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 HCAI-Lab-GT/gt-hive --skill slurm-coregit clone --depth 1 https://github.com/HCAI-Lab-GT/gt-hiveWrote 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/hcai-lab-gt/gt-hive/slurm-core)<a href="https://agentmods.dev/skills/hcai-lab-gt/gt-hive/slurm-core"><img src="https://agentmods.dev/badge/skills/hcai-lab-gt/gt-hive/slurm-core/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/hcai-lab-gt/gt-hive/slurm-core"><img src="https://agentmods.dev/badge/skills/hcai-lab-gt/gt-hive/slurm-core.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 | $0.00071 | $0.02559 |
| Opus 5 | $0.00036 | $0.01280 |
| Sonnet 5 | $0.00014 | $0.00512 |
| Haiku 4.5 | $0.00007 | $0.00256 |
Grade A, and why
slurm-core 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 11d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slurm Core
This skill teaches a terminal AI assistant how to help with portable Slurm workflows without inventing site-local facts.
What this skill is for
Use this skill when the user needs help with:
- CPU, Python, or GPU batch scripts
sbatch,srun, orsalloc- job arrays
- dependency pipelines
- monitoring and debugging
- accounting and exit-code interpretation
- converting ad hoc shell loops into repeatable Slurm workflows
Before drafting anything, build context:
- Identify the task type (
job submission,resource selection,monitoring,troubleshooting). - Identify the workload profile (
CPU,GPU,MPI,array,interactive debugging,I/O-heavy). - State assumptions explicitly and continue unless cluster policy or data handling forces a clarifying question.
What this skill must not guess
Do not invent any of the following:
- cluster-specific
--account --partition--qos- module names
- filesystem paths
- conda environment names
- site policy
- GPU type names that the cluster may not actually provide
If a value is unknown, mark it VERIFY_ON_SITE and explain what local doc or command should confirm it. The literal string VERIFY_ON_SITE is the convention readers grep for: it tells humans "the AI refused to invent this — fill it in yourself before submitting." Use it everywhere a site-local fact would otherwise be hallucinated (for example --account=VERIFY_ON_SITE, module load VERIFY_ON_SITE).
For reader-supplied values that are not site-secret (a job name, a script path), use angle-bracket placeholders like <job_name> or <script.py>.
Operating principles
- Prefer long-form Slurm directives (
--cpus-per-task=4, not-c 4) so scripts read as teaching material. - Prefer explicit resource requests to implicit defaults.
- Keep explanations beginner-friendly but technically correct.
- Separate portable Slurm ideas from site-local details. Portable goes in this skill; site-local goes in the overlay.
- When the user is debugging, start from evidence rather than speculation.
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.
- 11d ago First seen · 222 lines · 71 tokens per session scan A bbae135ad870
slurm-core is a skill published in the GitHub repository HCAI-Lab-GT/gt-hive (4 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 2,559 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 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…