hpc-checkup

hpc-checkup is a command for Claude Code from yale-som-hpc/claude-code-marketplace. It costs 14 tokens per session (257 once invoked), scanned A, original, Unlicense.

A command that checks whether recent jobs on a Slurm high-performance computing cluster requested suitable resources. Slurm is a system that schedules computing jobs; the report explains CPU, memory, time, and GPU use in plain language.

In plain words
What is it for?
Use it to review a specified job or recent finished jobs and receive suggested values for memory, CPUs, and time, plus warnings about inefficient GPU or CPU use.
Why use it?
It shows when a job requested too much or too little computing capacity. This helps avoid wasted resources and gives you better settings for future jobs.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the hpc plugin — 23 skills, 3 commands shipped together

Good fit Use it to review a specified job or recent finished jobs and receive suggested values for memory, CPUs, and time, plus warnings about inefficient GPU or CPU use.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/yale-som-hpc/claude-code-marketplace/hpc-checkup
Install

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.

Clone the repo
git clone --depth 1 https://github.com/yale-som-hpc/claude-code-marketplace

Made for: Claude Code.

Or install hpc, the plugin that ships this one along with the rest of its 23 skills, 3 commands.

Wrote 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.

agentmods badge for hpc-checkup

README.md
[![agentmods](https://agentmods.dev/badge/commands/yale-som-hpc/claude-code-marketplace/hpc-checkup/github.svg)](https://agentmods.dev/commands/yale-som-hpc/claude-code-marketplace/hpc-checkup)
Your own site
<a href="https://agentmods.dev/commands/yale-som-hpc/claude-code-marketplace/hpc-checkup"><img src="https://agentmods.dev/badge/commands/yale-som-hpc/claude-code-marketplace/hpc-checkup/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.

agentmods 80×15 button for hpc-checkup

Your own site · 80×15
<a href="https://agentmods.dev/commands/yale-som-hpc/claude-code-marketplace/hpc-checkup"><img src="https://agentmods.dev/badge/commands/yale-som-hpc/claude-code-marketplace/hpc-checkup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 257 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00257
Opus 5 $0.00007 $0.00129
Sonnet 5 $0.00003 $0.00051
Haiku 4.5 $0.00001 $0.00026

Measured 12d ago against content hash f882fe5f3530, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hpc-checkup 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 12d 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.

plugins/hpc/commands/hpc-checkup.md · 16 lines

What it actually says

Run a resource checkup on the Yale SOM HPC cluster and report in plain language.

Follow the self-diagnosing-resource-use skill. Steps:

  1. If a job ID was given ($ARGUMENTS), check that job. Otherwise list my recent jobs with sacct -u $USER --starttime=today --format=JobID,JobName,Elapsed,AllocCPUS,TotalCPU,MaxRSS,State and pick the finished ones.
  2. Run seff JOBID on each.
  3. Tell me, for each job, whether it used what it requested — CPUs, memory, time, and GPU if any — and give the concrete --mem / --cpus-per-task / --time I should request next time. Translate the numbers; don't just paste seff output.
  4. Flag anything wasteful (idle GPU, <10% CPU efficiency, memory hugely over-requested) and the one change that fixes it.

Run only read-only accounting commands. Do not submit or cancel jobs.

Changes

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.

  1. 12d ago First seen · 16 lines · 14 tokens per session scan A f882fe5f3530

Subscribe to this mod's changes

hpc-checkup is a command published in the GitHub repository yale-som-hpc/claude-code-marketplace (5 stars, last pushed 2mo ago), licensed Unlicense. It adds 14 tokens to every session and 257 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.