Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CUHK-AIM-Group/NeuroClawnpx agentmods add skills/cuhk-aim-group/neuroclaw/brain_gnnWrote 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/cuhk-aim-group/neuroclaw/brain_gnn)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/brain_gnn"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/brain_gnn/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/cuhk-aim-group/neuroclaw/brain_gnn"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/brain_gnn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.01982 |
| Opus 5 | $0.00030 | $0.00991 |
| Sonnet 5 | $0.00012 | $0.00396 |
| Haiku 4.5 | $0.00006 | $0.00198 |
Grade A, and why
braingnn 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 12d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BrainGNN Model Doc
Overview
BrainGNN is an interpretable graph neural network for fMRI analysis and phenotype prediction.
- Paper: Li et al., 2020, BrainGNN
- Official code: https://github.com/xxlya/BrainGNN_Pytorch/tree/main
- NeuroClaw reimplementation:
models/braingnn/(Windows-compatible, 无需 torch_sparse) - Primary input: ROI-level fMRI connectivity matrices (per-subject .pt files)
- Primary output: phenotype prediction (classification/regression) + interpretable pooling scores
Research use only.
NeuroClaw 实现要点
NeuroClaw 版本对原始 BrainGNN 做了以下关键改动：
- 去除 torch_sparse 依赖：
augment_adj不再使用spspmm做邻接矩阵平方，改用add_self_loops + remove_self_loops，在 Windows 上可直接运行。 - 全连接输入图：data_adapter 构建 FULL graph（所有 i!=j 对），edge_attr = |Pearson r|。TopKPooling 负责选择，不在输入端做稀疏化。
- Fisher-z 反变换：存储的 fc_matrix 是 Fisher-z，加载时用
torch.tanh()还原为 Pearson r，对角线置零。 - 支持 classification + regression 双任务：通过
--task参数切换，regression 时 nclass=1，输出 raw scalar，用 MSELoss。 - PyG >=2.3 兼容：TopKPooling.weight 可能在
pool.select.weight，forward 中做了兼容处理。 - 可选 T1 GM volume 融合：
--include-t1将 z-scored GM volume 作为额外 1 维 node feature 拼接。
Quick Start (NeuroClaw 内部)
前置条件
- conda env:
neuroclaw(Python 3.11) - 已有
data/braingnn_input/<atlas>/sub-*.pt文件（由 fmri-skill 生成） - 可选：
data/t1_volume/<atlas>/sub-*.npz（GM volume）
训练（分类）
python models/braingnn/scripts/train.py \
--atlas schaefer_100_7net \
--labels-csv data/hcp_gender_labels.csv \
--subjects-file data/ready_subjects.txt \
--fold 0 --kfold 5 \
--n-epochs 50 --batch-size 16 --lr 0.005 \
--include-t1
训练（回归）
python models/braingnn/scripts/train.py \
--atlas aal_116 \
--labels-csv data/hcp_age_labels.csv \
--subject-col subject_id --label-col age \
--task regression --label-scaling standardization \
--fold 0 --n-epochs 50
Atlas Sweep（快速对比）
python models/braingnn/scripts/sweep_atlases.py
对所有可用 atlas 跑 fold 0，输出 CSV 对比表。
What ships with it
8 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.
- scripts/data_adapter_reference.py 3.3 KB runs code
- scripts/hypothesis_label_mapper.py 25 KB runs code
- scripts/region_roi_mapper.py 11 KB runs code
- scripts/run_atom_task_validation.py 13 KB runs code
- scripts/run_ibgnn_tune.py 12 KB runs code
- scripts/run_lifespan_age.py 26 KB runs code
- scripts/run_lifespan_new_models_search.py 8.0 KB runs code
- scripts/train_reference.py 7.0 KB runs code
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.
- 12d ago First seen · 184 lines · 61 tokens per session scan A 19a92bfd0459
braingnn is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (85 stars, last pushed 6d ago), licensed MIT. It adds 61 tokens to every session and 1,982 once invoked, about $0.0003 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
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.