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 w1ne/kernelCAD-web --skill kernelcad-sdformatgit clone --depth 1 https://github.com/w1ne/kernelCAD-webWrote 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/w1ne/kernelcad-web/kernelcad-sdformat)<a href="https://agentmods.dev/skills/w1ne/kernelcad-web/kernelcad-sdformat"><img src="https://agentmods.dev/badge/skills/w1ne/kernelcad-web/kernelcad-sdformat/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/w1ne/kernelcad-web/kernelcad-sdformat"><img src="https://agentmods.dev/badge/skills/w1ne/kernelcad-web/kernelcad-sdformat.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 | $0.00064 | $0.02187 |
| Opus 5.5 | $0.00026 | $0.00875 |
| Sonnet 5.5 | $0.00013 | $0.00437 |
| Haiku 4.5 | $0.00006 | $0.00219 |
Grade A, and why
kernelcad-sdformat 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kernelCAD — SDFormat export
SDFormat is an XML model description that, unlike URDF, accepts closed kinematic loops natively and exposes a native ball-joint type. kernelCAD's export({ target: 'model', format: 'sdf-gazebo' }) writes a .sdf (spec version 1.10 — parsed by current simulator LTS releases) plus a sibling meshes/ directory with one STL per link. Ship the whole directory: the SDF references meshes/<part>.stl by relative URI, resolved against the .sdf file location, so the export loads in gz sim with no resource-path environment setup.
When to use over URDF
Pick SDFormat when:
- The assembly has a closed kinematic loop (4-bar linkages, parallel grippers, scissor mechanisms). URDF refuses these; SDFormat accepts.
- The assembly uses a ball mate. URDF must decompose into a 3-revolute chain; SDFormat emits one native
<joint type="ball">. - The downstream simulator accepts SDFormat directly.
Otherwise prefer URDF — wider tool ecosystem.
What the emitter writes (verified against gz-sim)
- Per-link
<pose>from the solved mate graph. The exporter runs the mate solver at the default pose and stamps each link's world transform, so links spawn assembled instead of stacked at the model origin. If the mate graph cannot be solved, the export still succeeds but emitsexport.sdf-gazebo.pose-unsolved(warn) and identity poses — fix the geometry before shipping to a simulator. - Joint
<pose>relative to the CHILD link frame (the SDFormat convention), i.e. the child-side connector origin;<axis><xyz>is the child-side connector axis expressed in the joint frame. - Mesh
<scale>0.001 0.001 0.001</scale>on every visual/collision: link STLs are kernelCAD-native mm, SDFormat consumes metres, and the scale keeps geometry consistent with the (already-SI) inertials and joint poses. - Companion mesh files:
meshes/<part>.stlwritten next tooutput_pathby the MCP tool and the CLI; the written paths are reported inmesh_files. - World anchor:
arm.virtualJoint(name, { type: 'fixed', parentFrame: 'world', childLink })lowers to a native<joint type="fixed"><parent>world</parent>...so the model spawns welded instead of free-falling. - Per-link density: prefer
arm.part(name, shape, { material })(steel/aluminum/pla/abs/pet) — one word seeds the<inertial>density from the catalog (and a matching render finish). A raw{ density }in kg/m³ still works and overrides the material's; every link with neither inherits water (1000) and the export warns.
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.
- 1mo ago First seen · 99 lines · 64 tokens per session scan A 7ee1c0e0f060
kernelcad-sdformat is a skill published in the GitHub repository w1ne/kernelCAD-web (33 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 2,187 once invoked, about $0.0003 per session on Opus 5.5. 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
opengis-skills
Use when AI coding assistant needs GIS/CAD/C#/AI/IoT/3D domain expertise. Index of 96 skills across 8 categories: gis (32), cad (21), csharp (9), ai (14), iot (2), 3d (6), demos (4), others (8). Tag-based search and on-demand loading for GDAL, GeoServer, MapServer, Leaflet, PROJ, PostGIS, JTS, CesiumJS, FreeCAD…
cad-skills
Use when doing parametric 3D modeling, 2D drafting, geometric kernel development, BIM/IFC processing, PCB design, or AutoCAD .NET development. Index of 21 skills: FreeCAD, OpenSCAD, OCCT, CadQuery, Blender, KiCad, SolveSpace, QCAD, xBIM, Clipper2, TongWen and more.
cadquery-modeling
Generate CAD models with CadQuery using an adaptive CAD Compiler workflow: plan-mode skill constraint handoff, focused iteration scopes, fail-first challenge review, compact review packets, real-product reference fidelity, visual/functional audits, source-first repair, and STEP/STL export. Use for CadQuery, CQ, 建模…
solidworks-mcp
Build, edit, inspect and export native SolidWorks models through solidworks-mcp. Use for CAD modeling, raster-to-sketch work and SolidWorks COM/MCP diagnostics. Read before calling a SolidWorks MCP tool.
estructura-de-proyecto
Cómo organizar un proyecto de robótica en CoppeliaSim para que sea reproducible — un script por artefacto, el orden conectar/limpiar/crear/construir/verificar, y qué va en la API de Python frente a qué va en las tools del MCP. Úsala al empezar un proyecto de CoppeliaSim, al añadir un script a uno existente, o cuando…
robot-diferencial-y-sensores
Montar un robot de tracción diferencial en CoppeliaSim y que se mueva de verdad — el eje y el modo de control de las juntas, la fricción que Bullet obedece, masa e inercia, grupos de colisión — más sensores de proximidad, su zona ciega y por qué un cono ancho ve el suelo. Úsala al construir un robot móvil, al montar…