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 dmt-har-med-skillgit 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/dmt-har-med-skill)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/dmt-har-med-skill"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/dmt-har-med-skill/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/dmt-har-med-skill"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/dmt-har-med-skill.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 | $0.00123 | $0.01838 |
| Opus 5 | $0.00062 | $0.00919 |
| Sonnet 5 | $0.00025 | $0.00368 |
| Haiku 4.5 | $0.00012 | $0.00184 |
Grade A, and why
dmt-har-med-skill 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.
DMT-HAR-MED Skill (Dataset-Orchestration Layer)
Overview
dmt-har-med-skill is the NeuroClaw orchestration skill for the DMT-HAR-MED dataset (OpenNeuro ds006644).
DMT-HAR-MED contains rs-fMRI data from 40 participants in a psychedelic intervention study investigating the effects of N,N-Dimethyltryptamine (DMT) on brain function. The dataset includes multiple experimental conditions (DMT, placebo) and behavioral/physiological measurements.
It coordinates a fixed three-phase workflow:
- Download DMT-HAR-MED data from OpenNeuro.
- Prepare and validate BIDS-style data organization.
- Delegate fMRI processing to
fmri-skill.
It also provides phenotype extraction and QC integration paths:
- Extract DMT-HAR-MED phenotype data (intervention conditions, behavioral measures).
- Generate per-subject QC summaries with exclusion lists.
This skill follows NeuroClaw hierarchy:
- Defines WHAT to do, not low-level implementation details.
- Does not execute direct shell commands itself.
- Delegates all execution via
claw-shellto base/tool skills.
Research use only.
Download Stage (Mandatory First Step)
Source
DMT-HAR-MED data is available on OpenNeuro:
Supported DMT-HAR-MED Data Packages
- Imaging data: rs-fMRI (NIfTI format)
- Phenotype data: intervention conditions, behavioral and physiological measurements
- Participants: 40 participants with psychedelic intervention
Delegation Rules for Download
- Environment/setup checks:
dependency-planner+conda-env-manager - OpenNeuro dataset download:
claw-shell(viaopenneuroCLI ordatalad) - Optional raw-data organization to BIDS-style staging:
bids-organizer
Download Inputs to Confirm in Plan
- Subject list scope (full or custom subset)
- Destination directory with sufficient disk space
Core Workflow (Never Bypassed)
- Identify user target: download, BIDS staging, or full preprocessing.
- Generate a numbered plan with tools, outputs, runtime, storage, and risks.
- Wait for explicit confirmation (
YES/execute/proceed). - On confirmation, run download stage first (if needed).
- After download success, verify/prepare BIDS staging using
scripts/reorganize_dmt_har_med.py. - Delegate to
fmri-skillfor rs-fMRI processing. - If phenotype extraction is requested, run
scripts/extract_dmt_har_med_phenotype.py. - If QC summary is requested, run
scripts/dmt_har_med_qc_summary.py. - Save outputs into a DMT-HAR-MED-centered structure under
dmt_har_med_output/.
What ships with it
3 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.
- 12d ago First seen · 184 lines · 123 tokens per session scan A e09cee09526b
dmt-har-med-skill is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (84 stars, last pushed 5d ago), licensed MIT. It adds 123 tokens to every session and 1,838 once invoked, about $0.0006 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…