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 Abhinavbwj/AEC-Scholar --skill aec-datasets-toolsgit clone --depth 1 https://github.com/Abhinavbwj/AEC-ScholarWrote 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/abhinavbwj/aec-scholar/aec-datasets-tools)<a href="https://agentmods.dev/skills/abhinavbwj/aec-scholar/aec-datasets-tools"><img src="https://agentmods.dev/badge/skills/abhinavbwj/aec-scholar/aec-datasets-tools/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/abhinavbwj/aec-scholar/aec-datasets-tools"><img src="https://agentmods.dev/badge/skills/abhinavbwj/aec-scholar/aec-datasets-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00110 | $0.01535 |
| Opus 5 | $0.00055 | $0.00767 |
| Sonnet 5 | $0.00022 | $0.00307 |
| Haiku 4.5 | $0.00011 | $0.00153 |
Grade A, and why
aec-datasets-tools 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 10d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AEC Research Datasets & Tools — Reference
Point researchers to credible tools and (where they exist) open datasets/benchmarks, and remind them to cite software and data (version + DOI) and to verify licenses and current availability before use.
1. Building energy & performance
- EnergyPlus (DOE) — whole-building energy simulation (the research standard); OpenStudio SDK/GUI;
EnergyPlus + Python (eppy, pyenergyplus),
besos,eppyfor parametric runs. - Modelica ecosystem — Buildings library (LBNL), Spawn-of-EnergyPlus, Dymola/OpenModelica.
- Ladybug Tools (Ladybug/Honeybee/Butterfly) in Grasshopper — daylight (Radiance), energy, CFD.
- Radiance — daylight/glare; CONTAM — airflow/IAQ; OpenFOAM — CFD (ventilation, urban microclimate).
- TRNSYS, IDA ICE, IES-VE, DesignBuilder — common (mostly commercial) BES tools.
- Weather data: EnergyPlus/EPW files (climate.onebuilding.org), TMY3; UBEM: UMI, CityEnergyAnalyst (CEA).
- Open datasets/benchmarks: ASHRAE Great Energy Predictor III (Kaggle), Building Data Genome Project 1/2, the DOE Commercial/Residential Prototype Building Models, and NREL ResStock/ComStock (verify current terms).
2. BIM / openBIM / interoperability
- IfcOpenShell (Python/C++) — parse, query, geometry from IFC; BlenderBIM/Bonsai — open BIM authoring.
- xBIM Toolkit (.NET), IFC.js / web-ifc / That Open Engine — IFC in the browser.
- Speckle — open data hub / interoperability across AEC tools; Solibri — model checking (commercial).
- buildingSMART resources: IFC schema, IDS samples, bSDD; Linked Building Data: IFCtoLBD, BOT ontology.
- Datasets: IFC sample files (buildingSMART, KIT IFC examples). Curated open BIM datasets are scarce — note this limitation; many studies build their own.
3. Computer vision, point clouds & ML in construction
- Point clouds: PDAL, Open3D, CloudCompare, PCL; photogrammetry/SLAM: COLMAP, Meshroom.
- Benchmarks/datasets: S3DIS, ScanNet, Semantic3D, KITTI (general 3D/segmentation); construction- specific: SODA / MOCS / ACID (site object/worker detection), Structured3D, building-defect crack datasets (e.g. SDNET2018, METU concrete crack) — verify licenses & current links, and report dataset size/splits honestly (AEC ML datasets are often small/narrow).
- ML frameworks: PyTorch, TensorFlow/Keras, scikit-learn, Ultralytics YOLO; GNN: PyTorch Geometric/DGL.
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.
- 10d ago First seen · 80 lines · 110 tokens per session scan A 8d13376c685e
aec-datasets-tools is a skill published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 1,535 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…