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-llm/perf-host-analysisnpx skills add NVIDIA/TensorRT-LLM --skill perf-host-analysisgit clone --depth 1 https://github.com/NVIDIA/TensorRT-LLMWhat 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 | $0.00171 | $0.03942 |
| Opus 5 | $0.00086 | $0.01971 |
| Sonnet 5 | $0.00034 | $0.00788 |
| Haiku 4.5 | $0.00017 | $0.00394 |
Grade A, and why
perf-host-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 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
11 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.
- references/examples.md 6.8 KB
- references/iteration-isolation-techniques.md 6.0 KB
- references/kernel-level-analysis.md 8.0 KB
- references/metrics.md 9.0 KB
- references/nsys-schema.md 3.1 KB
- references/output-format.md 6.1 KB
- references/phase-classification.md 4.1 KB
- references/thresholds.md 3.2 KB
- references/trtllm-nvtx-ranges.md 6.5 KB
- scripts/analyze_host_overhead.py 28 KB runs code
- scripts/detect_host_overhead.py 21 KB runs code
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 · 353 lines · 171 tokens per session scan A 3d67ec228375
perf-host-analysis is a skill published in the GitHub repository NVIDIA/TensorRT-LLM (14,505 stars, last pushed 2d ago), with no licence file. It adds 171 tokens to every session and 3,942 once invoked, about $0.0009 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
perf-host-analysis
Analyze host/CPU overhead in LLM inference (vLLM / SGLang / TRT-LLM serve / lmdeploy / TensorRT-LLM) from nsys traces. Phase 1 (Detection): determine whether host overhead is the bottleneck via a binary YES/NO verdict with metric evidence (GPU idle ratio, host prep exposed ratio, per-phase breakdown). Phase 2 (Root…
add-jit-kernel
Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jitkernel module.
sglang-runtime-context
How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace config bags, the pristine ServerArgs seed, override entry points, resource/stream/buffer leases, per-forward flags), the CI guardrails that enforce the design, and the idioms for developing and testing…
sglang-diffusion-performance
Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.
sglang-diffusion-add-model
Use when adding a new diffusion model or Diffusers pipeline to SGLang.
ci-workflow-guide
Guide to SGLang CI workflow orchestration — stage ordering, fast-fail, gating, partitioning, execution modes, and debugging CI failures. Use when modifying CI workflows, adding stages, debugging CI pipeline issues, or understanding how tests are dispatched and gated across stages.