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 aristoteleo/PantheonOS --skill gene_panel_selectiongit clone --depth 1 https://github.com/aristoteleo/PantheonOSWrote 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/aristoteleo/pantheonos/gene_panel_selection)<a href="https://agentmods.dev/skills/aristoteleo/pantheonos/gene_panel_selection"><img src="https://agentmods.dev/badge/skills/aristoteleo/pantheonos/gene_panel_selection/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/aristoteleo/pantheonos/gene_panel_selection"><img src="https://agentmods.dev/badge/skills/aristoteleo/pantheonos/gene_panel_selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 4 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00110 | $0.06961 |
| Opus 5 | $0.00055 | $0.03481 |
| Sonnet 5 | $0.00022 | $0.01392 |
| Haiku 4.5 | $0.00011 | $0.00696 |
Grade A, and why
Gene Panel Selection Workflow 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 — 673 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gene Panel Selection Workflow
This skill is used when you need to construct biologically meaningful and algorithmically robust gene panels. You will receive context from the leaderagent , use this context and STRICLTY follow this Gene Panel Selection Workflow
Workflow Enforcement (MANDATORY)
Determine which stage of the workflow (Steps 1–5) is required for the current task, and STRICTLY follow the corresponding step(s).
Once a step is entered, all its mandatory sub-steps must be executed. No partial execution or silent degradation is allowed.
Workdir
Always work in the workdir provided by the leader agent.
Calling other agents
You can call other agents by using the call_agent(agent_name, instruction) function.
-
Call the
browser_useagent for information collection: When you encounter software or biological knowledge you are not familiar with, callbrowser_useto search the web and collect the necessary information. -
Call the
system_manageragent for software environment installation: When you need to install software packages, callsystem_managerto install them. -
Call the
biologistagent for results interpretation: When you plot figures, compute a panel, or have intermediate results, callbiologistto ask for interpretations and include them in your report. -
Call the
reporteragent when all the results are obtained, to make a well written pdf.
Visual understanding
Use the observe_images function in the file_manager toolset to examine images and figures.
If a figure is not publication-quality, replot it.
Reporting
At the end of the task, write a markdown report named:
report_analysis.md
The report must include:
- Summary
- Data (inputs, key parameters, outputs)
- Results (figures + tables)
- Key findings
- Next steps
Large datasets
If the dataset is large, perform smart downsampling while preserving all cell types.
Gene Panel Selection Hyperparameters
What ships with it
1 file 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 · 673 lines · 110 tokens per session scan A 46c91091162e
Gene Panel Selection Workflow is a skill published in the GitHub repository aristoteleo/PantheonOS (485 stars, last pushed today), licensed BSD-2-Clause. It adds 110 tokens to every session and 6,961 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
histolab
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.