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/kernelcad-featuresnpx skills add w1ne/kernelCAD-web --skill kernelcad-featuresgit clone --depth 1 https://github.com/w1ne/kernelCAD-webWhat 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 | $0.00049 | $0.05074 |
| Opus 5 | $0.00024 | $0.02537 |
| Sonnet 5 | $0.00010 | $0.01015 |
| Haiku 4.5 | $0.00005 | $0.00507 |
Grade A, and why
kernelcad-features 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 2d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kernelCAD — edge and face features
Face refs through operations
Canonical face refs ({ face: 'top' }, etc.) work transparently across transforms (.translate, .rotate, .scale, .reflect, .mirror) and unambiguous booleans (.subtract, .union, .intersect). The kernel walks each face's lineage back to its originating primitive and forward through history.
Two cases produce explicit diagnostics:
feature.face-ref.ambiguous-after-split— an upstream boolean split the named face into multiple children (e.g., a divider cut splitstopinto two halves). Geometry-fallback disambiguation is planned for a future release; current workaround: apply the edge/face feature before the splitting operation, or use a query-based selector.feature.face-ref.removed— an upstream boolean removed the named face entirely. Reference a different face that still exists in the current shape.feature.hole.no-target-face— the hole entry face matched, but no body sits along the bore axis to drill into. Pick an entry face on a different body, or verify the target body extends along the bore axis.feature.created-ref.fallback-used— warning (not error). The created-ref resolver fell back to a geometry-snapshot match after the topology lookup lost the face. The downstream feature still resolves. Lock the ref against future edits by naming the upstream feature with.name()and addressing it by<name>.<slot>.
(The same feature.face-ref.* codes apply to both edge features (fillet, chamfer) and face features (shell).)
Created face refs
Subtractive features (hole, cutout) write created face refs that downstream
ops can address by <featureName>.<slot>:
const plate = box(100, 60, 5)
.hole('top', { u: 0, v: 0, diameter: 6, depth: 3, name: 'pilotHole' });
plate.fillet(0.2, { face: 'pilotHole.floor' });
Slots written by hole: wall, floor, wall-back, counterbore-wall,
counterbore-floor, countersink-cone, entry-rim, floor-rim,
wall-back-rim. Slots written by cutout: see cutoutClassifier.
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.
- 2d ago First seen · 336 lines · 49 tokens per session scan A bf5bf4e6e860
kernelcad-features is a skill published in the GitHub repository w1ne/kernelCAD-web (17 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 5,074 once invoked, about $0.0002 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
simplecadapi
Thin SimpleCAD SDK reference skill focused on the public API surface, core types, and current modeling workflows.
opengis-skills
Use when AI coding assistant needs GIS/CAD/C#/AI/IoT/3D domain expertise for 72+ 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
Use when doing parametric 3D modeling, 2D drafting, geometric kernel development, BIM/IFC processing, PCB design, or AutoCAD .NET development. Index of 19 skills: FreeCAD, OpenSCAD, OCCT, CadQuery, 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…
aieng-cad-authoring
Active MCP-first CAD authoring skill for AIENG Workbench. Use when the user asks to create, design, draft, model, or iteratively build CAD geometry through the active cad. MCP tools. Do not use for solver/result review, schema/library implementation, or editing legacy IR plans.
aieng-cad-cae-copilot
MCP-first evidence workflow for AIENG CAD/CAE setup, solver preflight, approval-gated solver execution, and result extraction. Use when the user asks to inspect CAE readiness, patch setup, prepare/run CalculiX, or report stress/displacement evidence.