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 yamaru-eu/hardware-probe --skill hardware-performance-expertgit clone --depth 1 https://github.com/yamaru-eu/hardware-probeWrote 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/yamaru-eu/hardware-probe/hardware-performance-expert)<a href="https://agentmods.dev/skills/yamaru-eu/hardware-probe/hardware-performance-expert"><img src="https://agentmods.dev/badge/skills/yamaru-eu/hardware-probe/hardware-performance-expert.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 | $0.00021 | $0.00741 |
| Opus 5 | $0.00010 | $0.00370 |
| Sonnet 5 | $0.00004 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
hardware-performance-expert 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Hardware & Performance Expert
This skill is your primary expert for everything related to your machine's physical capabilities and real-time health. It provides deep diagnostics and actionable solutions for performance bottlenecks.
When to use
Activate this skill whenever you need to:
- Inventory: Get a detailed report of the local hardware (CPU, RAM, GPU, OS).
- Troubleshoot: Resolve slowness, high resource usage, or thermal throttling.
- AI Optimization: Evaluate LLM compatibility and optimize inference speeds.
- Upgrades: Get technical recommendations for hardware improvements.
Performance Troubleshooting Protocol
1. Resource Saturation Analysis
- Tool:
analyze_performance,analyze_ram_pressure - CPU Threshold: If
currentLoad> 80% sustained, identify top processes and recommend actions. - RAM Threshold: If
memory_used_percent> 90%, runanalyze_ram_pressureto analyze swap usage and top RSS processes.
2. Thermal & Power Bottlenecks
- Context: High-end hardware performing below expectations.
- Action: Call
thermal_profileto check for temperature spikes or frequency clipping (throttling) and suggest environmental fixes.
3. Storage Performance
- Tool:
analyze_local_system,check_storage_health - Action: Monitor SSD fill rates (> 90%). Call
check_storage_healthto verify SMART status and identify legacy HDDs slowing down modern workflows.
4. Dev Environment & Security
- Context: Slow build times or "permission denied" errors on dev paths.
- Action: Call
diagnose_antivirus_impactto detect EDR/Antivirus exclusion coverage on project hot paths.
5. Time-Bound Monitoring
- Context: Transient issues that happen during a specific task (e.g., "The machine slows down only when I compile" or "Inference starts fast then lags").
- Action: Call
monitor_system_healthwith a duration (e.g., 30s) to collect statistical data (min/max/avg) while the problematic task is running.
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 · 62 lines · 21 tokens per session scan A 3602ad914974
hardware-performance-expert is a skill published in the GitHub repository yamaru-eu/hardware-probe (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 741 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 2026-08-31.
Other skills, from other repositories
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when a device is unreachable, a user reports connectivity problems, an interface…
pyats-troubleshoot
Systematic network troubleshooting - connectivity, routing, interface, protocol, and performance issues using structured OSI-layer and divide-and-conquer methodology. Use when something is broken, a device is unreachable, a link is flapping, users report slow performance, or an OSPF/BGP adjacency is down.