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 AkshitIreddy/agent-skills --skill comfyui-assetsgit clone --depth 1 https://github.com/AkshitIreddy/agent-skillsWrote 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/akshitireddy/agent-skills/comfyui-assets)<a href="https://agentmods.dev/skills/akshitireddy/agent-skills/comfyui-assets"><img src="https://agentmods.dev/badge/skills/akshitireddy/agent-skills/comfyui-assets/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/akshitireddy/agent-skills/comfyui-assets"><img src="https://agentmods.dev/badge/skills/akshitireddy/agent-skills/comfyui-assets.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 | $0.00061 | $0.01212 |
| Opus 5 | $0.00030 | $0.00606 |
| Sonnet 5 | $0.00012 | $0.00242 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade B, and why
comfyui-assets scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const { prompt_id } = await (await fetch('http://127.0.0.1:8188/prompt', { method: 'POST', How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generating assets with a local ComfyUI
Drive ComfyUI through its HTTP API. You do not need a plugin or MCP server — there are three endpoints.
Talking to it
ComfyUI listens on 127.0.0.1:8188 by default. Start it headless from its venv:
python main.py --listen 127.0.0.1 --port 8188
The API takes a workflow in "API format" — a flat object of node-id → {class_type, inputs}. Export it from the UI with Workflow → Export (API), or hand-author it; it is plain JSON.
// queue
const { prompt_id } = await (await fetch('http://127.0.0.1:8188/prompt', {
method: 'POST',
headers: { 'content-type': 'application/json' },
body: JSON.stringify({ prompt: workflow, client_id: clientId }),
})).json();
// poll until it appears in history
let out;
while (!out) {
const hist = await (await fetch(`http://127.0.0.1:8188/history/${prompt_id}`)).json();
out = hist[prompt_id];
if (!out) await new Promise((r) => setTimeout(r, 700));
}
// fetch the produced files
for (const node of Object.values(out.outputs)) {
for (const img of node.images ?? []) {
const url = `http://127.0.0.1:8188/view?filename=${encodeURIComponent(img.filename)}`
+ `&subfolder=${encodeURIComponent(img.subfolder)}&type=${img.type}`;
// save the bytes
}
}
Batch by looping the queue call with a different seed/prompt each time — ComfyUI queues them and works through the list. Keep a modest concurrency (queue depth of a few) rather than firing hundreds at once.
Model choice
For stylised assets (illustration, painterly, game art), prefer SDXL: seconds per image, the deepest LoRA/ControlNet ecosystem. Reserve FLUX for when prompt adherence or legible text really matters — quantised it is roughly an order of magnitude slower per image, which dominates when you are generating and re-rolling a large library.
VRAM guide: SDXL ~8GB, FLUX fp8 ~12GB, FLUX GGUF Q4/Q5 ~6–8GB.
Seamless tiling
Use circular padding in the sampler (ComfyUI: a "seamless"/tiling option or the CircularVAEDecode-style nodes; several tiling custom nodes expose it). Do not fake it by mirroring — mirrored tiles read as obviously symmetrical.
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 · 92 lines · 61 tokens per session scan B 07a416365d7e
comfyui-assets is a skill published in the GitHub repository AkshitIreddy/agent-skills (1 stars, last pushed 15d ago), licensed MIT. It adds 61 tokens to every session and 1,212 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
ultralytics-platform
This skill should be used when user asks to "upload my model to Ultralytics Platform", "push this run to the platform", "upload a dataset to platform", "download a dataset from platform", "search platform datasets", "start cloud training", "train on platform GPUs", "export a model on platform", "deploy a model…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
character-animation-qa
Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.
mongodb-query-optimizer
Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.