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/nilearn-toolWrote 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/nilearn-tool)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/nilearn-tool"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/nilearn-tool/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/nilearn-tool"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/nilearn-tool.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 | $0.00086 | $0.02725 |
| Opus 5 | $0.00043 | $0.01362 |
| Sonnet 5 | $0.00017 | $0.00545 |
| Haiku 4.5 | $0.00009 | $0.00272 |
Grade A, and why
nilearn-tool scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- No direct `subprocess.run()` for long operations in this skill. How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nilearn Tool (Base/Tool Layer)
Overview
nilearn-tool is the NeuroClaw base/tool skill that implements concrete Nilearn workflows for turning preprocessed BOLD into features (ROI time series, connectivity matrices, seed maps) and optional statistical modeling (GLM).
It is never called directly by the user. It is delegated to by fmri-skill (or other interface/modality skills) and executed via claw-shell.
Research use only.
Agent Reference Rule
When the agent needs Nilearn-based implementation code, it should first consult the curated snippets in skills/nilearn-tool/scripts/ instead of copying directly from long tutorial scripts with hard-coded paths.
Reference snippets available:
scripts/preprocess_bold_reference.py-> dummy removal, smoothing, band-pass filtering, MNI resamplingscripts/connectome_reference.py-> atlas ROI extraction and ROI-to-ROI connectivity exportscripts/zalff_summary_reference.py-> MNI resampling, zALFF summary, atlas-level regional exportscripts/task_glm_reference.py-> first-level task GLM with design matrix and contrast mapsscripts/second_level_glm_reference.py-> group-level GLM from subject contrast mapsscripts/rest_ica_reference.py-> resting-state CanICA component extractionscripts/rest_dictlearning_reference.py-> resting-state DictLearning component extractionscripts/svm_classifier_reference.py-> ROI/tabular disease classification with SVMscripts/spacenet_classifier_reference.py-> voxel-wise disease classification with SpaceNetscripts/kmeans_parcellation_reference.py-> mask-based K-means brain parcellationscripts/hierarchical_parcellation_reference.py-> mask-based hierarchical brain parcellationscripts/denoise_timeseries_reference.py-> confound regression and detrending withclean_img
Scope (What this tool does / does not do)
✅ This tool does
- Load BOLD NIfTI and (optional) brain mask.
- Load fMRIPrep confounds TSV and apply common denoising regressors.
- Extract ROI time series from an atlas/parcellation.
- Compute ROI-to-ROI functional connectivity matrices.
- Compute seed-to-voxel connectivity maps.
- (Optional) Run first-/second-level GLM when events/maps are provided.
What ships with it
12 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/connectome_reference.py 2.3 KB runs code
- scripts/denoise_timeseries_reference.py 2.0 KB runs code
- scripts/hierarchical_parcellation_reference.py 2.2 KB runs code
- scripts/kmeans_parcellation_reference.py 2.1 KB runs code
- scripts/preprocess_bold_reference.py 2.8 KB runs code
- scripts/rest_dictlearning_reference.py 2.0 KB runs code
- scripts/rest_ica_reference.py 2.1 KB runs code
- scripts/second_level_glm_reference.py 2.2 KB runs code
- scripts/spacenet_classifier_reference.py 2.1 KB runs code
- scripts/svm_classifier_reference.py 2.4 KB runs code
- scripts/task_glm_reference.py 2.5 KB runs code
- scripts/zalff_summary_reference.py 3.9 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.
- 9d ago First seen · 266 lines · 86 tokens per session scan A 74b02eed6972
nilearn-tool is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (85 stars, last pushed 6d ago), licensed MIT. It adds 86 tokens to every session and 2,725 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.