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/render-inspectnpx skills add w1ne/kernelCAD-web --skill render-inspectgit 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 | $0.00046 | $0.01222 |
| Opus 5 | $0.00023 | $0.00611 |
| Sonnet 5 | $0.00009 | $0.00244 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
render-inspect 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
render-inspect
Purpose
kernelcad evaluate returns diagnostics[]. Each entry carries code,
message, severity, and hint. This sub-skill is a quick lookup: given a
diagnostic code seen during a from-reference build, what is the most likely
cause and what is the fix.
Do NOT re-derive this from the code or message alone — read the hint field
first. It is a one-sentence imperative. This sub-skill is for when the hint is
not enough.
Categories of diagnostics in from-reference builds
1. Missing feature — the referenced operation does not exist yet
These diagnostics mean a feature the model depends on was not authored or was accidentally removed:
| Code | Typical cause in from-reference | Fix |
|---|---|---|
recompute.input.missing |
A feature's upstream shape (e.g., the blockout primitive) was renamed or removed. | Call why_did_this_fail MCP tool to walk the chain. Restore or rename the upstream shape. |
feature.face-ref.removed |
A boolean removed a face that a downstream fillet/shell still references. | Reorder: apply the fillet before the boolean. Or switch to a query-based selector. |
feature.face-ref.ambiguous-after-split |
A boolean split a face that was targeted by name. | Apply the feature before the splitting boolean, or use await selectEdges(shape, query) to target the specific post-split face. |
2. Wrong argument — the operation exists but the input is out of range
| Code | Typical cause in from-reference | Fix |
|---|---|---|
feature.invalid-args |
Fillet radius exceeds the local edge geometry (too large for a thin frame arm). | Reduce the fillet radius. Use the variable-radius form to apply a smaller radius on narrow edges. |
feature.invalid-args (scale) |
.scale([sx, sy, sz]) received a zero or negative factor (e.g., a param reached 0). |
Add a min: 0.001 guard on the controlling param. |
feature.hole.no-target-face |
The hole's entry face is correct but the bore axis does not intersect a solid body. | Check that the target body extends along the bore axis past the hole entry depth. |
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 · 89 lines · 46 tokens per session scan A 647f3db2cf7e
render-inspect is a skill published in the GitHub repository w1ne/kernelCAD-web (17 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 1,222 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.