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 uchicago-dsi/ai-sci-skills --skill slurmgit clone --depth 1 https://github.com/uchicago-dsi/ai-sci-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/uchicago-dsi/ai-sci-skills/slurm)<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/slurm"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/slurm/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/uchicago-dsi/ai-sci-skills/slurm"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/slurm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.01770 |
| Opus 5 | $0.00026 | $0.00885 |
| Sonnet 5 | $0.00010 | $0.00354 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
slurm 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slurm
Use It As A Platform Skill
- Assume repo and workspace policy has already been loaded into context.
- Honor the active authorization, quota, logging, and handoff rules for the current workspace.
- Keep heavy compute off the headnode. Inspect files, edit code, and submit or monitor jobs from the headnode; run real compute on Slurm nodes only.
- Compose this skill with repo or experiment skills. Let them define intent; use this skill for scheduler choices and failure triage.
Use This Decision Ladder
- Discover the project’s environment and command convention from local policy and existing launchers.
- Prefer the repo-native launcher, such as a checked-in workflow command, submission entrypoint, or scheduler wrapper.
- If cluster policy matters and no trustworthy local note exists, do a light bootstrap of the site facts.
- If QoS or partition policy matters, inspect the live scheduler limits instead of relying on memory.
- If no higher-level launcher exists, use the checked-in
sbatchscript or wrapper. - Classify the issue as scheduler-only or runtime-related before changing code or resubmitting.
- Report job IDs, states, reasons, and evidence paths precisely.
Bootstrap Site Facts Lightly
- Shared skills should stay generic. Do not edit the shared skill just because one cluster has special queues or limits.
- If
docs/slurm-site.mdexists, read it first. - Do not load
references/bootstrap.mdunless one of these is true:docs/slurm-site.mdis missingdocs/slurm-site.mdis missing required fields needed for the current task- live scheduler commands contradict
docs/slurm-site.md
- If local Slurm facts matter and are not already documented nearby, inspect them once, record the durable findings in project-local notes or policy, and reuse that note until contradicted.
- Write the local site note to
docs/slurm-site.md. - Required fields for
docs/slurm-site.mdare:- default account
- default partition
- preemptible or overflow QoS, if any
- when to use that QoS
- important limits
- native launcher
- environment convention
- Refresh the local note only when:
- commands contradict it
- admins changed cluster policy
- a new project uses different launch conventions
What ships with it
3 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.
- 10d ago First seen · 131 lines · 51 tokens per session scan A 37cf7dc36169
slurm is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (17 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,770 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…