sol-skill

sol-skill is a skill for Claude Code, Codex from Shu-Wan/solx. It costs 266 tokens per session (9,623 once invoked), scanned B, original, MIT.

A set of rules and tools for working on ASU’s Sol supercomputer, including its command-line tool for jobs and storage.

In plain words
What is it for?
It helps start and manage interactive or scheduled jobs, renew files in /scratch, choose storage locations, and work safely on Sol without using sudo.
Why use it?
It helps an AI assistant recognise Sol environments and follow their storage, scratch-file, and job-management practices.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/shu-wan/solx/sol-skill
Any agent
npx skills add Shu-Wan/solx --skill sol-skill
Clone the repo
git clone --depth 1 https://github.com/Shu-Wan/solx

Made for: Claude Code, 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 sol-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/shu-wan/solx/sol-skill.svg)](https://agentmods.dev/skills/shu-wan/solx/sol-skill)
Your own site
<a href="https://agentmods.dev/skills/shu-wan/solx/sol-skill"><img src="https://agentmods.dev/badge/skills/shu-wan/solx/sol-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 266 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,623 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
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 $0.00266 $0.09623
Opus 5 $0.00133 $0.04811
Sonnet 5 $0.00053 $0.01925
Haiku 4.5 $0.00027 $0.00962

Measured 4d ago against content hash 58b19da9de0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

sol-skill scanned grade B with 2 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 4d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

description: Conventions and tooling for ASU's Sol supercomputer, built around the `solx` CLI. Use whenever a task is happening on Sol - the user mentions Sol or ASU Research Computing, or is clearly on their Sol account

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fLo ~/.local/bin/solx https://github.com/Shu-Wan/solx/releases/latest/download/solx-x86_64-unknown-linux-musl
skills/sol-skill/SKILL.md · 698 lines

How it starts

The opening of the file, as written. The whole thing — 698 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🌵 Sol skills

Official doc: https://docs.rc.asu.edu/.

That official doc is authoritative; these notes are just a cache.

What this skill helps with

This skill teaches an AI coding assistant how to operate on ASU's Sol supercomputer the way a careful human user would. The everyday job and scratch operations are driven through solx, a small CLI this skill installs and prefers; the rest is situational guidance for Sol's native tools. Concretely, it covers:

  • Driving solx - the CLI for daily Sol work: request and manage interactive allocations (solx job start/list/jump/time/stop) and renew flagged /scratch files (solx keep). The skill installs it on first use and prefers it.
  • Detecting the environment - recognizing whether the agent is running on a Sol login/compute node or on a laptop, and branching behavior accordingly.
  • Storage decisions - putting datasets, model weights, and caches under /scratch/$USER and keeping /home for config; never asking for sudo.
  • Scratch retention - refreshing files Sol has flagged for deletion with solx keep, driven by Sol's own warning CSVs and a [keep] block in the solx config; refusing to bulk-touch /scratch.
  • Getting software onto Sol without sudo - module load for what the cluster already provides, uv for Python interpreters and envs, R's tinytex for LaTeX, ~/.local/~/opt for everything else.
  • SLURM jobs - interactive allocations through solx job; batch jobs through sbatch with correct partition/QOS/time headers and Sol's prebuilt SBATCH templates.
  • Situation-aware job management - checking fairshare before submitting (and backing off when it's low), and tracking the wall-time left on the current allocation so work is wrapped up or handed off before Slurm reclaims the node.
  • Status queries about you and your jobs - translating "what's queued?", "what's my fairshare?", "what accounts can I use?", "why is my job pending?" into the right Sol wrapper or SLURM call.
  • Reaching a Sol-side service from a laptop - Open OnDemand vs. the manual ssh -L ... -J ... chain for Jupyter / dev servers / OAuth callbacks. (solx is Sol-only, so this stays manual - compute nodes aren't internet-reachable, so the SSH chain has to ProxyJump (-J) through the login node.)
  • File sharing - the chmod/install/cp dance to share files between Sol users via /scratch.
  • Data transfer - rsync/scp between laptop and Sol.
  • VS Code - auto-activating shell environments via terminal.integrated.env.linux.

Read the full file on GitHub · 698 lines

Files

What ships with it

7 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.

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. 4d ago First seen · 698 lines · 266 tokens per session scan B 58b19da9de0d

Subscribe to this mod's changes

sol-skill is a skill published in the GitHub repository Shu-Wan/solx (3 stars, last pushed 6d ago), licensed MIT. It adds 266 tokens to every session and 9,623 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

latex-posters

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

K-Dense-AI/claude-scientific-writer · 60 tokens

scientific-slides

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…

K-Dense-AI/claude-scientific-writer · 65 tokens

peer-review

Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Use for authorized review of scientific manuscripts, protocols, preprints, or research proposals; reporting-guideline selection; claim–evidence checks; methods, statistics, reproducibility, ethics, figure/table, and…

K-Dense-AI/claude-scientific-writer · 66 tokens

research-lookup

Compile current scholarly evidence for a scientific manuscript or research brief. Use when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source verification, Parallel Research…

K-Dense-AI/claude-scientific-writer · 82 tokens

scientific-writing

Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when…

K-Dense-AI/claude-scientific-writer · 60 tokens

scientific-critical-thinking

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…

K-Dense-AI/claude-scientific-writer · 63 tokens