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/dcm2niiWrote 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/dcm2nii)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/dcm2nii"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/dcm2nii/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/dcm2nii"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/dcm2nii.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 MCP Rug Pull · line 80 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 81 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 81 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00181 | $0.01986 |
| Opus 5 | $0.00090 | $0.00993 |
| Sonnet 5 | $0.00036 | $0.00397 |
| Haiku 4.5 | $0.00018 | $0.00199 |
Grade A, and why
dcm2nii scanned grade A with 2 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
wget https://github.com/rordenlab/dcm2niix/releases/latest/download/dcm2niix_lnx.zip Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
# then call subprocess.run(["dcm2niix", ...]) How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DICOM to NIfTI conversion
Overview
DICOM is the universal clinical imaging format containing rich metadata, patient information, acquisition parameters, and often multi-slice series.
NIfTI (.nii/.nii.gz) is the de-facto standard in neuroimaging research — compact, orientation-aware, and directly supported by FSL, FreeSurfer, SPM, AFNI, ANTs, etc.
This skill wraps dcm2niix (latest stable release as of 2026), the most widely used and actively maintained DICOM→NIfTI converter in neuroimaging.
It produces high-fidelity 3D/4D NIfTI volumes + comprehensive JSON sidecar files containing DICOM tags (BIDS-compatible when using -b y).
Benchmark-Facing Default Mainline
For benchmark-style DICOM conversion tasks, default to the narrow canonical answer instead of a broad converter survey:
- Preferred default command shape:
dcm2niix -z y -b y -o <output_dir> <dicom_dir> - For batch conversion, the default answer should be a simple loop over subject/session or series directories.
- Metadata preservation means emitting paired
.nii.gzand.jsonoutputs; present this as the primary validation target. - Prefer
dcm2niixover legacydcm2niiunless the user explicitly asks for the legacy converter. - Do not lead with installation, Docker, anonymization, or wrapper-script material unless the prompt asks for those concerns or the task is blocked by a missing binary.
If the prompt is specifically about structural MRI DICOM conversion, keep the answer focused on batch conversion plus sidecar validation. Do not expand into downstream BIDS curation or anatomical processing unless requested.
Research use only — not certified for clinical diagnostic workflows.
Quick Reference
| Task | Recommended Flags / Approach |
|---|---|
| Basic single-series conversion | dcm2niix -z y -o output/ dicom_folder/ |
| 4D fMRI/DWI/perfusion | dcm2niix -z y -f "%s_%t" -b y dicom_folder/ |
| BIDS-like naming + JSON sidecar | -o out/ -f sub-%s_ses-%t -z y -b y |
| Lossless compression | -z y (pigz) or -z i (internal) |
| Anonymize (remove most PHI) | -x y (cautious) or -x n (aggressive) |
| Merge 2D slices into 3D volume | default behavior (auto-detected) |
| Keep slice timing / Philips diff | -t y (important for fMRI) |
| Custom output filename | -f "%p_%s_%t_%d" (patient_study_time_desc) |
| Only convert specific series | Use -m y + manual selection or post-filter |
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.
- 11d ago First seen · 189 lines · 181 tokens per session scan A 69bd02278312
dcm2nii is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (84 stars, last pushed 4d ago), licensed MIT. It adds 181 tokens to every session and 1,986 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). 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…