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 fboldo/openscad-mcp-server --skill openscad-iterative-modelinggit clone --depth 1 https://github.com/fboldo/openscad-mcp-serverWrote 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/fboldo/openscad-mcp-server/openscad-iterative-modeling)<a href="https://agentmods.dev/skills/fboldo/openscad-mcp-server/openscad-iterative-modeling"><img src="https://agentmods.dev/badge/skills/fboldo/openscad-mcp-server/openscad-iterative-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/fboldo/openscad-mcp-server/openscad-iterative-modeling"><img src="https://agentmods.dev/badge/skills/fboldo/openscad-mcp-server/openscad-iterative-modeling.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00108 | $0.01312 |
| Opus 5 | $0.00054 | $0.00656 |
| Sonnet 5 | $0.00022 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
openscad-iterative-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 9d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSCAD iterative modeling loop (SCAD → PNG → refine)
When to Use This Skill
- The user asks to create, design, or model a 3D object (bracket, enclosure, mount, gear, etc.)
- The user sends a picture of an object and asks to recreate it in 3D
- The user wants to render or preview OpenSCAD code
- The user asks to export an STL file from a SCAD description
- Any request that can be expressed as parametric CSG geometry
Prerequisites
Required Tools
- OpenSCAD MCP Server: Required for rendering and exporting OpenSCAD geometry
- Enables:
render_scad_png(SCAD → PNG preview),export_scad_stl(SCAD → STL mesh) - Tool names may be namespaced by the host (e.g.
mcp_openscad-mcp-_render_scad_png); match by suffix - Must be configured and running to render previews and export models
- Enables:
Operating mode
- Prefer small, parametric SCAD with named variables.
- Each iteration: change only what the PNG critique indicates.
- After 3 render-refine cycles without convergence, stop and ask the user for clarification.
Workflow
1. Normalize the request (minimal clarifications)
Extract and confirm only what you must to model correctly:
- Units (default to mm if unspecified)
- Critical dimensions (overall size, hole diameters, wall thickness)
- Constraints (must be printable? tolerance? symmetry? sharp vs filleted edges?)
If key dimensions are missing, ask 1–3 questions. Otherwise proceed with reasonable defaults and state them.
2. Draft SCAD code (first pass)
- Use
modulewith named parameters. - Center geometry at the origin when practical (
center=true). - Set
$fnexplicitly for curved parts (start with$fn=64). - Ensure cutters in
difference()extend beyond the body to avoid zero-thickness walls.
3. Render a PNG preview
Render with cameraPreset="isometric" first (width=800, height=600). If features are hard to judge, add orthographic views:
| Feature to verify | Camera preset |
|---|---|
| Plan-view layout, hole positions | top |
| Heights, steps, lips, profiles | front or right |
| Overall shape, proportions | isometric |
| Underside features | bottom |
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.
- 9d ago First seen · 127 lines · 108 tokens per session scan A dc173b26fcee
openscad-iterative-modeling is a skill published in the GitHub repository fboldo/openscad-mcp-server (3 stars, last pushed 6mo ago), licensed MIT. It adds 108 tokens to every session and 1,312 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.