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 pzfreo/build123d-mcp --skill b123d-modelinggit clone --depth 1 https://github.com/pzfreo/build123d-mcpWrote 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/pzfreo/build123d-mcp/b123d-modeling)<a href="https://agentmods.dev/skills/pzfreo/build123d-mcp/b123d-modeling"><img src="https://agentmods.dev/badge/skills/pzfreo/build123d-mcp/b123d-modeling/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/pzfreo/build123d-mcp/b123d-modeling"><img src="https://agentmods.dev/badge/skills/pzfreo/build123d-mcp/b123d-modeling.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 | $0.00000 | $0.06879 |
| Opus 5.5 | $0.00000 | $0.02752 |
| Sonnet 5.5 | $0.00000 | $0.01376 |
| Haiku 4.5 | $0.00000 | $0.00688 |
Grade A, and why
b123d-modeling 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 11d 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 — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build 3D Geometry with build123d
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
Use the build123d-mcp MCP server as the execution and verification authority.
Build incrementally with execute() by default and checkpoint the first valid
model. If matching-view evidence then shows a body-family/global-form mismatch,
keep the replacement in one canonical model.py and run it with execute_file();
then use measure() → validate() → render_view() before exporting it.
execute_file() runs in a clean namespace and preserves the previous valid model
if the rebuild fails, so a necessary global correction does not sacrifice the
verified checkpoint. Do not globally rebuild a checkpoint merely because a
canonical source file is available.
Step 0 — Start the session
reset(), thenexecute("from build123d import *").- Read the
build123d://quickrefresource before writing build code — it has accurate API syntax for the current build123d version. - If the part uses fasteners, bearings, or threads, read
build123d://bd_warehouseand probe catalogue sizes before scripting.
Step 1 — Extract the spec before modeling
Do not model while reading the input. First convert it into a parameter block.
From a technical drawing (image or PDF):
- Identify the views — front / plan (top) / side — and the projection convention; the title block states first- or third-angle, the SCALE (e.g. 2:1), and the units/tolerance standard.
- Printed dimension callouts are real part dimensions. Never replace one with a pixel-derived value, and never multiply a printed dimension by drawing scale.
- Hidden (dashed) lines are internal features — holes, pockets, bores. Centrelines (long-short chain) mark hole centres and symmetry axes. Section hatching shows solid material in a cut view.
- Symbols: Ø diameter (not radius), R radius, M6/M8… threads,
⌴ counterbore, ⌵ countersink, typical hole note
4× Ø6.6 THRU. - Cross-check every feature in at least two views before trusting it — a circle in plan with no matching hidden lines in front is probably a boss, not a hole.
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.
- 11d ago Changed · +1 lines cbecd2a631dd
- 1mo ago Changed 08fb73b810cb
- 1mo ago Changed · +39 lines 60ee72b0e0ab
- 1mo ago First seen · 450 lines · 0 tokens per session scan A 79749e74e222
b123d-modeling is a skill published in the GitHub repository pzfreo/build123d-mcp (132 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,879 tokens. 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
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-closed-loop-copilot
MCP-first closed-loop CAD/CAE copilot skill for improving an existing solved design against explicit targets. Use when the user asks for bounded design iteration using editable CAD parameters, solver reruns, and evidence-backed comparison.
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.
vibe-industrial-design
Take a product's OUTER APPEARANCE (industrial design: form, proportion, panel split, CMF, controls layout) from a brief + AI-generated look images to a parametric three.js appearance model, a fixed-camera contact sheet, Blender Cycles finals, and a versioned ID report (md authority + Word snapshot) — driven by an AI…
vibe-cad
Take a mechanical part / enclosure from a natural-language spec to a parametric build123d model, reviewed interactively in the latest CAD Viewer and exported as STEP/STL for print or tooling — written for a beginner driving CAD via Claude Code. Use when designing or revising an ENCLOSURE / bracket / carrier-shell…
wireframe-power-bi-page
Use when planning the layout of a Power BI report page. Triggers on phrases like "wireframe a page", "layout for a dashboard", "where should I put the visuals", "design the page layout", "how should I arrange these visuals". Covers canvas geometry (1280x720), 5 validated layouts, the pbirlayoutgrid tool, spacing math.