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 rawwerks/VibeCAD --skill model-comparegit clone --depth 1 https://github.com/rawwerks/VibeCADWrote 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/rawwerks/vibecad/model-compare)<a href="https://agentmods.dev/skills/rawwerks/vibecad/model-compare"><img src="https://agentmods.dev/badge/skills/rawwerks/vibecad/model-compare.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.01438 |
| Opus 5 | $0.00044 | $0.00719 |
| Sonnet 5 | $0.00018 | $0.00288 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
model-compare 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 8d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D Model Comparison Tool
Compare CAD models using boolean operations to compute similarity metrics like IoU, Dice, precision, and recall. Useful for:
- Evaluating ML-generated models against gold references
- Comparing revisions of CAD designs
- Computing metrics for training 3D generative models
- Visualizing geometric differences
Quick Start
# Compare two STEP files
uvx --from build123d python scripts/model_diff.py reference.step generated.step
# JSON output for training pipelines
uvx --from build123d python scripts/model_diff.py ref.step gen.step --json --no-export
# Demo mode (no files needed)
uvx --from build123d python scripts/model_diff.py --demo
Supported Formats
| Format | Extension | Notes |
|---|---|---|
| STEP | .step, .stp |
Recommended - full CAD fidelity |
| BREP | .brep |
OpenCASCADE native format |
| STL | .stl |
Mesh format - may have boolean issues |
Output Metrics
Primary Metrics (for ML training)
| Metric | Range | Description |
|---|---|---|
| IoU (Jaccard) | 0-1 | ` |
| Dice (F1) | 0-1 | `2 |
| Precision | 0-1 | ` |
| Recall | 0-1 | ` |
Diagnostic Metrics
| Metric | Description |
|---|---|
volume_ratio |
B/A volume ratio (1.0 = same size) |
center_offset |
Distance between centers of mass |
bbox_iou |
Bounding box IoU (coarse alignment) |
size_ratio_x/y/z |
Per-axis scale comparison |
surface_ratio |
Surface area comparison |
Interpretation
The tool provides automatic interpretation:
- Over-generating: Low precision, high extra geometry
- Under-generating: Low recall, missing geometry
- Size issues: Volume ratio far from 1.0
- Position issues: Large center offset
CLI Options
usage: model_diff.py [-h] [-o OUTPUT_DIR] [--json] [--no-export] [--demo]
[reference] [generated]
positional arguments:
reference Reference/gold model file (STEP, BREP, or STL)
generated Generated/predicted model file to compare
options:
-o, --output-dir Output directory for GLB files (default: .)
--json Output only JSON metrics (for pipelines)
--no-export Skip exporting GLB visualization files
--demo Run with built-in demo models
What ships with it
1 file 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.
- 8d ago First seen · 161 lines · 0 tokens per session scan A 6dab1b37e573
model-compare is a skill published in the GitHub repository rawwerks/VibeCAD (117 stars, last pushed 8mo ago), licensed MIT. It adds 89 tokens to every session and 1,438 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.
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…