hpc-foundations

hpc-foundations is a skill for Codex from SciMate-AI/HPC-Skills. It costs 87 tokens per session (506 once invoked), scanned A, original, MIT.

A guide to the basic ideas and tools behind high-performance computing (HPC), where large calculations run across powerful computers called clusters. It covers cluster systems, Linux, job schedulers, storage, containers, cloud basics, and administration.

In plain words
What is it for?
Use it to understand or explain HPC basics, Linux on clusters, Slurm, PBS Pro, or LSF job scheduling, containers, storage, networking, cloud setups, and cluster administration.
Why use it?
It removes the need to piece together HPC concepts from scattered sources. It helps explain how cluster jobs, software environments, and shared systems work.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to understand or explain HPC basics, Linux on clusters, Slurm, PBS Pro, or LSF job scheduling, containers, storage, networking, cloud setups, and cluster administration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/scimate-ai/hpc-skills/hpc-foundations
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.

Any agent
npx skills add SciMate-AI/HPC-Skills --skill hpc-foundations
Clone the repo
git clone --depth 1 https://github.com/SciMate-AI/HPC-Skills

Made for: Codex.

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-foundations

README.md
[![agentmods](https://agentmods.dev/badge/skills/scimate-ai/hpc-skills/hpc-foundations/github.svg)](https://agentmods.dev/skills/scimate-ai/hpc-skills/hpc-foundations)
Your own site
<a href="https://agentmods.dev/skills/scimate-ai/hpc-skills/hpc-foundations"><img src="https://agentmods.dev/badge/skills/scimate-ai/hpc-skills/hpc-foundations/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-foundations

Your own site · 80×15
<a href="https://agentmods.dev/skills/scimate-ai/hpc-skills/hpc-foundations"><img src="https://agentmods.dev/badge/skills/scimate-ai/hpc-skills/hpc-foundations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 506 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 $0.00087 $0.00506
Opus 5 $0.00044 $0.00253
Sonnet 5 $0.00017 $0.00101
Haiku 4.5 $0.00009 $0.00051

Measured 10d ago against content hash 02e71487e190, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hpc-foundations 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 10d 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.

skills/hpc-foundations/SKILL.md · 32 lines

What it actually says

HPC Foundations

Use this skill as the general HPC knowledge hub that sits below solver-specific skills and beside hpc-orchestration.

Start

  1. Read references/index-map.md first for the knowledge graph and the shortest route to the right topic.
  2. Read references/foundations-architecture-and-programming.md when the task starts from HPC concepts, system design, programming models, application development, or performance basics.
  3. Read references/schedulers-and-execution.md when the task is about Slurm, PBS Pro, LSF, queue semantics, batch scripts, arrays, or accounting commands.
  4. Read references/linux-and-os.md when the task is about Linux usage, login patterns, package management, glibc compatibility, or Linux versus Windows tradeoffs on clusters.
  5. Read references/software-environments.md when the task is about Conda, containers, Singularity or Apptainer-style execution, or picking common HPC tools.
  6. Read references/storage-network-cloud-and-admin.md when the task is about storage tiers, RDMA, hardware, cloud deployment, SSL, Hyper-V maintenance, or site-level administration topics.
  7. Read references/source-catalog.md when a page-level lookup of the hpclib.com crawl is needed.
  8. Read references/skillization-roadmap.md when splitting this index into narrower reusable skills.

Positioning

  • Prefer this skill for orientation, taxonomy, and first-pass explanation.
  • Prefer hpc-orchestration once the question becomes an execution workflow on a real cluster.
  • Prefer solver-specific skills once the question becomes input-deck or application specific.

Guardrails

  • Treat hpclib.com as a practical knowledge index, not as the final authority for production commands.
  • Re-check scheduler flags, MPI launch syntax, package names, and admin procedures against official upstream documentation before applying them on a live cluster.
  • Do not assume cluster policies, filesystem layouts, or security rules are portable across sites.
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. 10d ago First seen · 32 lines · 87 tokens per session scan A 02e71487e190

Subscribe to this mod's changes

hpc-foundations is a skill published in the GitHub repository SciMate-AI/HPC-Skills (85 stars, last pushed 5mo ago), licensed MIT. It adds 87 tokens to every session and 506 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens

ngs-pipeline-management

Next-generation sequencing pipeline management with Snakemake and Nextflow. Use for building, running, and debugging reproducible NGS workflows for RNA-seq, WGS, ChIP-seq, ATAC-seq, and amplicon sequencing. Covers pipeline design patterns, HPC/cloud execution, containerization, and workflow optimization.

Lord1Egypt/scientific-agent-toolkit · 72 tokens

pipeline-chipseq

Execute ENCODE ChIP-seq processing pipeline from FASTQ to peaks and signal tracks. Child of pipeline-guide. Provides stage-by-stage Nextflow execution with Docker containers and cloud deployment. Use when users need to process ChIP-seq data following ENCODE standards, run peak calling with MACS2, perform IDR analysis…

ammawla/encode-toolkit · 114 tokens

pipeline-dnaseseq

Execute ENCODE DNase-seq pipeline from FASTQ to hotspots and footprints. Child of pipeline-guide. Provides Nextflow execution with Docker and cloud deployment. Use when processing DNase-seq data, calling DNase hypersensitive sites, performing footprinting analysis. Trigger on: DNase-seq pipeline, DNase hypersensitive…

ammawla/encode-toolkit · 91 tokens

pipeline-wgbs

Execute ENCODE Whole Genome Bisulfite Sequencing (WGBS) pipeline from FASTQ to methylation calls. Child of pipeline-guide. Provides Nextflow execution with Docker and cloud deployment. Use when processing WGBS/bisulfite-seq data, calling methylation levels, generating bedMethyl files. Trigger on: WGBS pipeline…

ammawla/encode-toolkit · 103 tokens

nextflow-workflow-engine

Dataflow workflow engine for scalable bioinformatics pipelines. Defines processes (containerized tasks) connected by channels; runs local, HPC (SLURM/SGE), cloud (AWS/GCP/Azure), or Kubernetes via a single config change. Powers nf-core. Use Snakemake for rule-based Python workflows; use Nextflow for containerized…

jaechang-hits/SciAgent-Skills · 84 tokens