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 scott-createplay/blender-mcp-synthgen --skill skillgit clone --depth 1 https://github.com/scott-createplay/blender-mcp-synthgenWrote 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/scott-createplay/blender-mcp-synthgen/skill)<a href="https://agentmods.dev/skills/scott-createplay/blender-mcp-synthgen/skill"><img src="https://agentmods.dev/badge/skills/scott-createplay/blender-mcp-synthgen/skill/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/scott-createplay/blender-mcp-synthgen/skill"><img src="https://agentmods.dev/badge/skills/scott-createplay/blender-mcp-synthgen/skill.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 | $0.00069 | $0.00581 |
| Opus 5 | $0.00034 | $0.00291 |
| Sonnet 5 | $0.00014 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
blender-synthgen 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blender-synthgen
You are driving Blender to build procedural, reproducible synthetic-data pipelines: structural variation from Geometry Nodes, appearance variation from shaders, ground-truth labels from the compositor — swept over parameters/seeds.
Governing rule — read knowledge/procedural_paradigm.md first
Derive, don't set. Author/extend node graphs driven by scene-derived signals; treat
destructive bpy.ops scene edits as a last resort. You cannot sweep a hand-edit, and sweeping
is the job.
Never guess node identifiers — query the grounded schema
Socket label ≠ identifier (e.g. "Group ID" → Group Index; Math has Value/Value_001/ Value_002). Before writing bpy that builds a graph, look it up:
python -m synthgen.schema.query show "Store Named Attribute"
python -m synthgen.schema.query --shader show "Attribute"
python -m synthgen.schema.query --compositor find "Cryptomatte"
Knowledge base (read the relevant crosswalk before translating)
knowledge/procedural_paradigm.md— the constitution (derive-don't-set, scene signals).knowledge/houdini_to_geonodes.md— SOP → Geometry Nodes.knowledge/attribute_bridge.md— GN ↔ shader via named attributes (per-instance variation + labels).knowledge/cop_to_compositor.md— Houdini COPs (Copernicus) → Blender compositor (passes → masks/depth).knowledge/scene_graph_contexts.md— cross-context edge model for scene introspection/refactor.
Build → verify loop
- Plan in graphs and fields: "what signal drives this?" not "what tool changes this?"
- Look up every node/socket in the schema before wiring it.
- Build via graph edits (bpy that constructs/rewires nodes), not destructive ops.
- Verify across seeds/params, not one state: confirm attributes exist on the expected
domain (GN
Named Attribute.Exists), render a small batch, confirm variation is valid and label passes stay pixel-exact. A single rendered frame is never sufficient proof.
Composability
This runs alongside an existing Blender MCP that provides transport (execute_python, render).
This skill supplies the knowledge + grounding; execute bpy through that transport.
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 · 44 lines · 69 tokens per session scan A cef24afe28a3
blender-synthgen is a skill published in the GitHub repository scott-createplay/blender-mcp-synthgen (0 stars, last pushed 21d ago), licensed MIT. It adds 69 tokens to every session and 581 once invoked, about $0.0003 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
html-ppt-zhangzara-monochrome
A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review committee.
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
paper2video
Turn a research paper, a paper2assets package, or an existing PPT deck into a narrated MP4 video by fully delegating slide authoring to the installed ppt-master skill and fully delegating rendering, subtitles, timeline assembly, and strict media QA to the installed pptx2video skill and its public CLI. Resolves one…
figure-composer
Compose one publication-grade multi-panel figure. Start from a one-line claim plus immutable data Artifact Version references, or inspect an existing figure and draft its outline directly. Plan a 12-column panel outline, delegate one worker per panel, compose and inspect the result, then run at most three adversarial…