combraintf

combraintf is a skill for Claude Code, Codex from CUHK-AIM-Group/NeuroClaw. It costs 85 tokens per session (2,137 once invoked), scanned A, original, MIT.

A research model for predicting traits from fMRI connectomes, which are maps of connections between brain regions. It uses a two-level Transformer to analyse groups of related brain regions.

In plain words
What is it for?
Use it in research workflows that provide dense fMRI connection matrices and need phenotype prediction. The implementation is for research use only.
Why use it?
It gives researchers a defined model for turning dense brain-connection matrices into phenotype predictions, along with attention and grouping outputs.

Skill for Claude CodeCodex

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

Good fit Use it in research workflows that provide dense fMRI connection matrices and need phenotype prediction. The implementation is for research use only.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/combraintf/github.svg)](https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/combraintf)
Your own site
<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/combraintf"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/combraintf/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 combraintf

Your own site · 80×15
<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/combraintf"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/combraintf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,137 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 138
    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 $0.00085 $0.02137
Opus 5 $0.00043 $0.01069
Sonnet 5 $0.00017 $0.00427
Haiku 4.5 $0.00009 $0.00214

Measured 9d ago against content hash d71e1fc10bd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

combraintf 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/combraintf/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Com-BrainTF Model Doc

Overview

Com-BrainTF (Community-aware Brain Transformer) 是一种针对 fMRI 连接组的两级 Transformer。第一级对每个脑功能社区(如 Yeo 7-network)内的 ROI 独立做 self-attention,并为每个社区维护一个可学习的 CLS token;第二级把所有社区的 CLS + 全部 ROI 节点拼接,再过一个带 DEC 池化的 Transformer,最后展平进 FC head。

  • Paper: Bannadabhavi et al., 2023, "Community-Aware Transformer for Autism Prediction in fMRI Connectome",MICCAI
  • Official code: https://github.com/ubc-tea/Com-BrainTF
  • NeuroClaw reimplementation: models/combraintf/(去除 hydra/omegaconf 与硬编码 node_clus_map,改为运行时从 atlas 推导)
  • Primary input: dense FC 矩阵 [B, N, N]
  • Primary output: phenotype prediction + DEC assignment + per-level attention

Research use only.


NeuroClaw 实现要点

  1. 去除 hydra/omegaconf:原版用 hydra 配置 + DictConfig,NeuroClaw 改为纯 Python 构造函数,所有参数显式传入。
  2. 动态 community partition:原版从 node_clus_map.pickle 加载 Schaefer-400 的固定社区映射;NeuroClaw 在 data_adapter.py::build_community_ids(atlas) 里根据 ROI 名自动推导:
    • schaefer_*_7net → Yeo 7-network(Vis/SomMot/DorsAttn/SalVentAttn/Limbic/Cont/Default)+ Unknown 兜底,共 8 组
    • aal_* / destrieux / dk_* / harvard_oxford_* → 7 lobe + Other = 8 组
    • 其他无语义命名的 atlas(cc200/glasser/basc/power/msdl)→ MD5 hash round-robin 8 组兜底
  3. 支持任意 atlas:上层只需传 community_ids: list[int](长度 = n_roi),模型自动按社区分组、独立 local transformer。
  4. 每社区独立 CLS token:与原版一致,每个社区一个 nn.Parameter([1, d_model]),由 local_transformers[k] 持有。
  5. 任务统一接口:classification (nclass=N) 与 regression (nclass=1, task='regression')。
  6. 数据复用:直接复用 BNT 的 BNTDataset + bnt_collate,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 BNT/BrainGNN 共享)

训练(分类,单 fold 冒烟测试)

python skills/combraintf/scripts/train_reference.py \
    --atlas schaefer_200_7net \
    --labels-csv data/hcp_gender_labels.csv \
    --fold 0 --n-epochs 10 --batch-size 8

训练(回归,HCP age)

python skills/combraintf/scripts/train_reference.py \
    --atlas aal_116 \
    --labels-csv data/hcp_age_labels.csv \
    --task regression --fold 0 --n-epochs 50

Read the full file on GitHub · 143 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 · 143 lines · 85 tokens per session scan A d71e1fc10bd5

Subscribe to this mod's changes

combraintf is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (83 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 2,137 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 2026-08-30.

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

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

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

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

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

aipoch/open-science · 83 tokens