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 sd-node-opsgit 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/sd-node-ops)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/sd-node-ops"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/sd-node-ops.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.05045 |
| Opus 5 | $0.00034 | $0.02523 |
| Sonnet 5 | $0.00013 | $0.01009 |
| Haiku 4.5 | $0.00007 | $0.00505 |
Grade A, and why
sd-node-ops 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 8d 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SD 节点操作
⚠️ 操作前必须先阅读
sd-operation-rules（含工作流 + 陷阱 + API 速查）
✅ 伪代码 → 节点映射
SD 材质图是有向数据流，用伪代码能完整描述。每行伪代码对应一个或一组节点：
# 伪代码
weave = mesh_1(tiling=20) + rotate(90°) # 编织骨架
smooth = blur(weave, intensity=2.0) # 软化
warped = warp(weave, perlin_noise, intensity=0.05) # 有机化
color = gradient_map(warped, dark→light) # 着色
# 节点映射
pattern_mesh_1.sbs → mesh_1
sbs::compositing::transformation → rotate 90°
sbs::compositing::blur → smooth
noise_perlin_noise.sbs → perlin_noise
sbs::compositing::warp → warped
sbs::compositing::gradient (colorswitch=True) → color
1. 原子节点
原子节点是处理节点（调整/混合/变形），不是纹理生成器。
node = graph.newNode("sbs::compositing::levels")
node.setPosition(float2(0, 0))
常用原子节点
| 节点 | 定义 ID | 用途 |
|---|---|---|
| Blend | sbs::compositing::blend |
混合两个输入 |
| Levels | sbs::compositing::levels |
色阶/对比度调整 |
| Normal | sbs::compositing::normal |
灰度高度图→法线图 |
| Warp | sbs::compositing::warp |
扭曲（gradient=灰度） |
| DirectionalWarp | sbs::compositing::directionalwarp |
方向扭曲（intensity=灰度） |
| Uniform | sbs::compositing::uniform |
纯色（灰度或彩色） |
| Output | sbs::compositing::output |
PBR 输出通道 |
| Curve | sbs::compositing::curve |
曲线调整 |
| HSL | sbs::compositing::hsl |
HSL 颜色调整 |
| Blur | sbs::compositing::blur |
模糊 |
| Sharpen | sbs::compositing::sharpen |
锐化 |
sbs::compositing::invert |
⛔ 不存在！ newNode 返回 None。用 Levels（黑白点互换）或 Blend(Subtract)+Uniform(白) 代替 | |
| Transform 2D | sbs::compositing::transformation |
平移/旋转/缩放 |
| Gradient Map | sbs::compositing::gradient |
灰度→彩色渐变映射 |
| Emboss | sbs::compositing::emboss |
浮雕 |
| Edge Detect | sbs::compositing::edgedetect |
边缘检测 |
2. 库节点（噪波/纹理生成器）🔴
所有纹理生成节点都是库节点，从 SD 安装目录的 .sbs 文件加载。
加载方式（内联写法，不要用 def）
import os
pm = app.getPackageMgr()
base = r"C:\Program Files\Adobe\Adobe Substance 3D Designer\resources\packages"
# 加载 .sbs 包
path = os.path.join(base, "noise_perlin_noise.sbs")
pkg = pm.getUserPackageFromFilePath(path)
if not pkg:
pkg = pm.loadUserPackage(path)
# 获取图资源并创建实例
res = pkg.getChildrenResources(False)[0]
node = graph.newInstanceNode(res)
node.setPosition(float2(-800, 0))
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.
- 8d ago First seen · 428 lines · 67 tokens per session scan A 166fe3abb6fb
sd-node-ops is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 5,045 once invoked, about $0.0003 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
commercial-3d-product-render
Product lookdev and render-review helpers for commercial 3D work.
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…