NVIDIA/TensorRT-Model-Connect is a collection of C++ reference implementations for deploying supported Hugging Face models with NVIDIA TensorRT, a system that runs trained models to produce inference results. It is for developers who want to build and run supported models or evaluate model integrations through TensorRT. The catalogue entries provide skills and instructions for using this model deployment workflow.
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 skills add NVIDIA/TensorRT-Model-Connect --skill doc-syncgit clone --depth 1 https://github.com/NVIDIA/TensorRT-Model-ConnectWrote 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/skills/nvidia/tensorrt-model-connect/doc-sync)<a href="https://agentmods.dev/skills/nvidia/tensorrt-model-connect/doc-sync"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-model-connect/doc-sync/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/skills/nvidia/tensorrt-model-connect/doc-sync"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-model-connect/doc-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00386 |
| Opus 5.5 | $0.00012 | $0.00154 |
| Sonnet 5.5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
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 2mo 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.
What it actually says
Synchronize Documentation
Treat implementation, tests, executable help, and family manifests as the source of truth. Update only documentation affected by the requested change.
Route the change
- Public build behavior: check
core/builder/and the Python API docs. - Native user behavior: check
core/runtime/include/trtmc/, CLI parsing, and the C++ API docs. - Model behavior: check only the owning
families/<family>/implementation, manifests, thresholds, and model recipe. - Developer workflow: check
README.md,CONTRIBUTING.md, and the relevant page underwebsite/docs/. - Benchmark behavior: check
apps/benchmark/and its performance README. - Repo-local skills: check
plugins/trtmc-agent-skills/skills/.
Verify every changed path, symbol, option, and command locally when practical. If hardware or dependencies prevent execution, inspect the consuming code and state that boundary explicitly. Do not turn source presence into a runtime, parity, performance, or qualification claim.
Keep one canonical explanation and link to it instead of copying large policy sections. Remove stale links and generated counts rather than replacing them with unverified values.
Validate
git diff --check
PYTHONPATH=core/builder:apps/benchmark:. python3 -m tools.model_ci validate
npm --prefix website run test:model-support
npm --prefix website run build
Run additional focused tests for any documented command or API that changed. Summarize corrected claims, validation actually run, and remaining evidence boundaries. Publish or open a pull request only when the user requested it.
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.
- 2mo ago Changed · -326 lines · -35 tokens per session aa41a67ef18d
- 2mo 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 (289 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 386 once invoked, about $0.0001 per session on Opus 5.5. 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.
doc-sync compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| doc-syncNVIDIA/TensorRT-Model-Connect | Skill | 289 | yesterday | Apache-2.0 | A | 30 | Codex |
| graphsignal-profilergraphsignal/graphsignal-profiler | Skill | 245 | 3mo ago | Apache-2.0 | A | 74 | Claude Code, Codex |
| zoom-meeting-sdk-windowsanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 59 | Claude Code |
| scope-creep-detectorShubhamsaboo/awesome-llm-apps | Skill | 144k | yesterday | Apache-2.0 | A | 98 | Claude Code, Codex |
| mem0-test-integrationmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 207 | Claude Code, Codex |
| prowler-changelogprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 92 | Claude Code |
| groq-inferencesynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 77 | Claude Code, Codex |