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 marcinfinitesimal533/Claude-skills-for-Computational-Designers --skill computational-geometrygit clone --depth 1 https://github.com/marcinfinitesimal533/Claude-skills-for-Computational-DesignersWrote 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/marcinfinitesimal533/claude-skills-for-computational-designers/computational-geometry)<a href="https://agentmods.dev/skills/marcinfinitesimal533/claude-skills-for-computational-designers/computational-geometry"><img src="https://agentmods.dev/badge/skills/marcinfinitesimal533/claude-skills-for-computational-designers/computational-geometry/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/marcinfinitesimal533/claude-skills-for-computational-designers/computational-geometry"><img src="https://agentmods.dev/badge/skills/marcinfinitesimal533/claude-skills-for-computational-designers/computational-geometry.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 | $0.00032 | $0.12521 |
| Opus 5 | $0.00016 | $0.06260 |
| Sonnet 5 | $0.00006 | $0.02504 |
| Haiku 4.5 | $0.00003 | $0.01252 |
Grade A, and why
computational-geometry 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 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.
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.
This is a copy
100% identical to computational-geometry — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 891 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computational Geometry for AEC
This skill encapsulates the full breadth of computational geometry knowledge required for architecture, engineering, and construction workflows. It covers fundamental primitives, advanced surface mathematics, mesh processing, tessellation strategies, point cloud pipelines, and the precise tolerance management that separates prototype-grade geometry from fabrication-ready output.
1. Geometry Type Hierarchy
Every computational design system is built on a layered hierarchy of geometric types. Understanding the properties, capabilities, and conversion paths of each type is essential for selecting the right representation at every stage of a project.
1.1 Points, Vectors, Planes, Frames
Point (Point3d)
- Definition: A dimensionless location in 3D Euclidean space defined by (x, y, z) coordinates.
- Properties: No length, area, or volume. Carries only positional information.
- AEC use cases: Survey control points, grid intersections, insertion points for components, structural node locations, sensor positions.
- Conversion: A point can seed any higher-order geometry. Points become curve control points, mesh vertices, or centroid markers.
Vector (Vector3d)
- Definition: A direction and magnitude in 3D space, defined by (x, y, z) components. Unlike a point, a vector has no fixed position.
- Properties: Magnitude (length), direction (unit vector). Supports dot product, cross product, angle computation, projection.
- AEC use cases: Wind direction encoding, structural force vectors, surface normals for solar analysis, movement direction for pedestrian simulation, facade orientation vectors.
- Key operations: Normalize, scale, add, subtract, dot product (scalar projection), cross product (perpendicular vector), angle between vectors, reflection, rotation.
Plane
- Definition: An infinite flat surface defined by an origin point and a normal vector, or equivalently by an origin and two in-plane axes (X-axis, Y-axis) with the normal as Z-axis.
- Properties: Origin, Normal, XAxis, YAxis. Divides space into two half-spaces.
- AEC use cases: Floor levels, section cut planes, mirror planes for symmetric designs, construction planes for drawing, reference datums.
- Conversion: Planes can generate planar surfaces, serve as projection targets, or define local coordinate systems.
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.
- 11d ago First seen · 891 lines · 32 tokens per session scan A eeecdc5769ca
computational-geometry is a skill published in the GitHub repository marcinfinitesimal533/Claude-skills-for-Computational-Designers (2 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 12,521 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to computational-geometry, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
computational-geometry
NURBS curves and surfaces, mesh geometry, boolean operations, subdivision surfaces, tessellation methods, surface analysis, and point cloud processing for AEC computational design.
kernelcad-trace-from-image
Convert pixel-space features from a reference photo into normalized [0,1] waypoints, then into mm coordinates feedable to path().spline / path().nurbsSegment. Uses the tracefromimage MCP tool. Load when your blockout is in place and the next step is an organic-curve outline (eyewear brow, ergonomic handle, sneaker…
mesh-processing
Mesh data structures, mesh operations, mesh analysis, mesh repair, UV mapping and unfolding, quad meshing, mesh-to-NURBS conversion, and mesh quality assessment for AEC computational design.
cd-calculator
Python calculators for geometry analysis, structural checking, solar calculations, panel optimization, mesh analysis, material estimation, and fabrication cost estimation for AEC computational design.
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and…
paper-poster-html
A workflow for building an academic conference poster as one HTML/CSS file and printing it to a PDF at an exact page size. It uses the paper’s real figures and checks layout details before review.