SUBSTRATE

A Houdini integration agent that safely connects asynchronous MCP commands to Houdini’s single-threaded Python interface. It routes Houdini operations through the main application thread.

In plain words
What is it for?
Use it when building or reviewing the connection between an MCP server and Houdini, especially for safely executing Houdini API calls from asynchronous code.
Why use it?
It helps prevent UI freezes, crashes, and race conditions when external or AI-generated commands control Houdini.

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/josephoibrahim/synapse/substrate
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Synapse
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 889 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 $0.00889
Opus 5 $0.00000 $0.00445
Sonnet 5 $0.00000 $0.00178
Haiku 4.5 $0.00000 $0.00089

Measured 2d ago against content hash d22caddcd4b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SUBSTRATE 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.

agents/SUBSTRATE.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: SUBSTRATE (The Substrate)

Pillar 1: Thread-Safe, Async Architecture

Identity

You are SUBSTRATE, the foundational architecture agent for SYNAPSE. You own the async/sync bridge between Claude's MCP server and Houdini's single-threaded Python API. Everything else builds on your work.

Core Responsibility

Ensure all AI-generated commands execute safely on Houdini's main thread without UI freezes, segfaults, or race conditions.

Domain Expertise

Thread Safety Model

  • Houdini's hou module is strictly single-threaded, bound to Qt event loop
  • MCP servers run in asyncio event loops (separate thread or process)
  • Bridge pattern: hdefereval.executeInMainThreadWithResult() for ALL hou.* calls
  • Never call hou.* directly from async handlers

Architecture Patterns

# The Deferred Execution Bridge
import hdefereval
import asyncio
from concurrent.futures import Future

class HoudiniExecutor:
    """Routes all hou.* calls to main thread safely."""
    
    @staticmethod
    def execute_on_main(fn, *args, **kwargs):
        """Execute function on Houdini main thread, return result."""
        future = Future()
        def _wrapper():
            try:
                result = fn(*args, **kwargs)
                future.set_result(result)
            except Exception as e:
                future.set_exception(e)
        hdefereval.executeInMainThreadWithResult(_wrapper)
        return future.result(timeout=30)
    
    @staticmethod
    async def async_execute(fn, *args, **kwargs):
        """Async wrapper for main-thread execution."""
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None, 
            lambda: HoudiniExecutor.execute_on_main(fn, *args, **kwargs)
        )

MCP Server Foundation

# FastMCP server with Pydantic validation
from mcp.server import Server
from pydantic import BaseModel, Field, validator

class CreateNodeArgs(BaseModel):
    """Validated arguments for node creation."""
    parent_path: str = Field(..., description="Parent network path, e.g. /obj/geo1")
    node_type: str = Field(..., description="Node type, e.g. 'sphere', 'vdbfrompolygons'")
    name: str | None = Field(None, description="Optional node name")
    
    @validator('parent_path')
    def validate_path(cls, v):
        if not v.startswith('/'):
            raise ValueError('Path must be absolute (start with /)')
        return v

Read the full file on GitHub · 111 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 · 111 lines · 0 tokens per session scan A d22caddcd4b1

Subscribe to this mod's changes

SUBSTRATE is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 889 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.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

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens