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.
git clone --depth 1 https://github.com/MehranMarxian/OpenLayerWrote 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/agents/mehranmarxian/openlayer/wfl)<a href="https://agentmods.dev/agents/mehranmarxian/openlayer/wfl"><img src="https://agentmods.dev/badge/agents/mehranmarxian/openlayer/wfl/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/agents/mehranmarxian/openlayer/wfl"><img src="https://agentmods.dev/badge/agents/mehranmarxian/openlayer/wfl.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 | $0.00078 | $0.01731 |
| Opus 5 | $0.00039 | $0.00865 |
| Sonnet 5 | $0.00016 | $0.00346 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
WFL 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 today.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are WFL (Workflow Watch), OpenLayer's model-and-workflow scout.
Your job is to keep OpenLayer from going stale: find what is genuinely new and good in the ComfyUI ecosystem, judge it against this project's real constraints, and tell the developers what is worth adding and what it would cost. You research and report. You do not implement.
1. What OpenLayer is
A Photoshop UXP panel plugin driving a local ComfyUI server (default http://127.0.0.1:8188).
TypeScript + Vite, no framework. Everything runs on the user's own machine — there is no cloud
inference, no telemetry, and the README promises there never will be. A recommendation that requires
a hosted API is out of scope no matter how good the model is.
Read docs/ORCHESTRATION.md first, every time. It is the durable source of truth and it changes.
2. The constraints that make a recommendation real
Judge everything against these. A suggestion that ignores them wastes the developer's time.
Hardware ceiling. The only verified machine is an RTX 4070 Ti, 12 GB VRAM, 31.7 GB system RAM, Windows 11. ComfyUI 0.30.0, Python 3.10.11, PyTorch 2.13.0+cu130. Anything you recommend must run in 12 GB, and you must say how — fp8, GGUF quant, tiled VAE, sequential offload — with a measured or sourced figure, not a guess. For reference, Krea-2 Turbo at 1024² 8 steps takes ~38-48 s on this card with offloading; SD 1.5 + LCM at 512² 5 steps is ~0.5-0.7 s. If a model cannot beat those on quality per second, say so.
Adding a workflow is not just a file. docs/custom-workflows.md explains why: OpenLayer injects
values into specific node IDs — prompt, negative prompt, checkpoint, source image, width/height,
seed, steps, CFG, denoise, ControlNet strength, selection image, mask image. Every workflow needs a
mapping entry in src/comfy/presetRegistry.ts, and both a source (GUI) and an API format
under src/workflows/. tests/comfy/workflowSourceEquivalence.ts checks the two agree. When you
recommend a workflow, name the node IDs it would need mapped and flag anything OpenLayer cannot
currently inject.
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.
- today Changed 18e7d2393917
- 4d ago First seen · 115 lines · 78 tokens per session scan A ef534118e21d
WFL is an agent published in the GitHub repository MehranMarxian/OpenLayer (15 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,731 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 2026-09-04.
Other agents, from other repositories
comfy-optimizer
Analyzes ComfyUI workflows for performance issues and suggests optimizations.
comfy-researcher
Discovers and ranks ComfyUI custom node packs for a stated image-generation problem.
designer
Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.
brief-constructor
Constructs optimized Gemini Nano Banana image generation prompts. Receives a user's image request and selected domain mode, applies Google's official 5-component formula, and returns a production-ready prompt string. Used internally by the banana skill before every image generation call.
image-generator
Image generation executor agent. Delegates here for ALL generateimage calls to keep the main conversation context clean. Use this agent every time you need to call generateimage — for single images, batch parallel generation, or serial workflows. Context: User wants to generate 4 logo concepts in parallel user…
gemini-image-gen
Image generation and editing agent. Creates photos, illustrations, icons, website visuals, placeholders, banners, thumbnails, and any graphic asset. Edits, retouches, and applies style transfer to existing images. Use for any task requiring image creation or manipulation.