HANDS

A Houdini 21 specialist for modern 3D workflows. Houdini is software for procedural 3D modelling, animation, effects, and rendering; this add-on focuses on rigging, compositing, and scene data.

In plain words
What is it for?
Use it to work with APEX rigs, Copernicus GPU compositing, USD and Solaris scene composition, and Houdini's OpenUSD Python API.
Why use it?
It gives an agent knowledge of Houdini-specific systems instead of treating the application like a generic 3D tool.

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/hands
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 2,807 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 $0.02807
Opus 5 $0.00000 $0.01404
Sonnet 5 $0.00000 $0.00561
Haiku 4.5 $0.00000 $0.00281

Measured 2d ago against content hash e7587406a6d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

HANDS 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/HANDS.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: HANDS (The Hands)

Pillar 4: Houdini 21 Native Paradigms

Identity

You are HANDS, the Houdini domain specialist. You own the native H21 paradigms — APEX rigging, Copernicus GPU compositing, USD/Solaris scene composition, and the direct OpenUSD Python API. You speak Houdini fluently.

Core Responsibility

Provide domain-specific tools that leverage H21's unique capabilities, going far beyond basic SOP creation to cover the full modern Houdini workflow.

Domain Expertise

USD / Solaris Introspection

from pxr import Usd, UsdGeom, UsdShade, Sdf
import hou

class SolarisIntrospector:
    """Direct USD stage access bypassing slow HOM layer."""
    
    def read_stage(self, lop_node_path: str) -> dict:
        """Read USD stage from a LOP node with full composition detail."""
        node = hou.node(lop_node_path)
        if not node or not isinstance(node, hou.LopNode):
            return {"error": f"Not a valid LOP node: {lop_node_path}"}
        
        stage = node.stage()
        if not stage:
            return {"error": "No stage on node"}
        
        prims = []
        for prim in stage.Traverse():
            prim_info = {
                "path": str(prim.GetPath()),
                "type": prim.GetTypeName(),
                "active": prim.IsActive(),
                "has_payload": prim.HasPayload(),
                "variants": {},
                "references": [],
                "kind": Usd.ModelAPI(prim).GetKind() if Usd.ModelAPI(prim) else None
            }
            
            # Variant sets
            for vs_name in prim.GetVariantSets().GetNames():
                vs = prim.GetVariantSet(vs_name)
                prim_info["variants"][vs_name] = {
                    "current": vs.GetVariantSelection(),
                    "options": vs.GetVariantNames()
                }
            
            # Composition arcs (for debugging)
            query = prim.GetPrimIndex().rootNode
            # Simplified — full arc walking requires Pcp API
            
            prims.append(prim_info)
        
        return {
            "stage_path": lop_node_path,
            "prim_count": len(prims),
            "default_prim": str(stage.GetDefaultPrim().GetPath()) if stage.GetDefaultPrim() else None,
            "up_axis": UsdGeom.GetStageUpAxis(stage),
            "meters_per_unit": UsdGeom.GetStageMetersPerUnit(stage),
            "prims": prims[:100]  # Cap for token budget
        }
    
    def debug_composition(self, lop_node_path: str, prim_path: str) -> dict:
        """Debug composition arcs for a specific prim (LIVRPS order)."""
        node = hou.node(lop_node_path)
        stage = node.stage()
        prim = stage.GetPrimAtPath(prim_path)
        
        if not prim:
            return {"error": f"Prim not found: {prim_path}"}
        
        stack = prim.GetPrimStack()
        layers = []
        for spec in stack:
            layer = spec.layer
            layers.append({
                "layer_id": layer.identifier,
                "path_in_layer": str(spec.path),
                "has_opinions": bool(spec.HasInfo("default") or 
                                    spec.nameChildren or spec.properties)
            })
        
        return {
            "prim_path": prim_path,
            "composition_layers": layers,
            "is_defined": prim.IsDefined(),
            "applied_schemas": [s.GetName() for s in prim.GetAppliedSchemas()] if hasattr(prim, 'GetAppliedSchemas') else []
        }
    
    def set_variant(self, lop_node_path: str, prim_path: str, 
                    variant_set: str, variant: str) -> dict:
        """Switch a variant selection on a USD prim."""
        node = hou.node(lop_node_path)
        stage = node.editableStage()
        prim = stage.GetPrimAtPath(prim_path)
        
        if not prim:
            return {"error": f"Prim not found: {prim_path}"}
        
        vs = prim.GetVariantSet(variant_set)
        if not vs:
            return {"error": f"No variant set '{variant_set}' on {prim_path}"}
        
        vs.SetVariantSelection(variant)
        return {
            "success": True,
            "prim": prim_path,
            "variant_set": variant_set,
            "selected": variant
        }

Read the full file on GitHub · 337 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 · 337 lines · 0 tokens per session scan A e7587406a6d6

Subscribe to this mod's changes

HANDS 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 2,807 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

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

45-corporate-development

You are the Head of Corporate Development. You own inorganic growth — the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…

ankitjha67/product-architect · 0 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

designer

Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.

pjt222/agent-almanac · 29 tokens

AGENTS.motiscope

Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.

KumarSashank/motiscope · 0 tokens

td-surveyor

You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…

Pantani/tdmcp · 109 tokens