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 Saddss/cursor-skills --skill perf-nsight-compute-analysisgit clone --depth 1 https://github.com/Saddss/cursor-skillsWrote 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/saddss/cursor-skills/perf-nsight-compute-analysis)<a href="https://agentmods.dev/skills/saddss/cursor-skills/perf-nsight-compute-analysis"><img src="https://agentmods.dev/badge/skills/saddss/cursor-skills/perf-nsight-compute-analysis/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/saddss/cursor-skills/perf-nsight-compute-analysis"><img src="https://agentmods.dev/badge/skills/saddss/cursor-skills/perf-nsight-compute-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00127 | $0.03847 |
| Opus 5 | $0.00063 | $0.01924 |
| Sonnet 5 | $0.00025 | $0.00769 |
| Haiku 4.5 | $0.00013 | $0.00385 |
Grade B, and why
perf-nsight-compute-analysis scanned grade B with 1 finding 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `Permission denied` | Needs elevated privileges | `sudo ncu ...` or `--cap-add=SYS_ADMIN` in containers | 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
8 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.
- 9d ago First seen · 399 lines · 127 tokens per session scan B b3ea7fb46b2d
perf-nsight-compute-analysis is a skill published in the GitHub repository Saddss/cursor-skills (2 stars, last pushed 11d ago), with no licence file. It adds 127 tokens to every session and 3,847 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
performance
Use when a page or interaction is slow for one user and the fix starts from a measurement — a failing Core Web Vital (LCP, INP, CLS), a heavy JS bundle, wasted re-renders, an over-broad client boundary: profile, attribute the cost to one phase, fix it, re-measure. NOT surviving concurrent load (that is scaling), NOT…
Function Call Tracing
Instrument C/C++ with -finstrument-functions for execution tracing and Perfetto visualisation.
rust-build-optimization
Use when a Rust or Cargo build is slow and the user wants it diagnosed or sped up: profiling compile times with cargo --timings or -Zself-profile, finding whether the bottleneck is dependencies, codegen/LLVM, linking, or one oversized crate, and applying targeted fixes such as faster linkers (lld, mold, wild)…
persistent_straggler
Find ranks that are slow on many steps (worstfraction), not just once.
performance-optimization
Use when performance requirements exist, profiling reveals bottlenecks, or Core Web Vitals need improvement. Do NOT use without evidence — premature optimization adds complexity.
nccl_culprit_victim
NCCL proxy wait decomposition — culprit (sendgpuwait) vs victim (recvwait).