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 artokun/comfyui-mcp --skill lora-managergit clone --depth 1 https://github.com/artokun/comfyui-mcpWrote 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/artokun/comfyui-mcp/lora-manager)<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/lora-manager"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/lora-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/artokun/comfyui-mcp/lora-manager"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/lora-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.00808 |
| Opus 5 | $0.00032 | $0.00404 |
| Sonnet 5 | $0.00013 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
lora-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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI-LoRA-Manager
ComfyUI-LoRA-Manager (willmiao)
registers Vue autocomplete widgets via getCustomWidgets(). Those widgets
are healthy in the ComfyUI menu, and drag-from-palette works, but panel_add_node
cannot add the nodes that require them.
The add-node guard polls app.widgets for a constructor. ComfyUI 1.49+ stores
getCustomWidgets() results in the frontend widget store, not on app.widgets.
The wait always expires after 5s. Reload, panel_refresh_nodes, and retry
cannot clear it. That refusal is not a missing pack.
Which nodes panel_add_node will actually add
| Works | Refuses (AUTOCOMPLETE_TEXT_*) |
|---|---|
LoRA Text Loader (LoraManager) |
Lora Loader (LoraManager) |
core LoraLoader |
Lora Stacker (LoraManager) |
core LoraLoaderModelOnly |
WanVideo Lora Select (LoraManager) |
Text (LoraManager) |
|
Prompt (LoraManager) |
LoRA Text Loader (LoraManager) is the same backend as Lora Loader (LoraManager) (MODEL / CLIP / trigger_words / loaded_loras). The difference
is the LoRA input: lora_syntax is a STRING socket (forceInput), so a
regular string node or panel_set_widget can drive it.
Syntax (spaces or punctuation between entries):
<lora:lora_name:strength>
<lora:lora_name:model_strength:clip_strength>
Recipe — stack a LoRA from the panel
panel_add_node(class_type="LoRA Text Loader (LoraManager)"). Do not addLora Loader (LoraManager); it will wait 5s and refuse.- Wire
MODEL(andCLIPif you have one) through it. - Drive
lora_syntaxwithpanel_set_widgetor a wired STRING, e.g.<lora:style/foo.safetensors:0.8>. - Put the node's
trigger_wordsoutput into the prompt if the sidecar has any.
If LoRA Manager is not installed, use core LoraLoader and set lora_name /
strength_model / strength_clip as usual.
Gotchas
- The refusal names a tab reload. Do not follow that. The constructor will
never appear on
app.widgets. panel_set_widgetontextafter a refused add never runs, because nothing was created. The working widget name islora_syntax.- A freshly added Text Loader still needs
lora_syntaxwritten; an empty string loads no LoRA.
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 · 65 lines · 63 tokens per session scan A 0f778e108fe4
lora-manager is a skill published in the GitHub repository artokun/comfyui-mcp (735 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 808 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
c2pa-metadata
Embed a C2PA provenance manifest into an AI-generated marketing asset (PNG, JPG, WebP, GIF, TIFF, MP4, MOV, WebM, MP3, WAV, PDF) via scripts/embed-c2pa.py — produces a signed copy of the file carrying IPTC digital-source-type AI claims, an optional c2pa.ai-disclosure assertion for EU AI Act Article 50 (applicable 2…
AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI
Generate images and videos from text with multi-provider routing — supports GPT Image 2.0 (near-perfect text rendering), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (unified photorealistic + anime), Flux 2 Klein (cheap drafts), Seedance 2.0 / Veo 3.1 / Grok Video / Agnes Video, and local ComfyUI workflows. Includes…
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
video-content
Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a…
comfyui-skill-openclaw
Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities. Use this Skill when: (1) The user requests to "generate an image", "draw a picture", or "execute a ComfyUI workflow". (2) The user has…
comfy
Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP server. Cloud-only — connects to the hosted service, not a local ComfyUI install. Use for any "generate/edit an image"…