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-partsgit 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-parts)<a href="https://agentmods.dev/skills/w1ne/kernelcad-web/kernelcad-parts"><img src="https://agentmods.dev/badge/skills/w1ne/kernelcad-web/kernelcad-parts/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-parts"><img src="https://agentmods.dev/badge/skills/w1ne/kernelcad-web/kernelcad-parts.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 | $0.00048 | $0.07229 |
| Opus 5.5 | $0.00019 | $0.02892 |
| Sonnet 5.5 | $0.00010 | $0.01446 |
| Haiku 4.5 | $0.00005 | $0.00723 |
Grade A, and why
kernelcad-parts 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 today.
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 — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kernelcad-parts
Load this skill when the agent needs an off-the-shelf component (M-series fastener, deep-groove ball bearing, NEMA stepper, pin header, JST-XH housing) and does not already know a STEP file path.
The catalog ships bundled with the npm package — npm install resolves
every bundled id offline. When a query has no bundled match, discovery and
fetch fall through to a built-in public parts catalog by default (see "Remote
tier" below), so kernelCAD can find off-the-shelf parts it does not bundle.
Set KERNELCAD_PARTS_BASE_URL=off to stay offline on the bundled seed only.
Four-tool discovery flow
When the agent does not know which id covers the intent, walk the discovery chain. Each step narrows the search:
inspect({ of: 'part-categories' })→ top-level buckets (e.g.fastener,bearing,motor,connector,shaft).inspect({ of: 'part-families', category })→ families within the bucket (e.g.socket-head-cap-screw,deep-groove-ball-bearing).find_part{ query, family?, standard?, tag?, licenseClass? }→ ranked records that match the fuzzy query plus filters. Tokens AND-combine; cross-facet filters AND-combine.licenseClass('permissive'|'share-alike'|'fetch-only') filters by redistribution license; records with no class are treated aspermissive(the bundled catalog).fetch_part{ id }→ resolves the id to a record, writes the STEP into the cache, returns the cache path + sha256.
For tasks where the id is already known, skip straight to fetch_part or
use the typed lib.standard.* shortcuts.
Fetch-by-URL (parts not in the catalog)
For a hash-verified STEP or GLB model file, call fetch_part with
includeModel: true or a model object:
fetch_part({ model: { url, sha256, source, license, expectedBboxMm? } }) for a
direct asset, or fetch_part({ id, includeModel: true }) / { query: <MPN>, includeModel: true } to resolve through the catalog. Explicit URLs require a
64-character sha256 and source/license provenance. The tool caches
URL-fetched assets by content digest and compares STEP bounds, or GLB POSITION
accessor bounds when present, dimension-by-dimension with expectedBboxMm
(default relative tolerance 25%, toleranceRatio to change it). A GLB without
usable accessor bounds reports not_checked; missing or ambiguous catalog
results are returned with a specific errorCode. This resolves a model asset
but does not place it or perform a fit check.
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.
- today Changed · +17 lines 0150e1309333
- yesterday Changed · +27 lines d74cfacb2e65
- 2d ago Changed · +2 lines f029427643a6
- 6d ago Changed · +7 lines 831fa98a943c
- 7d ago Changed · +99 lines fcc70d4b84f2
- 10d ago Changed · +11 lines c9b85e373f8f
- 14d ago Changed · +15 lines 948609b336e8
- 26d ago Changed · +40 lines 804a4fde4553
- 1mo ago First seen · 277 lines · 48 tokens per session scan A 38caf990726a
kernelcad-parts is a skill published in the GitHub repository w1ne/kernelCAD-web (33 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 7,229 once invoked, about $0.0002 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.
urdf
URDF robot description authoring and validation. Use when creating, editing, inspecting, validating, or debugging .urdf files, robot links, joints, limits, inertials, visual/collision geometry, mesh references, frame conventions, or robot-description artifacts. Use the SRDF skill for MoveIt2 semantic groups and…
step-parts
Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers, bearings, standoffs, and other catalog components. Use when Codex needs to search the hosted step.parts catalog before…