What is blender-mcp-synthgen CLAUDE.md?

A project guide for a Python toolkit that procedurally creates 3D synthetic training data in Blender. It varies scene structure, materials, and random seeds, then produces ground-truth labels from the compositor.

Use it to develop or extend Blender workflows that generate varied synthetic scenes, apply shader-based appearance changes, and create labeled data through Geometry Nodes and the compositor.

It gives agents rules for inspecting Blender’s node and socket schema before editing and for making controlled graph changes. This reduces errors caused by guessing Blender identifiers or using destructive scene operations.

How scott-createplay/blender-mcp-synthgen configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to scott-createplay/blender-mcp-synthgen. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/scott-createplay/blender-mcp-synthgen/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/scott-createplay/blender-mcp-synthgen

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/scott-createplay/blender-mcp-synthgen/claude-md/github.svg)](https://agentmods.dev/instructions/scott-createplay/blender-mcp-synthgen/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/scott-createplay/blender-mcp-synthgen/claude-md"><img src="https://agentmods.dev/badge/instructions/scott-createplay/blender-mcp-synthgen/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/scott-createplay/blender-mcp-synthgen/claude-md"><img src="https://agentmods.dev/badge/instructions/scott-createplay/blender-mcp-synthgen/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 884 This file is loaded in full into every session.

When invoked 884 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00884	$0.00884
Opus 5.5	$0.00354	$0.00354
Sonnet 5.5	$0.00177	$0.00177
Haiku 4.5	$0.00088	$0.00088

Measured 2mo ago against content hash b777e8aa4d88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blender-mcp-synthgen CLAUDE.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 2mo 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.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — blender-synthgen-mcp

Project context + working rules for any Claude agent editing this repo. Keep this concise; the deep material lives in knowledge/ and docs/ONBOARDING.md — read those, don't duplicate them here.

What this is

A Python toolkit + (later) composable MCP that helps an agent generate 3D synthetic data in Blender procedurally: structural variation from Geometry Nodes, per-instance appearance from shaders, ground-truth labels from the compositor — swept over parameters/seeds. It composes with an existing Blender MCP (transport), it does not replace it.

Start here: README.md → ROADMAP.md → knowledge/procedural_paradigm.md → knowledge/scene_graph_contexts.md. For a task handoff, docs/ONBOARDING.md.

Working principles (non-negotiable)

Grounding, not memory. Never guess Blender node/socket ids. Query the extracted schema: python -m synthgen.schema.query show "<node>" (also --shader, --compositor). Socket label ≠ identifier.
Derive, don't set. Author/rewire node graphs; treat destructive bpy.ops scene edits as a last resort. Read-only first; mutation is graph-diff, never a destructive command.
The scene graph is a lazy, pull-based view over bpy; the JSON snapshot is a projection for offline/diff only. Edge tiers: ① native pointer, ② reconstructed via cook-then-read, ③ ontological gap (record, never fabricate).
Complete up to Blender's data model — authorability ⇒ introspectability.

Dev workflow

Tests are offline (no Blender): pip install -e ".[dev]" && pytest (or PYTHONPATH=src pytest). Keep them green; add tests with new code. ~70% of the code needs no Blender.
Only scenegraph/backend_bpy.py (and the extractors) need Blender. Run bpy headless: & "C:\Program Files\Blender Foundation\Blender 5.2\blender.exe" -b [file.blend] -P script.py
Layout: src/synthgen/{extract,schema,scenegraph} · data/schemas/<app-version>/ · knowledge/ (agent brain) · skill/SKILL.md · mcp/ (Phase 3).

Read the full file on GitHub · 56 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.

2mo ago First seen · 56 lines · 884 tokens per session scan A b777e8aa4d88

Subscribe to this mod's changes

blender-mcp-synthgen CLAUDE.md is an instructions file published in the GitHub repository scott-createplay/blender-mcp-synthgen (0 stars, last pushed 2mo ago), licensed MIT. It adds 884 tokens to every session, about $0.0035 per session on Opus 5.5. 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.

Creative and media Data and AI

blender-mcp-synthgen CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
blender-mcp-synthgen CLAUDE.mdscott-createplay/blender-mcp-synthgen	Instructions file	0	2mo ago	MIT	A	884	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

blender-mcp-synthgen: Instructions file for Claude Code