Borrowing it
Nothing to install: this file belongs to petrijr/openscad-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/petrijr/openscad-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/petrijr/openscad-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/instructions/petrijr/openscad-mcp/agents-md)<a href="https://agentmods.dev/instructions/petrijr/openscad-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/petrijr/openscad-mcp/agents-md.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 5.1 | $0.01251 | $0.01251 |
| Opus 5 | $0.00626 | $0.00626 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
openscad-mcp AGENTS.md 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 8d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT.md — OpenSCAD MCP Server
Purpose of this File
This document provides guidance for humans and AI agents contributing to or extending the OpenSCAD MCP Server project.
It defines:
- Project goals and non-goals
- Architectural boundaries
- Design principles
- Coding and safety guidelines
The intent is to ensure that future contributions (human or AI-assisted) remain coherent, safe, and aligned with the original vision.
Project Mission
OpenSCAD MCP Server turns OpenSCAD into a deterministic, scriptable geometry compiler exposed via the Model Context Protocol (MCP).
The server enables MCP-compatible clients (including LLMs) to:
- Generate OpenSCAD source
- Inject parameters
- Compile models headlessly
- Export artifacts (STL, 3MF, OFF, PNG)
All while maintaining:
- Predictable behavior
- Clear execution boundaries
- Local-first safety
This project is intentionally scoped as:
A robust, minimal MCP implementation that is easy to reason about and safe to run locally.
It also serves as a learning and architectural stepping stone toward a more complex FreeCAD MCP server.
Core Design Principles
1. Stateless by Default
- Each MCP tool invocation should be self-contained
- No persistent scene graph or mutable global state
- Any temporary state must be explicit (e.g. temp directories)
Rationale:
- Improves reproducibility
- Simplifies error handling
- Makes LLM-driven workflows reliable
2. OpenSCAD as a Compiler, Not an Editor
- Treat OpenSCAD like a compiler:
- Input: SCAD source + parameters
- Output: artifacts or errors
- Do not attempt interactive mesh editing
This aligns with OpenSCAD’s strengths and avoids unnecessary complexity.
3. Explicit Safety Boundaries
- The server must not:
- Execute arbitrary Python code from MCP input
- Evaluate untrusted expressions outside OpenSCAD
- All execution should flow through the
openscadCLI
Assume all SCAD input is untrusted.
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.
- 8d ago First seen · 251 lines · 1,251 tokens per session scan A 073d06d7313c
openscad-mcp AGENTS.md is an instructions file published in the GitHub repository petrijr/openscad-mcp (4 stars, last pushed 7mo ago), licensed MIT. It adds 1,251 tokens to every session, about $0.0063 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.