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 naveedharri/benai-skills --skill scan-my-machinegit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/scan-my-machine)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/scan-my-machine"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/scan-my-machine/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/naveedharri/benai-skills/scan-my-machine"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/scan-my-machine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00130 | $0.00911 |
| Opus 5 | $0.00065 | $0.00456 |
| Sonnet 5 | $0.00026 | $0.00182 |
| Haiku 4.5 | $0.00013 | $0.00091 |
Grade A, and why
scan-my-machine 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan My Machine
Reads the machine's real memory and GPU, then names the local models that fit. Read-only: this skill never installs, downloads, or changes anything.
Before you start
Run the check in references/environment-check.md first. These skills need a shell on the user's own machine. If the environment is a sandbox or container, stop and tell the user to run this in Claude Code on the computer they want to set up. Do not report detected specs from a sandbox: wrong specs are worse than none.
Steps
Track progress:
Task Progress:
- [ ] 1. Detect the hardware
- [ ] 2. Work out the usable memory budget
- [ ] 3. Name the models that fit
- [ ] 4. Report what is already installed
- [ ] 5. Render the HTML report
1. Detect the hardware
Run the detection commands for the user's OS from references/detect-hardware.md. Get: total memory, GPU and its VRAM, chip name, free disk. Never ask the user for specs you can detect yourself. If a command fails, try the fallback in that file before asking.
2. Work out the usable memory budget
Take the memory that matters (discrete GPU VRAM, or unified memory on Apple Silicon) and multiply by 0.75. That headroom is for conversation context and the app itself. Report the raw figure and the budget separately so the user sees why they differ.
3. Name the models that fit
Match the budget against the tier table in references/model-tiers.md. Output named models with their quantization tag and expected tokens per second, never a tier number alone. State one primary pick and at most two alternates. If the budget spans two tiers, pick the lower one.
4. Report what is already installed
Run the inventory commands in references/detect-hardware.md to find existing Ollama, LM Studio, Open WebUI and already-pulled models. Tell the user what they already have so they do not download something twice.
5. Render the HTML report
Deliver the result as a rendered HTML page, not as chat text. Build it from references/report-template.md using the scan-my-machine layout in section 4, save it to the Desktop, and open it. Keep the chat reply to two lines plus the file path.
What ships with it
4 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.
- 6d ago First seen · 63 lines · 130 tokens per session scan A c851fa77da4d
scan-my-machine is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 8d ago), licensed MIT. It adds 130 tokens to every session and 911 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
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.
actual-setup
Set up Actual Computer (actual.inc) inference in Hermes.
ai-prompting-basics
A practical guide to writing clearer requests for Claude, an AI assistant, by adding context, examples, roles, and output rules.