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 IvanYangYangXi/artclaw_bridge --skill houdini-operation-rulesgit clone --depth 1 https://github.com/IvanYangYangXi/artclaw_bridgeWrote 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/ivanyangyangxi/artclaw_bridge/houdini-operation-rules)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/houdini-operation-rules"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/houdini-operation-rules/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/ivanyangyangxi/artclaw_bridge/houdini-operation-rules"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/houdini-operation-rules.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 | $0.00128 | $0.02126 |
| Opus 5 | $0.00064 | $0.01063 |
| Sonnet 5 | $0.00026 | $0.00425 |
| Haiku 4.5 | $0.00013 | $0.00213 |
Grade A, and why
houdini-operation-rules 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 12d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Houdini 操作通用规则
所有涉及 Houdini 场景修改的操作都必须遵守以下规则。
⚠️ 仅适用于 Houdini — 通过
run_python执行,使用hou模块
🌐 规则 0:坐标系
Houdini 使用 Y-Up 右手坐标系(与 Maya 一致):
| 轴 | 方向 | 说明 |
|---|---|---|
| X | 右 (Right) | 屏幕右侧 |
| Y | 上 (Up) | 垂直向上 |
| Z | 前/外 (Forward) | 朝向屏幕外(面向你) |
右手系判定:右手拇指指向 X(右),食指指向 Y(上),中指指向 Z(屏幕外)。
与其他 DCC 的换算:
- 与 Maya:坐标轴方向一致,无需转换
- 到 UE (Z-Up 左手系):Houdini Y → UE Z,Houdini Z → UE -Y
- 到 3ds Max (Z-Up 右手系):Houdini Y → Max Z,Houdini Z → Max -Y
import hou
# Houdini 坐标示例
node = hou.node("/obj/geo1")
node.parm("tx").set(100) # X = 右 100
node.parm("ty").set(50) # Y = 上 50
node.parm("tz").set(0) # Z = 前 0
🔄 规则 1:Undo 包装(强制)
所有修改操作必须包裹在 undo group 中,确保用户可以一次 Ctrl+Z 撤销整个操作。
import hou
with hou.undos.group("ArtClaw: 操作描述"):
# ... 所有修改操作放在这里 ...
geo = hou.node("/obj").createNode("geo", "my_geo")
box = geo.createNode("box", "my_box")
⚠️ 禁止在 undo group 外直接执行场景修改操作。
🔗 规则 2:节点操作基础
Houdini 以节点网络为核心,几乎所有操作都是创建/连接/设置节点参数。
获取节点
node = hou.node("/obj/geo1") # 通过完整路径获取
children = node.children() # 获取子节点列表
child = node.node("box1") # 获取相对路径子节点
创建节点
parent = hou.node("/obj/geo1")
box = parent.createNode("box", "my_box") # (节点类型, 节点名称)
xform = parent.createNode("xform", "move_up") # 创建 Transform 节点
连接节点
# xform 的第 0 个输入 ← box 的第 0 个输出
xform.setInput(0, box, 0)
# 多输入节点(如 merge)
merge = parent.createNode("merge")
merge.setInput(0, box, 0)
merge.setInput(1, sphere, 0)
设置参数
box.parm("sizex").set(2.0) # 标量参数
box.parm("scale").set(1.5)
xform.parmTuple("t").set((0, 5, 0)) # 向量参数(translate)
布局节点
parent.layoutChildren() # 自动排列所有子节点
设置显示/渲染标记
node.setDisplayFlag(True) # 蓝色显示标记
node.setRenderFlag(True) # 紫色渲染标记
🍳 规则 3:Cook 机制
- Houdini 的节点修改后需要 cook 才能计算出结果
- 大部分参数修改会自动触发 cook,无需手动干预
- 需要强制 cook 时:
node.cook(force=True)
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.
- 12d ago First seen · 254 lines · 128 tokens per session scan A 534437be0559
houdini-operation-rules is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 128 tokens to every session and 2,126 once invoked, about $0.0006 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 2026-08-30.
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-cua
A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…
clawhub-compat
Example skill — demonstrates full compatibility with the ClawHub/OpenClaw skill format. Use as a reference when creating skills for both the dcc-mcp-core ecosystem and ClawHub marketplace. Not intended for production use — this is an authoring reference only.
example-layered-skill
Example skill — reference implementation of the internal layered architecture pattern (Tools / Services / Utils) for complex skills with shared business logic. Use as a template when a skill outgrows a single scripts/execute.py file. Not intended for production use — see docs/guide/skills.md for the architectural…
marketplace-create-extension
Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.