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 comfyui-inpaintinggit 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/comfyui-inpainting)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/comfyui-inpainting"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/comfyui-inpainting/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/comfyui-inpainting"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/comfyui-inpainting.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 | $0.00065 | $0.01734 |
| Opus 5 | $0.00032 | $0.00867 |
| Sonnet 5 | $0.00013 | $0.00347 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
comfyui-inpainting 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI 局部重绘 (Inpainting)
修改图像的特定区域,保持其他部分不变。
预注入变量
run_python 已注入:submit_workflow, save_preview
核心概念
局部重绘需要:
- 原图 - 要修改的图像
- 遮罩 (Mask) - 标记要修改的区域(白色=修改,黑色=保持)
- 提示词 - 描述修改后的内容
使用方法
方法 1: 使用便捷函数
from comfyui_inpainting import build_inpaint_workflow
wf = build_inpaint_workflow(
image_path="original.png",
mask_path="mask.png", # 白色区域会被重绘
prompt="beautiful red dress", # 修改后的内容
negative_prompt="low quality",
checkpoint="sdxl_base.safetensors",
denoise=1.0, # 1.0 = 完全重绘遮罩区域
seed=42
)
result = submit_workflow(wf)
if result.get("images"):
save_preview(result["images"][0])
方法 2: 分步构建
import random
wf = {}
# 1. 加载模型
wf["1"] = {"class_type": "CheckpointLoaderSimple", "inputs": {"ckpt_name": "sdxl.safetensors"}}
# 2. 加载原图和遮罩
wf["2"] = {"class_type": "LoadImage", "inputs": {"image": "original.png"}}
wf["3"] = {"class_type": "LoadImageMask", "inputs": {"image": "mask.png", "channel": "alpha"}}
# 3. 编码提示词
wf["4"] = {"class_type": "CLIPTextEncode", "inputs": {"text": "beautiful red dress", "clip": ["1", 1]}}
wf["5"] = {"class_type": "CLIPTextEncode", "inputs": {"text": "low quality", "clip": ["1", 1]}}
# 4. VAE 编码原图
wf["6"] = {"class_type": "VAEEncode", "inputs": {"pixels": ["2", 0], "vae": ["1", 2]}}
# 5. 设置潜空间噪波(只在遮罩区域)
wf["7"] = {
"class_type": "SetLatentNoiseMask",
"inputs": {
"samples": ["6", 0],
"mask": ["3", 0]
}
}
# 6. 采样(只在遮罩区域重绘)
wf["8"] = {
"class_type": "KSampler",
"inputs": {
"model": ["1", 0],
"positive": ["4", 0],
"negative": ["5", 0],
"latent_image": ["7", 0],
"seed": random.randint(0, 2**32),
"steps": 25,
"cfg": 7.0,
"sampler_name": "euler",
"scheduler": "normal",
"denoise": 1.0 # 只在遮罩区域生效
}
}
# 7. 解码保存
wf["9"] = {"class_type": "VAEDecode", "inputs": {"samples": ["8", 0], "vae": ["1", 2]}}
wf["10"] = {"class_type": "SaveImage", "inputs": {"images": ["9", 0], "filename_prefix": "inpaint"}}
result = submit_workflow(wf)
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 · 261 lines · 65 tokens per session scan A 384be6f87a55
comfyui-inpainting is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 1,734 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
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.