation drift against the implementation and produce focused GitHub PRs. Process these phases in order:
- Canonical documentation: keep the six website sections and newcomer path accurate.
- Architecture context and traceability: maintain ADRs and evidence status without upgrading incomplete evidence into a compliance claim.
- Compatibility redirects: preserve retired routes without restoring a second source of truth.
Do not guess based on filenames. Read the implementation, tests, manifests, and live command help before changing behavioral prose or command examples.
Keep evidence tiers distinct:
- a path, symbol, option, or command exists;
- static and documentation checks pass;
- CPU tests pass;
- target-hardware execution passes; and
- model parity, performance, or qualification is proven.
Canonical Information Architecture
The maintained website sources are:
| Section | Source |
|---|---|
| Getting Started | website/docs/getting-started/ |
| Learn & Tutorials | website/docs/learning-path.md, website/docs/tutorials/ |
| API Reference | website/docs/api/ |
| Architecture & Design | website/docs/architecture/ |
| Contribute & Extend | website/docs/extend/ |
| Feature Reference & Context | website/docs/features/, website/docs/context/, website/docs/reference/ |
The navigation in website/sidebars.js and website/docusaurus.config.js
must expose those sources consistently. website/docs/wiki/,
website/docs/operations/, website/docs/unit-design/, and retired
architecture pages are compatibility routes, not maintained content sources.
Change Set
Fetch current GitHub main:
git fetch github main
DOC_SYNC_CURRENT_SHA=$(git rev-parse github/main)
If website/docs/context/.last_scan_sha exists, use it only after proving that
it names a commit and is an ancestor of the current main SHA:
DOC_SYNC_LAST_SHA=$(cat website/docs/context/.last_scan_sha)
git cat-file -e "${DOC_SYNC_LAST_SHA}^{commit}"
git merge-base --is-ancestor \
"$DOC_SYNC_LAST_SHA" "$DOC_SYNC_CURRENT_SHA"
git diff --name-status \
"$DOC_SYNC_LAST_SHA".."$DOC_SYNC_CURRENT_SHA"
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.
- 2d ago First seen · 372 lines · 65 tokens per session scan A 77a27746dd27
doc-sync is a skill published in the GitHub repository NVIDIA/TensorRT-Model-Connect (188 stars, last pushed 2d ago), licensed Apache-2.0. It adds 65 tokens to every session and 3,310 once invoked, about $0.0003 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.
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.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.