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 max-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/max-operation-rules)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/max-operation-rules"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/max-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/max-operation-rules"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/max-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 | $0.00117 | $0.01406 |
| Opus 5 | $0.00059 | $0.00703 |
| Sonnet 5 | $0.00023 | $0.00281 |
| Haiku 4.5 | $0.00012 | $0.00141 |
Grade A, and why
max-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 10d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3ds Max 操作通用规则
所有涉及 3ds Max 场景修改的操作都必须遵守以下规则。
⚠️ 仅适用于 3ds Max — 通过
run_python执行
🌐 规则 0:坐标系
3ds Max 使用 Z-Up 右手坐标系:
| 轴 | 方向 | 说明 |
|---|---|---|
| X | 右 (Right) | 屏幕右侧 |
| Y | 屏幕里 (Away from Viewer) | 面向屏幕时指向屏幕深处 |
| Z | 上 (Up) | 垂直向上 |
右手系判定:右手拇指指向 X(右),食指指向 Y(屏幕里),中指指向 Z(上)。
注意:Max 的 Y 轴方向与 Maya 正好相反(Max Y 指向屏幕里,Maya Z 指向屏幕外)。
与其他 DCC 的换算:
- 导出到 UE (Z-Up 左手系):Max Y → UE -Y(Max 右手系 Y 对应 UE 左手系 -Y)。Z 轴相同(都是 Up)
- 导出到 Maya (Y-Up 右手系):Max Z → Maya Y,Max Y → Maya -Z
- FBX 导出时 Max 默认 Z-Up,UE 导入时自动处理手系转换
from pymxs import runtime as rt
# Max 坐标示例
box = rt.Box()
box.pos = rt.Point3(10, 20, 5) # X=右10, Y=屏幕里20, Z=上5
box.rotation = rt.EulerAngles(45, 0, 0) # 绕 X 轴旋转 45°
🔄 规则 1:批量操作使用 Undo 管理
使用 theHold 或 undo() 上下文确保操作可撤销。
from pymxs import runtime as rt
# 方式 1:undo 上下文(推荐)
with rt.undo(True, 'ArtClaw_BatchOperation'):
# ... 所有修改操作 ...
pass
# 方式 2:MAXScript undo
rt.execute('undo "ArtClaw Op" on ( /* operations */ )')
何时使用 Undo 包裹
- 涉及多个对象或多步操作时必须使用
- 单个简单操作(如移动一个物体)可以不包裹
- 避免在循环中逐个开关 undo——包裹整个循环
🖨️ 规则 2:输出方式
Max Python 中 print 输出到 MAXScript Listener。确保重要信息用 print 输出。
# ✅ 输出到 Listener
print("操作完成: 已修改 5 个对象")
💡 规则 3:提示用户可撤销
对场景进行修改后,应告知用户:
- 所有操作支持 Ctrl+Z 撤销
- 如果使用了 undo 块,说明整个批量操作可以一次撤销
📋 规则 4:操作前确认(破坏性操作)
以下操作执行前应向用户确认:
- 删除节点/对象(除非用户明确指示)
- 批量修改属性(超过 10 个对象)
- 重置场景 / 塌陷修改器堆栈
非破坏性操作(调整参数、移动位置等)可以直接执行。
📂 规则 5:中文版 Max 路径注意
3ds Max 中文版的脚本/插件路径可能包含 locale 子目录:
# 常见 locale 目录
CHS/ (简体中文)
ENU/ (英文)
JPN/ (日文)
安装脚本时应自动检测 locale 目录并同步部署。
🔧 标准操作收尾模板
from pymxs import runtime as rt
with rt.undo(True, 'ArtClaw_Operation'):
# ... 所有操作代码 ...
pass
print("✅ 操作完成")
# 提示:可用 Ctrl+Z 撤销
🧠 规则 6:记忆系统集成
反复出错时主动查记忆 (强制)
当同一类操作连续失败 2 次以上时,必须先搜索记忆再继续尝试:
from core.memory_store import get_memory_store
mm = get_memory_store()
if mm:
hints = mm.manager.search("相关关键词", tag="crash", limit=3)
hints += mm.manager.search("相关关键词", tag="pattern", limit=3)
team = mm.manager.search_team_memory("相关关键词", limit=3)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 178 lines · 117 tokens per session scan A 2689fde8785b
max-operation-rules is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 117 tokens to every session and 1,406 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…
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…
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.
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.
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…
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.