Synapse: Skill for Claude Code

.claude/skills/solaris-render/SKILL.md

solaris-render is a skill for Claude Code from JosephOIbrahim/Synapse. It costs 0 tokens per session (1,005 once invoked), scanned A, original, MIT.

A staged workflow for creating and rendering Solaris scenes in Houdini, a 3D production tool, through the SYNAPSE connection. Solaris uses USD, a format and system for assembling 3D scenes from layered parts.

In plain words
What is it for?
Use it to build scene geometry and lights, assign materials, set up cameras and render settings, and validate the scene before rendering.
Why use it?
It checks each stage before moving on and addresses Houdini and USD layering rules that can otherwise produce missing objects, materials, or incorrect renders.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is JosephOIbrahim/Synapse's own configuration. It tells Claude Code how to work on Synapse itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Synapse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JosephOIbrahim/Synapse. 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/JosephOIbrahim/Synapse/master/.claude/skills/solaris-render/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Synapse

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.

agentmods badge for solaris-render

README.md
[![agentmods](https://agentmods.dev/badge/skills/josephoibrahim/synapse/solaris-render.svg)](https://agentmods.dev/skills/josephoibrahim/synapse/solaris-render)
Your own site
<a href="https://agentmods.dev/skills/josephoibrahim/synapse/solaris-render"><img src="https://agentmods.dev/badge/skills/josephoibrahim/synapse/solaris-render.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,005 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 5.1 $0.00000 $0.01005
Opus 5 $0.00000 $0.00502
Sonnet 5 $0.00000 $0.00201
Haiku 4.5 $0.00000 $0.00101

Measured 6d ago against content hash e64c7da186f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

solaris-render 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 6d 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/skills/solaris-render/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solaris Scene Rendering Pipeline

Progressive validation pipeline for creating and rendering Solaris scenes via the SYNAPSE MCP connection to Houdini. Do NOT skip stages.

Stage 1: Scene Setup

  • Create scene geometry and light rig
  • After creation, query the stage and confirm all expected prims exist at correct paths
  • List any missing prims before proceeding
  • Wire nodes in correct order: geometry -> merge -> materials -> camera -> render_settings -> karma

USD layering gotchas (verified 21.0.671, 2026-05-30)

  • sublayer LOP ordering is the OPPOSITE of raw USD. It composes filepathN (highest index) as the STRONGEST layer — whereas raw subLayerPaths index 0 is strongest. To make a render department layer win, fill weakest-first (filepath1=layout … filepath5=render).
  • node.editableStage() is None outside an active Python-LOP cook. It is not a general authoring surface. Author via LOP nodes + parms, read via node.stage(), and write USD attrs via a pythonscript-LOP (where editableStage() IS valid in-cook). A pythonscript subLayerPaths edit does NOT compose downstream — use a real sublayer LOP + files instead.

Stage 2: Material Assignment

  • Assign materials to geometry using exact USD prim paths (NOT wildcard patterns)
  • After assignment, validate by querying each prim's material binding
  • Print: prim path + bound material for every assigned prim
  • Fix mismatches before proceeding
  • Use material library nodes with subnets (not separate matlib + assign)

Stage 3: Render Output Config

  • Set up render product and output path
  • Set picture on the Karma LOP AND outputimage on the ROP
  • Validate the output directory exists and is writable
  • Print the resolved output path

Stage 4: Test Render

  • Execute a minimal-resolution render: max 256x256, no SSS, no displacement, low samples (4-8)
  • Wait for completion with a 60-second timeout
  • Do NOT use soho_foreground=1 for heavy scenes (blocks Houdini entirely)
  • If Houdini becomes unresponsive, report failure and STOP — do NOT attempt higher quality
  • Use iconvert.exe from $HFS/bin/ for EXR-to-JPEG preview conversion

Read the full file on GitHub · 72 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. 6d ago First seen · 72 lines · 0 tokens per session scan A e64c7da186f7

Subscribe to this mod's changes

solaris-render is a skill published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,005 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 2026-08-31.

Related

Other skills, from other repositories

dcc-mcp-core

Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…

dcc-mcp/dcc-mcp-core · 109 tokens

maya-pipeline

Domain skill — Maya asset pipeline orchestration: set up project directory structures, export scenes to USD, and coordinate multi-step DCC workflows. Use when initialising a Maya project or exporting assets for a downstream pipeline. Not for raw geometry editing — use maya-geometry for that. Not for low-level USD file…

dcc-mcp/dcc-mcp-core · 74 tokens

imagemagick-tools

Infrastructure skill — image processing and manipulation via ImageMagick: resize, composite, convert formats, add watermarks. Use when batch-processing textures, thumbnails, or rendered images at the file level. Not for in-DCC texture or material editing — use a domain skill bound to the specific DCC for that.

dcc-mcp/dcc-mcp-core · 67 tokens

asset-source

Gateway skill for cross-DCC asset import — search and resolve assets into a validated AssetDescriptor (local path + attribution). Demo source returns static catalog entries; production sources can add download or remote resolution without changing the contract.

dcc-mcp/dcc-mcp-core · 47 tokens

ffmpeg-media

Infrastructure skill — media conversion and processing via FFmpeg: convert video/audio formats, extract frames, resize, and transcode. Use when manipulating raw media files (mp4, mov, wav, image sequences) regardless of DCC context. Not for DCC-specific render output handling — use a domain pipeline skill for…

dcc-mcp/dcc-mcp-core · 77 tokens

maya-geometry

Domain skill — Maya geometry primitives: create spheres, cubes, cylinders; bevel, extrude, and merge polygon components. Use for individual geometry creation or editing operations inside Maya. Not for full asset export pipelines — use maya-pipeline for that. Not for USD scene inspection — use usd-tools for that.

dcc-mcp/dcc-mcp-core · 65 tokens