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 CUHK-AIM-Group/NeuroClaw --skill lggnngit clone --depth 1 https://github.com/CUHK-AIM-Group/NeuroClawWrote 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/lggnn)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/lggnn"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/lggnn/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/lggnn"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/lggnn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 127 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00077 | $0.01802 |
| Opus 5 | $0.00039 | $0.00901 |
| Sonnet 5 | $0.00015 | $0.00360 |
| Haiku 4.5 | $0.00008 | $0.00180 |
Grade A, and why
lggnn 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 9d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LG-GNN Model Doc
Overview
LG-GNN (Local-to-Global GNN) 是一种针对脑疾病诊断的两阶段图神经网络。原始论文使用 Local_GNN 提取每个被试的脑图嵌入,再通过基于人口学信息构建的 Global_GNN 进行人群图分类。NeuroClaw 改造为单被试任务:保留 Local_GNN(含 SABP + 互信息正则化的创新组件),用 MLP head 替代人口图。
- Paper: Zhang et al., 2022, "Local to Global Hierarchical Graph Neural Network for Brain Disorder Diagnosis",MICCAI
- Official code: https://github.com/cnuzh/LG-GNN
- NeuroClaw reimplementation:
models/lggnn/(去除人口图依赖,单被试 PyG 流程) - Primary input: PyG Data graph(与 BrainGNN 共享数据格式)
- Primary output: phenotype prediction + ROI 重要性(SABP perm)+ MI loss 辅助监督
Research use only.
NeuroClaw 实现要点
- 单被试改造:原版需要非影像表型数据构建人口图,NeuroClaw 仅保留 Local_GNN,用 MLP head 输出。
- SABP 池化:Self-Attention Brain Pooling,topk 选择 ROI + tanh(score) 加权,并产生互信息估计
mi作为辅助 loss(论文权重 0.1,loss 取loss - 0.1 * mi鼓励高互信息)。 - PyG 2.7 兼容:原
torch_geometric.nn.pool.topk_pool已重构,NeuroClaw 用pool.select.topk+ 内联filter_adj。 - 任务统一接口:classification (
nclass=N) 与 regression (nclass=1, task='regression') 一套代码。 - 数据复用:直接复用 BrainGNN 的
NeuroClawFCDataset,无需额外预处理。
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(与 BrainGNN 共享)
训练(分类,单 fold 冒烟测试)
python skills/lggnn/scripts/train_reference.py \
--atlas aal_116 \
--labels-csv data/hcp_gender_labels.csv \
--fold 0 --n-epochs 10 --batch-size 16
训练(回归,HCP age)
python skills/lggnn/scripts/train_reference.py \
--atlas schaefer_100_7net \
--labels-csv data/hcp_age_labels.csv \
--task regression --fold 0 --n-epochs 50
核心文件
| 文件 | 作用 |
|---|---|
models/lggnn/net/lggnn.py |
模型定义:LocalGNN (GCN×2 + SABP + GCN) + MLP head |
models/lggnn/scripts/data_adapter.py |
数据适配(薄封装复用 models.braingnn) |
skills/lggnn/scripts/train_reference.py |
K-fold CV 训练参考实现 |
模型架构
Input PyG Data (x=[N,N], edge_index, edge_attr, batch)
-> GCNConv(N, 64) + ReLU
-> GCNConv(64, 20) + ReLU
-> SABP pool (ratio=0.5): topk_score + tanh weighted; 产生 mi_estimate
-> GCNConv(20, 20) + ReLU
-> 残差: pooled + conv3
-> global_mean_pool
-> MLP head: Linear(20 -> 64) + ReLU + Dropout + Linear(64 -> nclass)
Output: (logits, mi_loss)
What ships with it
2 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.
- 9d ago First seen · 132 lines · 77 tokens per session scan A 83afaf08dc3b
lggnn is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (85 stars, last pushed 6d ago), licensed MIT. It adds 77 tokens to every session and 1,802 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 2026-09-03.
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.