cluster-screening

cluster-screening is a skill for Claude Code from mronkko/claude-academic-research. It costs 98 tokens per session (2,993 once invoked), scanned B, original, MIT.

A workflow for screening or coding research papers on a computing cluster, which is a shared group of powerful computers, instead of through an online language-model service. It creates requests, runs them through SLURM—a system for scheduling cluster jobs—and brings back the results.

In plain words
What is it for?
Preparing request files, submitting SLURM jobs, collecting screening or coding responses, and applying those responses to Zotero.
Why use it?
It handles the gap between a research tool and a cluster it cannot directly reach. It also applies the returned answers to Zotero, a reference-management program.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the academic-research plugin — 11 skills, 1 plugin shipped together

Good fit Preparing request files, submitting SLURM jobs, collecting screening or coding responses, and applying those responses to Zotero.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mronkko/claude-academic-research
Claude Code
/plugin install academic-research

Made for: Claude Code.

Or install academic-research, the plugin that ships this one along with the rest of its 11 skills, 1 plugin.

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 cluster-screening

README.md
[![agentmods](https://agentmods.dev/badge/skills/mronkko/claude-academic-research/cluster-screening/github.svg)](https://agentmods.dev/skills/mronkko/claude-academic-research/cluster-screening)
Your own site
<a href="https://agentmods.dev/skills/mronkko/claude-academic-research/cluster-screening"><img src="https://agentmods.dev/badge/skills/mronkko/claude-academic-research/cluster-screening/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 cluster-screening

Your own site · 80×15
<a href="https://agentmods.dev/skills/mronkko/claude-academic-research/cluster-screening"><img src="https://agentmods.dev/badge/skills/mronkko/claude-academic-research/cluster-screening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,993 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00098 $0.02993
Opus 5 $0.00049 $0.01496
Sonnet 5 $0.00020 $0.00599
Haiku 4.5 $0.00010 $0.00299

Measured 10d ago against content hash 12dc4b1663fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

cluster-screening scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

allow_rules: Bash(ssh:*) (~/.claude/settings.local.json)
skills/cluster-screening/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cluster-screening

Glossary: unfamiliar with PRISMA, MCP, BBT, stage tag, or DOI? See skills/_glossary.md.

This skill covers one thing: running the screening or coding LLM pass somewhere the plugin cannot reach, and bringing the answers back. Everything before it (search, import, enrichment, the screening protocol) and everything after it (audit, export, the manuscript) is systematic-review's. Load that skill for those; load this one for the round trip.

Pre-flight (ALWAYS run first, both of them, in this order)

python3 "${CLAUDE_PLUGIN_ROOT:-.}/scripts/setup/check_configured.py"
python3 "${CLAUDE_PLUGIN_ROOT:-.}/scripts/setup/check_cluster_config.py"

If the first says NOT CONFIGURED, stop and hand off to /setup.

The second prints the automation level. Read the effective: line and obey it. The level is not yours to choose, raise, or work around. It is a statement about how much of a shared facility account — somebody else's allocation, on hardware the user is accountable for — the user has agreed to hand over. If the level blocks what you were asked to do, say so and print the commands; do not set a level to get past a permission prompt, and do not suggest --automation auto as a fix for one.

The block looks like this:

automation: confirm
source: config.toml [cluster] automation
effective: auto
allow_rules: Bash(ssh:*) (~/.claude/settings.local.json)
query_rules: none
settings_files: 2 read

automation: is what was asked for; effective: is what will actually happen; any NOTE: line explains a difference between them. Relay a NOTE: to the user in full. Both directions matter: confirm with an allow rule confirms nothing (usually one "don't ask again" click, long forgotten), and auto without one prompts on every call, which in a headless session reads as a hang.

To change it, the user decides and this writes it:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/setup/set_cluster_automation.py <level>

Read the full file on GitHub · 277 lines

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 · 277 lines · 98 tokens per session scan B 12dc4b1663fc

Subscribe to this mod's changes

cluster-screening is a skill published in the GitHub repository mronkko/claude-academic-research (23 stars, last pushed 6d ago), licensed MIT. It adds 98 tokens to every session and 2,993 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens