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 agentmods add skills/w1ne/kernelcad-web/use-the-available-kernelnpx skills add w1ne/kernelCAD-web --skill use-the-available-kernelgit 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/use-the-available-kernel)<a href="https://agentmods.dev/skills/w1ne/kernelcad-web/use-the-available-kernel"><img src="https://agentmods.dev/badge/skills/w1ne/kernelcad-web/use-the-available-kernel.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 | $0.00051 | $0.02569 |
| Opus 5 | $0.00026 | $0.01285 |
| Sonnet 5 | $0.00010 | $0.00514 |
| Haiku 4.5 | $0.00005 | $0.00257 |
Grade A, and why
use-the-available-kernel 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 5d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
use-the-available-kernel
The from-reference loop fails most often not because kernelCAD lacks a primitive, but because the author did not reach for one that exists. This skill is a checklist of hard rules: when condition X holds in the reference, USE primitive Y.
Rule 1 — Non-uniform corner radii → variable fillet
If the reference shows a product where different corners have visibly different radii (Wayfarer brow: 4 mm at temple, 8 mm at outer-top wing corner; bottle shoulders; controller grips), USE the variable-radius form:
shape.fillet([
{ edges: { face: 'top', byNormal: '+Z' }, radius: 8 },
{ edges: { face: 'top', byNormal: '+Z', region: 'temple' }, radius: 4 },
]);
Do NOT author with repeated single-radius .fillet(r) calls and live with a
uniform-look body. The scorer detects the sharp vs. rounded corner curvature
mismatch in the silhouette gate.
Rule 2 — Symmetric parts → mirror, author one side
If the reference is symmetric about a cardinal plane (eyewear: YZ; most bottles:
ZY axis; most consumer products: some cardinal plane), build the right half
explicitly and call .mirror('YZ'):
const right = bodyHalf();
const full = right.mirror('YZ');
Do NOT author both halves manually with mirrored arcs. The cost is roughly 2× LoC and creates inevitable asymmetry bugs — the scorer will detect the SSIM break on the opposite side of the model.
Rule 3 — Cross-section varies along the body → surfaceFromCurves
If the body is visibly thicker at one end and thinner at another (acetate
frames, handle grips, bottle necks), USE surfaceFromCurves with 2–3
cross-section profiles and .thicken(t):
const body = surfaceFromCurves([
outlineAtTemple,
outlineAtBridge,
outlineAtTemple.mirror('YZ'),
]).thicken(15);
Do NOT uniform-extrude a single silhouette. The resulting slab is what the scorer detects as a "fake" body — the silhouette gate passes, but the SSIM gate fails because the depth profile is wrong.
Rule 4 — Organic curves → smoothSpline
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.
- 5d ago First seen · 247 lines · 51 tokens per session scan A db2110a0bbc0
use-the-available-kernel is a skill published in the GitHub repository w1ne/kernelCAD-web (17 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 2,569 once invoked, about $0.0003 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
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…
opengis-skills
Use when AI coding assistant needs GIS/CAD/C#/AI/IoT/3D domain expertise for 73+ open-source projects. One-stop skill index with tag-based search and on-demand loading for GDAL, GeoServer, QGIS, PostGIS, JTS, CesiumJS, FreeCAD, OpenSCAD, OCCT, NPOI, SqlSugar, Furion, Dify, SuperSplat, Go and more.
cad-skills
Use when doing parametric 3D modeling, 2D drafting, geometric kernel development, BIM/IFC processing, PCB design, or AutoCAD .NET development. Index of 20 skills: FreeCAD, OpenSCAD, OCCT, CadQuery, KiCad, SolveSpace, QCAD, xBIM, Clipper2, TongWen and more.
cadquery-modeling
Create, edit, or debug parametric 3D CAD parts in CadQuery (Python) that export to STEP for SolidWorks. Use when the request involves CadQuery, .step/.stl export, or modelling a physical part — enclosure, bracket, PCB, motor mount, cam, gear. Also use when a STEP will not open in CAD, or geometry looks correct in STL…
bambu-labs
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
srdf
MoveIt2 SRDF authoring, validation, and planning-semantics workflow. Use when creating, editing, inspecting, or validating .srdf files, MoveIt planning groups, virtual joints, passive joints, end effectors, group states, disabled collisions, URDF-paired planning semantics, or SRDF handoff for live review. Use the URDF…