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 claude-dev-suite/claude-dev-suite --skill ai-hardware-selectiongit clone --depth 1 https://github.com/claude-dev-suite/claude-dev-suiteWrote 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/claude-dev-suite/claude-dev-suite/ai-hardware-selection)<a href="https://agentmods.dev/skills/claude-dev-suite/claude-dev-suite/ai-hardware-selection"><img src="https://agentmods.dev/badge/skills/claude-dev-suite/claude-dev-suite/ai-hardware-selection.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 5.1 | $0.00159 | $0.00633 |
| Opus 5 | $0.00079 | $0.00316 |
| Sonnet 5 | $0.00032 | $0.00127 |
| Haiku 4.5 | $0.00016 | $0.00063 |
Grade A, and why
ai-hardware-selection 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 7d 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
AI Hardware Selection
The metric that usually decides: memory, then bandwidth
For LLM inference, the binding constraint is typically VRAM/HBM capacity
(weights + KV-cache must fit) and memory bandwidth (decode is
memory-bound) — not raw FLOPS. Size first:
weights ≈ params × bytes/param (e.g. 70B × 2B(FP16) ≈ 140GB → multi-GPU or
quantize). Add KV-cache (grows with context × batch). Only then look at TOPS.
Accelerator families
| Type | Strength | Use |
|---|---|---|
| GPU (NVIDIA H/B-series, AMD MI) | Flexible, huge ecosystem, HBM | Training + inference, the default |
| TPU | Matmul-dense, pod-scale interconnect | Large-scale training/inference on GCP |
| NPU | Perf/Watt at low power | Edge / mobile / AI-PC inference |
| FPGA | Custom low-latency dataflow | Niche ultra-low-latency / fixed pipelines |
| CPU | Available, fine for small/batch | Small models, embeddings, light load |
Other levers
- Interconnect (NVLink, InfiniBand): decisive for multi-GPU training and tensor parallelism — bandwidth between accelerators bounds scaling.
- Precision support: FP8/INT4 support multiplies effective throughput/capacity.
- Cost/Watt & TCO: cloud per-hour vs owned; power/cooling; utilization. The honest metric is cost per token (or per request) at target latency.
- Training vs inference: training needs FLOPS + interconnect + memory; inference needs memory capacity/bandwidth + latency.
When to recommend what
- Default / flexibility / training → NVIDIA GPUs (size by model VRAM).
- Edge/mobile/low-power inference → NPU.
- Hyperscale training on GCP → TPU pods.
- Fixed ultra-low-latency pipeline → FPGA (only if justified).
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.
- 7d ago First seen · 49 lines · 159 tokens per session scan A c3fcd980a749
ai-hardware-selection is a skill published in the GitHub repository claude-dev-suite/claude-dev-suite (30 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 633 once invoked, about $0.0008 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
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.