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-kinematicnpx skills add w1ne/kernelCAD-web --skill kernelcad-kinematicgit 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-kinematic)<a href="https://agentmods.dev/skills/w1ne/kernelcad-web/kernelcad-kinematic"><img src="https://agentmods.dev/badge/skills/w1ne/kernelcad-web/kernelcad-kinematic.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 | $0.00065 | $0.04037 |
| Opus 5 | $0.00032 | $0.02018 |
| Sonnet 5 | $0.00013 | $0.00807 |
| Haiku 4.5 | $0.00006 | $0.00404 |
Grade A, and why
kernelcad-kinematic 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 4d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kernelcad-kinematic — feasibility gates for moving assemblies
Units (read this first)
Joint angles throughout the kinematic API are degrees for revolute joints
and millimetres for prismatic joints. This matches the unit convention
used by arm.mate(..., 'revolute', { limitsDeg }), arm.mate(..., 'prismatic', { limitsMm }),
and arm.solvedModel({poses}) — there is no degree-vs-radian split anywhere
on the user-facing surface.
That includes the IK seed: kinematic.checkReachable({ seed: { shoulder: 60 } })
means 60 degrees, not 60 radians and not 60 of anything else. Authors porting
code from URDF / MoveIt / ROS — where radians are conventional — must convert
(deg = rad * 180 / Math.PI) before passing values to this API.
A small seed value like 0.3 is interpreted as 0.3°, which is effectively
zero — fine as a "near rest pose" hint, but not the ~17° you'd get if you
were thinking in radians.
When to load
Load this skill whenever the user asks any of:
- "Will this arm hit itself?" / "Does this mechanism clear across its motion?"
- "Can this robot reach this point?" / "Is this target in the workspace?"
- "Will these mounting holes line up?" / "Are the bolt patterns compatible?"
- "Will this bracket hold this load?" / "What's the safety factor?"
Do NOT load this skill for static CAD authoring (use kernelcad-authoring) or
for visualization (use the renderer). This skill is feasibility-checking only.
The 4 entry points
All four live under the kinematic.* namespace exposed to every .kcad.ts
script. The same surface is reachable from host code via import * as kinematic from 'src/kinematic'. Every entry returns a Promise<…Result> envelope carrying
source: 'local'.
| Call | Question answered | Key diagnostics |
|---|---|---|
kinematic.checkMountingHoleConsistency(arm) |
Do fastener holes match across all mates? | kinematic.mounting-hole.diameter-mismatch (K9) |
kinematic.checkSweptCollision(arm, opts) |
Does any link pair penetrate across the swept range? | kinematic.collision.swept (K1), kinematic.collision.swept.sample-density-warning (K2) |
kinematic.checkReachable(arm, opts) |
Can the end-effector reach this target? | kinematic.unreachable (K3, axis-discriminated), kinematic.reachability.iteration-cap-hit (K4), kinematic.solver.unsupported-config (K5) |
kinematic.checkLoadCapacity(arm, loads, opts) |
Will any beam-shaped element exceed yield under these loads? | kinematic.load-exceeds-yield (K6), kinematic.load.beam-not-applicable (K7), kinematic.no-material-declared (K8) |
What ships with it
6 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.
- cookbook/01-swept-collision-shoulder.kcad.ts 2.4 KB runs code
- cookbook/02-reachable-with-seed.kcad.ts 4.5 KB runs code
- cookbook/03-cantilever-beam-stress.kcad.ts 2.0 KB runs code
- cookbook/04-scissor-jack-swept.kcad.ts 1.9 KB runs code
- cookbook/05-clamshell-hinge-swept.kcad.ts 2.1 KB runs code
- cookbook/06-over-center-latch-reachable.kcad.ts 3.6 KB runs code
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.
- 4d ago First seen · 218 lines · 65 tokens per session scan A 3f755f94bb21
kernelcad-kinematic is a skill published in the GitHub repository w1ne/kernelCAD-web (17 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 4,037 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
cad-viewer
Start CAD Viewer and return review links for explicit CAD, implicit CAD, and robot-description files. Use when visually reviewing .step, .stp, .implicit.js, .implicit.mjs, .glb, .stl, .3mf, .dxf, .urdf, .srdf, or .sdf files, especially when handed off from CAD, implicit-cad, URDF, SRDF, or SDF generation skills.
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.
print-design-rules
Apply 3D-printing design rules when modelling geometry in Blender that will be printed — overhang limits, wall thickness, clearances between mating parts, hole sizing, fillets and chamfers, print-in-place gaps, part orientation. Use BEFORE generating or modifying geometry intended for FDM printing, and when reviewing…
step-parts
Find, evaluate, and download low-level common standard CAD parts from step.parts, such as screws, bolts, nuts, washers, bearings, standoffs, electronics parts, motors, connectors, and other off-the-shelf components. Use when Codex needs to search the hosted step.parts catalog, resolve fuzzy part names, standards…
nurb
Design 3D-printable parts as Python functions with nurb. Use when the user wants a part designed, changed, or checked for 3D printing (a bracket, mount, holder, enclosure, shelf, or any STL/STEP to print), and in any directory with a parts/ folder. The user describes the part and judges it in a browser; you model it.
industrial-product-design
Define, compare, model, review, and mature industrial products before manufacturing drafting. Use for new products, major redesigns, enclosures, appliances, controls, ports, mechanisms, configurable assemblies, product-quality 3D, CMF, ergonomics, service, motion states, native renders, prototype planning, or any task…