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/deeplink-org/probing/gpu_pressurenpx skills add DeepLink-org/probing --skill gpu_pressuregit clone --depth 1 https://github.com/DeepLink-org/probingWrote 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/deeplink-org/probing/gpu_pressure)<a href="https://agentmods.dev/skills/deeplink-org/probing/gpu_pressure"><img src="https://agentmods.dev/badge/skills/deeplink-org/probing/gpu_pressure.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00241 |
| Opus 5 | $0.00005 | $0.00120 |
| Sonnet 5 | $0.00002 | $0.00048 |
| Haiku 4.5 | $0.00001 | $0.00024 |
Grade A, and why
gpu_pressure 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 4d 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
GPU memory and utilization pressure
查看 gpu.utilization 采样与 python.torch_trace 中的 allocated 是否一致， 判断是「真 OOM 风险」还是「利用率低 / 内存碎片」。
Parameters
sample_limit(integer, default20):
Related skills
- 显存持续上涨 → skill: memory_leak
- MPS Mac → torch.mps.current_allocated_memory 已在 torch_trace 中
- 启用更细 profiling → probing.torch.profiling=on,random:0.1
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.
- 4d ago First seen · 29 lines · 10 tokens per session scan A fc9a6f467919
gpu_pressure is a skill published in the GitHub repository DeepLink-org/probing (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 10 tokens to every session and 241 once invoked, about $0.0001 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
profiling
Diagnose frame-rate bottlenecks (CPU vs GPU bound FIRST), control Unreal Insights traces, sample live frame times, and annotate performance captures. Use when FPS is low/bad, the game is slow, or you need to find what is limiting the frame rate.
pytorch-profile-analysis
Analyze single-file PyTorch/Kineto Chrome trace .json(.gz) files using the VeloQ CLI. Use for CPU/CUDA/kernel correlation, ProfilerStep/annotation slicing, memory/shape grouping, and single-trace NCCL evidence.
cuda-kernel-optimizer
Use when optimizing, tuning, diagnosing, or profiling CUDA, CUTLASS, Triton, PyTorch, vLLM, TensorRT-LLM, or another GPU workload; when assessing an NCU, Nsys, or PyTorch Profiler report; or when the test workload, correctness checks, measurement path, or target environment is incomplete.
ncu-profile-analysis
Analyze Nsight Compute .ncu-rep and .ncu-repz kernel reports using the VeloQ CLI. Use for occupancy, warp stalls, memory/instruction bottlenecks, rule findings, source/SASS/PTX correlation, and metric CSV/table export.
nsys-profile-analysis
Analyze Nsight Systems .nsys-rep or pqtdir/ timeline traces using the VeloQ CLI. Use for GPU idle gaps, launch causes, CPU/GPU correlation, NVTX, CUDA graphs, metrics, sampling, and overlap/concurrency.
performance-profiling
优化性能时使用。先测量定位再优化,不凭感觉。.