simplecadapi

A compact reference for the public API and modeling workflows of the SimpleCAD software development kit, which is a collection of programming tools for building 3D models. It contains documentation rather than the SDK's source code.

In plain words
What is it for?
Use it when writing or checking SimpleCAD code, choosing modeling APIs, or looking up documented geometry and modeling workflows.
Why use it?
It gives an agent the exact reference material needed to work with SimpleCAD's available interfaces and core modeling types.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nijingzhe/simplecadapi/simplecadapi
Any agent
npx skills add NiJingzhe/SimpleCADAPI --skill simplecadapi
Clone the repo
git clone --depth 1 https://github.com/NiJingzhe/SimpleCADAPI

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,544 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.02544
Opus 5 $0.00013 $0.01272
Sonnet 5 $0.00005 $0.00509
Haiku 4.5 $0.00003 $0.00254

Measured 3d ago against content hash 19bbc3d492f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simplecadapi 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 3d 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.

skills/simplecadapi/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SimpleCAD SDK Skill

Philosophy

  • This is a thin SDK reference skill: docs only.
  • SDK source code is not bundled in this skill.

Working From Repo Root

  • Tool calls run from the repo root.
  • Use one explicit skill root: ./skills/simplecadapi/ or ./workspace/skills/simplecadapi/.
  • Main doc paths:
    • <skill_root>/SKILL.md
    • <skill_root>/references/docs/api/README.md
    • <skill_root>/references/docs/api/<api_name>.md
    • <skill_root>/references/docs/stdlib/README.md
    • <skill_root>/references/docs/stdlib/<stdlib_api_name>.md
    • <skill_root>/references/docs/core/<type_name>.md
    • <skill_root>/references/SDK_OVERVIEW.md
    • <skill_root>/references/SDK_SURFACES.md
    • <skill_root>/references/MODELING_WORKFLOWS.md
    • <skill_root>/references/inspect/brep-reverse-engineering.md

MUST Requirements

  1. Read SKILL.md, references/docs/api/README.md, and references/docs/stdlib/README.md before choosing APIs.
  2. Read the exact API Markdown page for every API you use.
  3. Read the needed core/ or exact api/ docs when an API needs Edge, Face, Wire, Solid, GraphSession, Sketch, or expression types.
  4. Prefer the standard parts library for standard parts before hand-modeling with core geometry APIs.
  5. Follow the documented API signatures exactly.
  6. When calling any SimpleCAD public API or standard-library function, use keyword arguments for every documented parameter; do not use positional arguments.
  7. Use one @model entry point for replayable tasks, @requires_session for child builders, capture_result(...) for explicit outputs, and the returned ModelResult for model/session JSON and replay.
  8. Use geometry APIs for integrated parts: profiles, features, booleans, transforms, tagging, QL inspection, serialization, and exports.
  9. Use tags consistently through apply_tag(shape=..., tag=...) and list_tags(shape=...); do not call shape member tag mutators.
  10. Build and validate incrementally. Each step MUST include a small grounding print, and grounding MUST use QL where possible.
  11. For inspection/debugging, query geometry with QL and print only the queried facts you need; do not print whole solids or full model objects.
  12. Boolean operations return a single Solid.
  13. Use union_rsolid(...) for boolean union.
  14. For automated example/test harnesses, prefer the repo-local examples in examples/ and avoid scratch scripts in sandbox/.
  15. If union cannot produce exactly one merged solid, it fails explicitly; do not silently pick one piece.
  16. If a single merged solid is required and union fails, slightly adjust part placement so intended bodies overlap/embed, then recompute.
  17. If a task depends on model replay or interchange, prefer ModelResult.model_json or export_model_json() output over hand-written payloads.
  18. For STEP/BREP inspection or target/candidate comparison, read references/inspect/brep-reverse-engineering.md completely.
  19. Use simplecadapi.inspect.brep only outside GraphSession and @model; inspection functions are diagnostic tools, not modeling operations.
  20. Reverse engineering is case-by-case: the built-in inspection primitives are tools, not a pipeline — write ad hoc inspection code for the specific model when built-ins do not answer the question. Acceptance hierarchy: BREP topology identity is the best endpoint (complete reverse engineering); identical structure with minor float-level parameter drift from export is acceptable; a visually-close but structurally different result is a valid stop only when no better feature operation order/combination exists or the SDK lacks the required operation type.

Read the full file on GitHub · 146 lines

Files

What ships with it

60 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.

Changes

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.

  1. 3d ago First seen · 146 lines · 25 tokens per session scan A 19bbc3d492f2

Subscribe to this mod's changes

simplecadapi is a skill published in the GitHub repository NiJingzhe/SimpleCADAPI (105 stars, last pushed 8d ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,544 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

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.

znlgis/opengis-skills · 97 tokens

cadquery

Use when scripting parametric 3D CAD models in Python — programmatic part generation, parametric design optimization, STEP export. CadQuery: Python-based parametric CAD built on OCCT kernel with a fluent API.

znlgis/opengis-skills · 47 tokens

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.

znlgis/opengis-skills · 79 tokens

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…

armpro24-blip/cad-cae-copilot · 97 tokens

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.

armpro24-blip/cad-cae-copilot · 67 tokens

kernelcad-authoring

Author or modify kernelCAD models in TypeScript. Scripts live in .kcad.ts files; the kernelCAD CLI (kernelcad evaluate and kernelcad export stl|step|dxf|3mf|glb -o ) executes them via an OpenCASCADE WASM kernel.

w1ne/kernelCAD-web · 55 tokens