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 TianchenGuan/duke-cs-cluster-skill --skill check-availabilitygit clone --depth 1 https://github.com/TianchenGuan/duke-cs-cluster-skillWrote 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/tianchenguan/duke-cs-cluster-skill/check-availability)<a href="https://agentmods.dev/skills/tianchenguan/duke-cs-cluster-skill/check-availability"><img src="https://agentmods.dev/badge/skills/tianchenguan/duke-cs-cluster-skill/check-availability/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/tianchenguan/duke-cs-cluster-skill/check-availability"><img src="https://agentmods.dev/badge/skills/tianchenguan/duke-cs-cluster-skill/check-availability.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 | $0.00086 | $0.01007 |
| Opus 5 | $0.00043 | $0.00504 |
| Sonnet 5 | $0.00017 | $0.00201 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
check-availability 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Duke CS Cluster Availability
When invoked, produce a nicely formatted summary of current cluster state to help the user decide where to submit their next job.
Behavior
If no GPU type was specified: give an overall snapshot.
- Run
bash ~/.claude/skills/duke-cluster/scripts/check_cluster_load.shto get the one-liner summary. - Also run
sinfo -p compsci-gpu -o '%G %D %t'to get per-GPU-type idle counts. - Format into a single table showing each GPU type, total count, idle count, and a qualitative label ("free", "busy", "full").
If a specific GPU type was specified: drill down on that type.
- Run
bash ~/.claude/skills/duke-cluster/scripts/check_gpu_contention.sh <type>. - Optionally run
bash ~/.claude/skills/duke-cluster/scripts/estimate_wait.sh <type> 1to get a Slurm start estimate for a single-GPU placeholder. - Format the output into three sections: summary line, table of currently-running jobs on those nodes (job ID, user, GPUs, elapsed, remaining), and the Slurm start estimate.
Output format
Use markdown tables. Keep the response scannable — a user running this before submitting a job wants the answer in 2 seconds, not a paragraph.
For the overall snapshot, target this shape:
| GPU type | Idle / Total | Status |
|---|---|---|
| a5000 | 18 / 124 | Mostly free |
| a6000 | 0 / 16 | Full |
| rtx_pro_6000 | 0 / 20 | Full |
| v100 | 3 / 5 | Mostly free |
| p100 | 8 / 25 | Free |
| rtx_2080 | 12 / 22 | Free |
| rtx_5000 | 2 / 5 | Mixed |
Add a one-sentence verdict underneath. Examples: "A5000 pool is healthy — submit and expect to start in seconds." / "A6000 and RTX Pro 6000 are fully allocated — consider A5000 or V100 instead."
For a specific GPU type, target:
A6000 (fitz-[05-08]) — 0 of 16 GPUs idle, 4 users running jobs.
Job ID User CPUs GPUs Elapsed Remaining Name 1234567 alice 32 gpu:a6000:4 2h 34m 5h 26m finetune ... Slurm's start estimate for a new 1x A6000 job: 2026-04-13T18:23:00 (about 4 hours from now).
Verdict: long wait expected. If your job is less than 48GB VRAM, consider A5000 instead.
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 · 74 lines · 86 tokens per session scan A 17ecd5ee9151
check-availability is a skill published in the GitHub repository TianchenGuan/duke-cs-cluster-skill (6 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 1,007 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…
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.
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…
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…