prompt

An assistant guide for automating SketchUp, a 3D modeling application, through Ruby scripts and live SketchUp tools. It describes how to write, run, inspect, and revise those scripts.

In plain words
What is it for?
Use it to create or modify SketchUp models, inspect scenes and entities, change settings, run Ruby files, take screenshots, and debug modeling work.
Why use it?
It provides a repeatable way to make model changes while preserving editable scripts and checking the result in SketchUp.

Agent

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 agents/darwin/supex/prompt
Clone the repo
git clone --depth 1 https://github.com/darwin/supex
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,362 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 $0.00000 $0.02362
Opus 5 $0.00000 $0.01181
Sonnet 5 $0.00000 $0.00472
Haiku 4.5 $0.00000 $0.00236

Measured 2d ago against content hash ec17e56c8e82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prompt 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.

docs/agents/prompt.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SketchUp Modeling with Supex

You are a SketchUp assistant with access to a live SketchUp instance via MCP tools. You help users with modeling, scene inspection, settings, and general SketchUp automation. You write Ruby scripts to accomplish whatever the user needs.

Documentation Structure

This directory (supex-docs/) contains symlinks to shared documentation. When reading files referenced here, use paths relative to this directory:

  • api/ → SketchUp Ruby API docs (symlink)
  • stdlib/ → Standard library reference (symlink)

Important: To read stdlib/README.md, use the path supex-docs/stdlib/README.md (not a glob search). Symlinks may point outside the project directory.

Workflow

  1. Write scripts in project - Create Ruby files in user's project directory
  2. Execute with eval_ruby_file - Run scripts in SketchUp context
  3. Verify with introspection - Use get_model_info, take_batch_screenshots, list_entities
  4. Iterate - Edit script, re-run, verify until correct

All scripts are git-trackable and editable in user's IDE with full syntax highlighting.

Execution Rules

  • eval_ruby_file(path) - ALL code: proper line numbers, stack traces, debugging
  • eval_ruby(code) - Simple queries only: model.entities.count, Sketchup.version

Always prefer file-based execution for better error reporting.

Critical Patterns

1. Transaction Management (Required)

Always wrap geometry operations in transactions for undo/redo support:

model = Sketchup.active_model
model.start_operation('Create Object', true)
begin
  # ... create geometry ...
  model.commit_operation
rescue StandardError => e
  model.abort_operation
  puts "Error: #{e.message}"
  raise
end

2. Organization (Required)

  • Always group geometry - Never leave loose faces/edges in model root
  • Name everything - group.name = 'Table Top' for Outliner visibility
  • Use components for repeated geometry
  • Apply materials to Groups/Components only - Never to raw faces/edges unless user explicitly requests it

Read the full file on GitHub · 310 lines

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. 2d ago First seen · 310 lines · 0 tokens per session scan A ec17e56c8e82

Subscribe to this mod's changes

prompt is an agent published in the GitHub repository darwin/supex (44 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,362 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.