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 agentmods add skills/mckruz/comfyui-expert/comfyui-apinpx skills add MCKRUZ/ComfyUI-Expert --skill comfyui-apigit clone --depth 1 https://github.com/MCKRUZ/ComfyUI-ExpertWrote 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/mckruz/comfyui-expert/comfyui-api)<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-api"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-api.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 | $0.00051 | $0.01282 |
| Opus 5 | $0.00026 | $0.00641 |
| Sonnet 5 | $0.00010 | $0.00256 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
comfyui-api scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: {"openclaw":{"emoji":"🔌","os":["darwin","linux","win32"],"requires":{"anyBins":["curl","wget"]},"primaryEnv":"COMFYUI_URL"}} How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI API Skill
Connect to ComfyUI's REST API to execute workflows, monitor progress, and retrieve outputs.
Configuration
- Default URL:
http://127.0.0.1:8188 - Custom URL: Set in project manifest or pass as parameter
- Timeout: 30s for API calls, no timeout for generation polling
Two Modes
Online Mode (ComfyUI Running)
Full API access. Preferred mode for interactive work.
- Test connection:
GET /system_stats - Discover capabilities: Use
comfyui-inventoryskill - Queue workflow:
POST /prompt - Poll for results:
GET /history/{prompt_id}every 5 seconds - Retrieve outputs:
GET /view?filename=...
Offline Mode (No Server)
Export workflow JSON for manual loading in ComfyUI.
- Generate workflow JSON following ComfyUI's format
- Save to
projects/{project}/workflows/{name}.json - Instruct user to drag-drop into ComfyUI
API Operations
Check Server Status
curl http://127.0.0.1:8188/system_stats
Response fields:
system.os: Operating systemsystem.comfyui_version: Version stringdevices[0].name: GPU namedevices[0].vram_total: Total VRAM bytesdevices[0].vram_free: Free VRAM bytes
Queue a Workflow
curl -X POST http://127.0.0.1:8188/prompt \
-H "Content-Type: application/json" \
-d '{"prompt": WORKFLOW_JSON, "client_id": "video-agent"}'
WORKFLOW_JSON format:
{
"1": {
"class_type": "LoadCheckpoint",
"inputs": {
"ckpt_name": "flux1-dev.safetensors"
}
},
"2": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "photorealistic portrait...",
"clip": ["1", 1]
}
}
}
Each node is keyed by a string ID. Inputs reference other nodes as ["{node_id}", {output_index}].
Response:
{"prompt_id": "abc-123-def", "number": 1}
Poll for Completion
curl http://127.0.0.1:8188/history/abc-123-def
Incomplete: Returns {} (empty object)
Complete: Returns execution data with outputs:
{
"abc-123-def": {
"outputs": {
"9": {
"images": [{"filename": "ComfyUI_00001.png", "subfolder": "", "type": "output"}]
}
},
"status": {"completed": true}
}
}
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.
- 6d ago First seen · 174 lines · 51 tokens per session scan A efce79b1633f
comfyui-api is a skill published in the GitHub repository MCKRUZ/ComfyUI-Expert (91 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,282 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-media-generator
為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞,並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0/2.5、Suno v5.5、Seedream 5.0/4.0、Vidu Q3、Midjourney V8.1、Flux 1.1 Pro / Kontext、Runway Gen-4.5 / Aleph、Google Veo 3.1、Ideogram 3、Nano Banana Pro、Stable Diffusion 3.5(⚠️ OpenAI Sora 2 已於 2026-04-26 停運,API 撐到 2026-09-24,預設改推…
Prompt craft for ComfyUI generation
Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…
handoff
Work with Master Canvas AI video handoff packages. Use when a user provides a Master Canvas ZIP or projectmanifest.json and wants Hermes to inspect assets, preserve scene and shot order, prepare ComfyUI/LTX 2.3 jobs, or hand off prompts to Kling, Veo, or another video generation operator. Also use when a user wants…
local-ai-film
用本地或云端模型生产 AI 短片(氛围片/情绪片/预告片/vlog/带对白的剧情片)。导演总控入口:管开片决策、反同质化、踩坑规避、执行流程、后期总装。 触发场景:「做一部短片」「生成一个 XX 风格的视频」「跑一批氛围视频」「用 LTX/Wan/H3/可灵 出片」「AI 短片」「AI 剧情片」。 风格、时长、结构每次由需求决定,不预设。模型参数由 profile 决定,不写死。 不适用于:单张配图、已有实拍素材的剪辑。 Produce AI short films with local or cloud models. Directing hub: shot decisions, anti-homogenization…
rhythm-density
当用户有多个本地生成的短镜头,要决定"每镜多长、怎么排布"才有节奏感时调用;尤其想做"长镜头"呼吸感却受限于单镜时长上限时。核心:高能段压到疏密比的短端快切,首尾放慢做呼吸;单镜时长上限由 profile 的 maxshotsec 决定,不是固定数值;上限之下用同机位连续两镜+极缓运镜拼接制造"伪长镜"。 不适用于:音效/调色/BGM决策(见 editing-triad)、生成阶段镜头筛选(见 shot-breakdown)、单镜头光位机位描述(见 emotion-to-camera-language)。 也不适用于旁白驱动的科普/教程片剪辑刀数决策(见…