Borrowing it
Nothing to install: this file belongs to NVIDIA/TensorRT-LLM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NVIDIA/TensorRT-LLM/main/.claude/skills/perf-torch-cuda-graphs/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/TensorRT-LLMWrote 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-llm/perf-torch-cuda-graphs)<a href="https://agentmods.dev/skills/nvidia/tensorrt-llm/perf-torch-cuda-graphs"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/perf-torch-cuda-graphs/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-llm/perf-torch-cuda-graphs"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/perf-torch-cuda-graphs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 319 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 330 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 583 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00119 | $0.05904 |
| Opus 5.5 | $0.00048 | $0.02362 |
| Sonnet 5.5 | $0.00024 | $0.01181 |
| Haiku 4.5 | $0.00012 | $0.00590 |
Grade A, and why
perf-torch-cuda-graphs 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 17d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
6 files 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.
- 17d ago Changed 901c48fafb23
- 2mo ago First seen · 635 lines · 119 tokens per session scan A aee437b6c16c
perf-torch-cuda-graphs is a skill published in the GitHub repository NVIDIA/TensorRT-LLM (15,021 stars, last pushed today), with no licence file. It adds 119 tokens to every session and 5,904 once invoked, about $0.0005 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.
perf-torch-cuda-graphs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| perf-torch-cuda-graphsNVIDIA/TensorRT-LLM | Skill | 15k | today | none | A | 119 | Claude Code |
| sglang-diffusion-cache-ditsgl-project/sglang | Skill | 39k | today | Apache-2.0 | A | 161 | Claude Code |
| ml-training-recipesOrchestra-Research/AI-Research-SKILLs | Skill | 14k | 26d ago | MIT | A | 88 | Claude Code |
| perf-torch-cuda-graphswenyi-li/awesome-agent-kernel-skills | Skill | 10 | 5mo ago | none | A | 119 | Claude Code, Codex |
| ml-training-recipesTTAWDTT/elegant-researcher-skill | Skill | 5 | 5mo ago | MIT | A | 88 | Claude Code, Codex |
| sglang-diffusion-performancesgl-project/sglang | Skill | 39k | today | Apache-2.0 | A | 29 | Claude Code, Codex |
| sglang-diffusion-add-modelsgl-project/sglang | Skill | 39k | today | Apache-2.0 | A | 24 | Claude Code, Codex |