best_practices

Guidance for creating realistic 3D models in SketchUp, a tool for designing three-dimensional objects and spaces. It covers shape construction, extrusion direction, rounded-looking edges, and when to apply materials.

In plain words
What is it for?
Use it when scripting SketchUp models, especially objects made by extruding flat profiles, shaping corners, checking face direction, and adding materials.
Why use it?
It helps avoid broken geometry and unexpected results caused by complicated modeling operations.

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/best_practices
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 1,064 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 $0.01064
Opus 5 $0.00000 $0.00532
Sonnet 5 $0.00000 $0.00213
Haiku 4.5 $0.00000 $0.00106

Measured 2d ago against content hash 1226c9226779, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

best_practices 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/best_practices.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Modeling Best Practices

Lessons learned from real SketchUp modeling projects. For code patterns and workflow, see the main prompt.

Profile-First Geometry

Build 3D shapes by extruding 2D profiles rather than complex boolean operations:

# Good: Draw profile, then extrude
profile = entities.add_face(profile_points)
profile.pushpull(depth)

# Avoid: Complex 3D boolean operations
# They often create broken geometry or unexpected results

Pushpull Direction

Face normals determine pushpull direction. If pushpull goes the wrong way:

# Check/flip normal before pushpull
face.reverse! if face.normal.z < 0

# Or use negative value
face.pushpull(-depth)  # Extrude in opposite direction

Edge Treatment for Realism

Real objects have slightly rounded edges. For clean geometry:

  • Chamfer in profile - Add angled corners to 2D profile before extrusion
  • Octagonal sections - For fully rounded rectangular parts, use 8-sided profile
  • Avoid complex fillets - SketchUp fillets often create overlapping/broken geometry
# Instead of sharp corner [0,0], [1,0], [0,1]
# Use chamfered corner [0,0.1], [0.1,0], [1,0], [0,1]

Material Timing

Apply materials after geometry is verified:

  1. Create all geometry first
  2. Verify with list_entities or take_screenshot
  3. Apply materials only after structure is correct

Materials on broken geometry are wasted effort.

Apply materials to Groups/Components only - never to raw faces/edges unless the user explicitly requests it. Materials on containers are cleaner and easier to manage.

Visual Debugging with Batch Screenshots

When developing and testing geometry-creating code, use take_batch_screenshots for comprehensive visual verification:

Best practices:

  1. Isolate the target - Use the isolate parameter to show only the component/group being worked on
  2. Multiple angles - Capture several views to verify geometry from all sides
  3. Use isometric view - The iso view uses parallel projection (no perspective), ideal for verifying proportions

Read the full file on GitHub · 129 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 · 129 lines · 0 tokens per session scan A 1226c9226779

Subscribe to this mod's changes

best_practices 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 1,064 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.

Related

Other agents, from other repositories

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

medical-learning-safety-reviewer

审校医学学习草稿的来源、教育边界、患者隐私和输出风险;只返回审校意见,不处理外部动作或状态写入。.

TencentCloud/Octop · 35 tokens

deep-reflector

Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.

feiskyer/claude-code-settings · 40 tokens

nw-documentarist

Use for documentation quality enforcement using DIVIO/Diataxis principles. Classifies documentation type, validates against type-specific criteria, detects collapse patterns, and provides actionable improvement guidance.

nWave-ai/nWave · 0 tokens

docs-writer

Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.

alirezarezvani/claude-code-tresor · 33 tokens

retrospective

Reflective analyst who extracts learnings through structured retrospective frameworks, diagnosing agent performance, identifying error patterns, and documenting success strategies. Uses Five Whys, timeline analysis, and learning matrices. Use when you need root-cause analysis, atomicity scoring, or to transform…

rjmurillo/ai-agents · 62 tokens