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-model-managergit 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-model-manager)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/comfyui-model-manager"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/comfyui-model-manager/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-model-manager"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/comfyui-model-manager.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 | $0.00082 | $0.01090 |
| Opus 5 | $0.00041 | $0.00545 |
| Sonnet 5 | $0.00016 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
comfyui-model-manager 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 11d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI 模型管理器
管理 ComfyUI 的模型文件:查询、下载、删除。
预注入变量
run_python 已注入:folder_paths, client
核心功能
1. 列出模型
from comfyui_model_manager import list_models
# 列出所有 checkpoints
checkpoints = list_models("checkpoints")
print(f"找到 {len(checkpoints)} 个 checkpoints")
for ckpt in checkpoints[:10]:
print(f" - {ckpt}")
# 列出 LoRA
loras = list_models("loras")
print(f"\n找到 {len(loras)} 个 LoRA")
2. 搜索模型
from comfyui_model_manager import search_models
# 本地搜索
results = search_models("sdxl", model_type="checkpoints")
print(f"本地找到 {len(results)} 个匹配")
3. 下载模型
from comfyui_model_manager import download_model
# 从 URL 下载
result = download_model(
url="https://civitai.com/api/download/models/12345",
model_type="loras",
filename="my_lora.safetensors"
)
print(result)
# {
# "success": True,
# "path": ".../models/loras/my_lora.safetensors",
# "size": "145.2 MB"
# }
4. CivitAI 搜索下载
from comfyui_model_manager import search_civitai, download_from_civitai
# 搜索
results = search_civitai(
query="anime style",
model_type="LORA",
sort="Most Downloaded"
)
# 下载第一个
if results:
model = results[0]
download_from_civitai(
model_id=model["id"],
save_path=f"models/loras/{model['name']}.safetensors"
)
5. 删除模型
from comfyui_model_manager import delete_model
delete_model("old_model.safetensors", model_type="checkpoints")
支持的模型类型
| 类型 | folder_paths 参数 | 说明 |
|---|---|---|
| Checkpoints | checkpoints |
主模型 |
| LoRA | loras |
LoRA 模型 |
| VAE | vae |
VAE 模型 |
| ControlNet | controlnet |
ControlNet 模型 |
| CLIP | clip |
CLIP 模型 |
| CLIP Vision | clip_vision |
CLIP Vision |
| Upscale | upscale_models |
超分模型 |
| Embeddings | embeddings |
Textual Inversion |
完整示例
下载并使用新模型
# 1. 检查模型是否存在
from comfyui_model_manager import model_exists
if not model_exists("sdxl_anime.safetensors", "checkpoints"):
print("模型不存在,开始下载...")
# 2. 从 CivitAI 搜索
from comfyui_model_manager import search_civitai
results = search_civitai("sdxl anime", model_type="Checkpoint")
if results:
# 3. 下载
from comfyui_model_manager import download_from_civitai
download_from_civitai(
model_id=results[0]["id"],
model_type="checkpoints"
)
else:
print("模型已存在")
# 4. 在 workflow 中使用
ckpts = folder_paths.get_filename_list("checkpoints")
print(f"可用 checkpoints: {ckpts}")
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.
- 11d ago First seen · 185 lines · 82 tokens per session scan A 8c6f83af686e
comfyui-model-manager is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 1,090 once invoked, about $0.0004 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.