lggnn

lggnn is a skill for Claude Code, Codex from CUHK-AIM-Group/NeuroClaw. It costs 77 tokens per session (1,802 once invoked), scanned A, original, MIT.

A graph neural network model for predicting traits or diagnosing disorders from brain graphs. Brain graphs represent brain regions as nodes and their connections as edges; this version uses attention-based pooling to select important regions.

In plain words
What is it for?
Use it with PyTorch Geometric brain graphs to predict categories or continuous outcomes and inspect which brain regions contribute to the result.
Why use it?
It provides a single-subject alternative to the original model's population-graph design and can handle both classification and numeric prediction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it with PyTorch Geometric brain graphs to predict categories or continuous outcomes and inspect which brain regions contribute to the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cuhk-aim-group/neuroclaw/lggnn
Install

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.

Any agent
npx skills add CUHK-AIM-Group/NeuroClaw --skill lggnn
Clone the repo
git clone --depth 1 https://github.com/CUHK-AIM-Group/NeuroClaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lggnn

README.md
[![agentmods](https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/lggnn/github.svg)](https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/lggnn)
Your own site
<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.

agentmods 80×15 button for lggnn

Your own site · 80×15
<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>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 83afaf08dc3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/data_adapter_reference.py, scripts/train_reference.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/lggnn/SKILL.md · 132 lines

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

  1. 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。
  2. 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)。
  3. PyG 2.7 兼容:原 torch_geometric.nn.pool.topk_pool 已重构,NeuroClaw 用 pool.select.topk + 内联 filter_adj
  4. 任务统一接口:classification (nclass=N) 与 regression (nclass=1, task='regression') 一套代码。
  5. 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)

Read the full file on GitHub · 132 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 132 lines · 77 tokens per session scan A 83afaf08dc3b

Subscribe to this mod's changes

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.

Related

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…

K-Dense-AI/scientific-agent-skills · 66 tokens

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…

K-Dense-AI/scientific-agent-skills · 216 tokens

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.

K-Dense-AI/scientific-agent-skills · 61 tokens

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…

K-Dense-AI/scientific-agent-skills · 80 tokens

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.

NVIDIA/skills · 56 tokens

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.

maziyarpanahi/openmed · 64 tokens