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 Lzy599775/agent-auto-sci-skills --skill torch-geometricgit clone --depth 1 https://github.com/Lzy599775/agent-auto-sci-skillsWrote 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/lzy599775/agent-auto-sci-skills/torch-geometric)<a href="https://agentmods.dev/skills/lzy599775/agent-auto-sci-skills/torch-geometric"><img src="https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/torch-geometric/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/lzy599775/agent-auto-sci-skills/torch-geometric"><img src="https://agentmods.dev/badge/skills/lzy599775/agent-auto-sci-skills/torch-geometric.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 | $0.05610 |
| Opus 5.5 | $0.00028 | $0.02244 |
| Sonnet 5.5 | $0.00014 | $0.01122 |
| Haiku 4.5 | $0.00007 | $0.00561 |
Grade A, and why
torch-geometric 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 15d 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.
This is a copy
95% identical to torch-geometric — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyTorch Geometric (PyG)
PyG is the standard library for Graph Neural Networks built on PyTorch. It provides data structures for graphs, 60+ GNN layer implementations, scalable mini-batch training, and support for heterogeneous graphs.
Installation
Reviewed released torch-geometric 2.8.0.post1 (2026-10-01); CPU examples tested with Python 3.13 / PyTorch 2.14.1. Rolling latest docs identify 2.9.0; check the installed release before adopting new APIs. PyG 2.8 requires PyTorch 2.9+; its original release table covers 2.9–2.12. Our 2.14.1 core tests do not establish every extension/backend combination.
# Install the PyTorch build for your platform from https://pytorch.org/get-started/locally/
uv pip install torch==2.14.1
uv pip install torch-geometric==2.8.0.post1
python -c "import torch, torch_geometric; print(torch.__version__, torch.version.cuda, torch_geometric.__version__)"
Basic tensor-based layers need no extensions. Neighbor sampling requires pyg-lib or torch-sparse; spatial k-NN operators require pyg-lib in 2.8. torch-cluster and torch-spline-conv are deprecated and ignored. Inspect the wheel index for your exact Python/OS/Torch/CUDA tuple. Never install wheels for a different Torch release merely because core imports succeed. The tested macOS ARM CPU extension is below; choose a different matching wheel for other platforms, and verify its operators:
uv pip install --only-binary=:all: "pyg-lib==0.9.0+pt214" \
-f https://data.pyg.org/whl/torch-2.14.0+cpu.html
Conda packages are no longer provided for Torch >2.5. See installation and 2.8 release changes. Optional sampling/GPU/distributed/download examples below are illustrative unless covered by the CPU checks in review notes.
Core Concepts
Graph Data: Data and HeteroData
What ships with it
7 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.
- 15d ago Changed · +12 lines 89805e17cdbc
- 1mo ago Changed · +17 lines 3b6dd242f763
- 1mo ago First seen · 459 lines · 71 tokens per session scan A b6a1c0c48e4d
torch-geometric is a skill published in the GitHub repository Lzy599775/agent-auto-sci-skills (2 stars, last pushed 11d ago), licensed MIT. It adds 71 tokens to every session and 5,610 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to torch-geometric, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
code-execution
Execute scientific Python code for computation, data analysis, simulation, and verification. Use when: (1) running statistical analyses, (2) numerical computation, (3) data processing pipelines, (4) verifying calculations, (5) running simulations. NOT for: literature search (use literature-search), writing papers (use…
model-assessment
Use when validating or evaluating a trained medical-imaging model. Audits split leakage and validation design, computes task-correct held-out metrics (Dice + HD95, AUROC + AUPRC, FROC, calibration), and covers uncertainty/OOD and Grad-CAM explainability, each with a gate.
model-scaffold
Use when you need a runnable PyTorch training repo for a medical-imaging task (segmentation, classification, detection, synthesis, self-supervised, or fine-tuning a pretrained backbone). Emits a patient-level seed-locked split, train/evaluate scripts, config and a Methods stub.
radiomics-ml
Use when building or auditing a radiomics or tabular clinical-ML prediction model with a classical learner (LASSO, SVM, random forest, XGBoost and similar). Enforces nested CV, dimensionality control, in-fold feature selection, feature stability, calibration and external validation.
imaging-data
Use when preparing a medical-imaging dataset (DICOM/NIfTI) for modelling. Profiles spacing, orientation, intensity, label integrity, foreground fraction and target volume, gates them against the plan, then plans and audits preprocessing and augmentation for leakage.
model-selection
Use when choosing the model for a medical-imaging study. Picks a paper-grounded architecture family (CNN/ViT, U-Net/nnU-Net, detection, SAM/foundation, GNN), then vets the concrete repo or checkpoint for licence, version pin, weight provenance and benchmark overlap.