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-capturegit 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-capture)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/sd-node-capture"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/sd-node-capture/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/sd-node-capture"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/sd-node-capture.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 | $0.00106 | $0.01476 |
| Opus 5 | $0.00053 | $0.00738 |
| Sonnet 5 | $0.00021 | $0.00295 |
| Haiku 4.5 | $0.00011 | $0.00148 |
Grade A, and why
sd-node-capture 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 9d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SD 节点输出捕获与视觉分析
核心机制
save_preview — 预注入的截图函数
save_preview 是预注入到 exec 命名空间的辅助函数,自动完成:缩放 1/4 → jpg 压缩 → [IMAGE:] 标记输出。
AI 在 tool result 中可直接看到图片。
# 最简用法:传入节点,自动截图
node = graph.getNodeFromId("node_id")
save_preview(node, "height")
# 传入纹理对象也行
tex = node.getPropertyValue(out_props[0]).get()
save_preview(tex, "height")
# 自定义缩放比(默认 4 即 1/4)
save_preview(node, "height_hires", scale=2) # 1/2 大小
save_preview(node, "height_full", scale=1) # 原始大小
参数:
| 参数 | 类型 | 默认 | 说明 |
|---|---|---|---|
texture_or_node |
SDTexture / SDNode | 必填 | 传 node 时自动取第一个输出端口 |
label |
str | "preview" | 显示标签,也用于文件名 |
scale |
int | 4 | 缩小倍数(1=原始, 2=半, 4=四分之一) |
quality |
int | 80 | JPEG 质量 |
[IMAGE:path] 标记(底层机制)
save_preview 内部调用 print(f"[IMAGE:{path}]"),MCP Server 自动将图片 base64 嵌入返回。
也可以手动使用这个标记:
tex.save("path/to/file.jpg")
print(f"[IMAGE:path/to/file.jpg]") # AI 看到图片
操作示例
1. 截图单个节点
node = graph.getNodeFromId("1567699435")
save_preview(node, "weave_pattern")
2. 截取所有 PBR 输出
output_nodes = graph.getOutputNodes()
for i in range(output_nodes.getSize()):
on = output_nodes.getItem(i)
usage = "unknown"
try:
val = on.getAnnotationPropertyValueFromId("identifier")
if val:
usage = str(val.get()) if hasattr(val, 'get') else str(val)
except Exception:
pass
save_preview(on, f"output_{usage}")
3. 截取关键中间节点
check_nodes = {
"1567699435": "weave_pattern",
"1567699547": "height_levels",
"1567699553": "final_blend",
}
for nid, label in check_nodes.items():
node = graph.getNodeFromId(nid)
if node:
save_preview(node, label)
else:
print(f"节点 {nid} ({label}) 未找到")
4. 多输出端口的库节点
node = graph.getNodeFromId("target_node_id")
if node:
out_props = node.getProperties(SDPropertyCategory.Output)
for p in out_props:
port_id = p.getId()
val = node.getPropertyValue(p)
if val:
tex = val.get()
if tex:
save_preview(tex, f"port_{port_id}")
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.
- 9d ago First seen · 177 lines · 106 tokens per session scan A 38c678a0dba2
sd-node-capture is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 106 tokens to every session and 1,476 once invoked, about $0.0005 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.