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 athola/claude-night-market --skill cpu-gpu-performancegit clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/athola/claude-night-market/cpu-gpu-performance)<a href="https://agentmods.dev/skills/athola/claude-night-market/cpu-gpu-performance"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/cpu-gpu-performance/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/athola/claude-night-market/cpu-gpu-performance"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/cpu-gpu-performance.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 | $0.00038 | $0.01135 |
| Opus 5 | $0.00019 | $0.00567 |
| Sonnet 5 | $0.00008 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
cpu-gpu-performance 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Table of Contents
- When to Use
- Required TodoWrite Items
- Step 1: Establish Current Baseline
- Step 2: Narrow the Scope
- Step 3: Instrument Before You Optimize
- Step 4: Throttle and Sequence Work
- Step 5: Log Decisions and Next Steps
- Output Expectations
CPU/GPU Performance Discipline
When To Use
- At the beginning of every session (auto-load alongside
token-conservation). - Whenever you plan to build, train, or test anything that could pin CPU cores or GPUs for more than a minute.
- Before retrying a failing command that previously consumed significant resources.
When NOT To Use
- Simple operations with no resource impact
- Quick single-file operations
Required TodoWrite Items
cpu-gpu-performance:baselinecpu-gpu-performance:scopecpu-gpu-performance:instrumentcpu-gpu-performance:throttlecpu-gpu-performance:log
Step 1: Establish Current Baseline
-
Capture current utilization:
uptimeps -eo pcpu,cmd | headnvidia-smi --query-gpu=utilization.gpu,memory.used --format=csv
Note which hosts/GPUs are already busy.
-
Record any CI/cluster budgets (time quotas, GPU hours) before launching work.
-
Set a per-task CPU minute / GPU minute budget that respects those limits.
Step 2: Narrow the Scope
- Avoid running "whole world" jobs after a small fix. Prefer diff-based
or tag-based selective testing:
pytest -k- Bazel target patterns
cargo test <module>
- Batch low-level fixes so you can validate multiple changes with a single targeted command.
- For GPU jobs, favor unit-scale smoke inputs or lower epoch counts before scheduling the full training/eval sweep.
Step 3: Instrument Before You Optimize
- Pick the right profiler/monitor:
- CPU work:
perfintel vtunecargo flamegraph- language-specific profilers
- GPU work:
nvidia-smi dmonnsysnvprof- DLProf
- framework timeline tracers
- CPU work:
- Capture kernel/ops timelines, memory footprints, and data pipeline latency so you have evidence when throttling or parallelizing.
- Record hot paths and I/O bottlenecks in notes so future reruns can jump straight to the culprit.
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.
- 6d ago First seen · 120 lines · 38 tokens per session scan A cfba73866da4
cpu-gpu-performance is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 1,135 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
hf-cloud-sagemaker-deployment-planner
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image /…
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
minicpm5-deploy-llama-cpp
Run MiniCPM5-1B or MiniCPM5-2B with llama.cpp using the released GGUF artifacts (F16 / Q80 / Q4KM). Use when the user wants CPU-only / consumer-GPU / cross-platform native deployment, asks for "llama.cpp", "llama-cli", "llama-server", "GGUF", or has no Python available.