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 ma-compbio-lab/SkillFoundry --skill slurm-job-debug-templategit clone --depth 1 https://github.com/ma-compbio-lab/SkillFoundryWrote 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/ma-compbio-lab/skillfoundry/slurm-job-debug-template)<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/slurm-job-debug-template"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/slurm-job-debug-template/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/ma-compbio-lab/skillfoundry/slurm-job-debug-template"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/slurm-job-debug-template.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 | $0.00031 | $0.00592 |
| Opus 5 | $0.00015 | $0.00296 |
| Sonnet 5 | $0.00006 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
slurm-job-debug-template 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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Generate a conservative sbatch template, submit it to Slurm, and capture the accounting record needed to verify the cluster path end to end.
When to use
- You need a tiny Slurm smoke job.
- You want a reusable starting point for queue, environment, and log validation.
When not to use
- You need multi-node or GPU tuning guidance beyond a first smoke job.
Inputs
- Command string
- Optional job name, partition, runtime, memory, and output path
Outputs
- Rendered
sbatchscript - JSON submission and
sacctsummary
Requirements
- Python 3.13+
sbatch,squeue, andsacct- A real Slurm cluster
Procedure
- Run
python3 skills/hpc/slurm-job-debug-template/scripts/render_sbatch.py --command "echo hello" --job-name smoke. - Inspect the generated script or save it with
--out. - Submit a verified smoke job with
python3 skills/hpc/slurm-job-debug-template/scripts/submit_smoke_job.py --partition cpu --job-name slurm-smoke --sleep 2 --out slurm/reports/slurm-smoke.json. - Inspect the returned
job_id, the log paths inslurm/logs/, and theaccountingblock fromsacct.
Validation
- Renderer exits successfully.
- Output contains
#SBATCHdirectives and the command body. - Submitted smoke job reaches
State=COMPLETED. ExitCodeis0:0.
Failure modes and fixes
- Missing partition/account information: add them before submission.
- Output paths wrong: switch to cluster-appropriate scratch or log paths.
sacctlags briefly after completion: retry once accounting catches up.
Safety and limits
- Keep resource requests small for initial smoke jobs.
- Use a CPU partition and a short walltime for smoke checks.
Examples
python3 .../render_sbatch.py --command "python analysis.py" --partition short --time 00:10:00 --mem 2Gpython3 .../submit_smoke_job.py --partition cpu --job-name slurm-smoke --sleep 1
Provenance
- Slurm quick start: https://slurm.schedmd.com/quickstart.html
- Slurm
sbatchreference: https://slurm.schedmd.com/sbatch.html sacctreference: https://slurm.schedmd.com/sacct.html
What ships with it
10 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.
- 5d ago First seen · 61 lines · 31 tokens per session scan A e2ab17070189
slurm-job-debug-template is a skill published in the GitHub repository ma-compbio-lab/SkillFoundry (38 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 592 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
academic-email
Professional academic email workflow (≤200 words). Invokes AcademicEmailAgent to draft a concise email with subject line and follow-up action for one of five standard email types: collaboration, question, interview, recommendation, or application. Output carries HUMAN REVIEW REQUIRED; no auto-send (§16.3).
arxiv-search
Skill "arxiv-search" from TaewoooPark/MagLab, covering category scoping, query families (3–6 per topic), version and doi resolution, tier classification and output contract.
cover-letter
Journal submission cover letter workflow (≤250 words). Invokes CoverLetterAgent to draft a concise novelty-focused cover letter from the author's key results. Output carries HUMAN REVIEW REQUIRED; no auto-send. All personal/institutional fields are marked [FILL] for the author to complete (§16.3).
revision-letter
Point-by-point peer-review response letter workflow for journal resubmission. Invokes RevisionLetterAgent to quote each reviewer comment verbatim, draft a response, and add a change-location marker. Outputs carry HUMAN REVIEW REQUIRED; no auto-send. A DOI or manuscript location is required for every factual response…
literature-review
Systematic literature review workflow — search → screening → quality assessment → topic-centred synthesis. Includes local-gap analysis. A DOI citation is required for every factual claim (§14.7). Activated by the maglab lit search command and the synthesis-editor agent.
literature-search
Broad literature search for magnetism & spintronics — OpenAlex REST query strategy, query family generation, tier classification, and evidencematrix construction (§14.3·§14.7). Activated by the maglab lit search command and the research orchestration search-scout agent.