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/laurigates/claude-plugins/comfy-workflow-layoutnpx skills add laurigates/claude-plugins --skill comfy-workflow-layoutgit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/comfy-workflow-layout)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfy-workflow-layout"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-workflow-layout.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 | $0.00043 | $0.02569 |
| Opus 5 | $0.00022 | $0.01285 |
| Sonnet 5 | $0.00009 | $0.00514 |
| Haiku 4.5 | $0.00004 | $0.00257 |
Grade A, and why
comfy-workflow-layout 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI workflow auto-layout
scripts/layout_workflow.py runs a layered (Sugiyama-style) DAG layout
over the nodes in a workflow JSON: median layering (each node sits at
the midpoint between its earliest and latest possible depth, so source
and sink nodes spread across columns instead of piling up at the edges),
a barycenter sweep within each layer to reduce edge crossings, and a
group-cohesion post-pass that clusters members of the same authored
group contiguously within each column. Group bounding boxes are re-fit
around their final members. Pure stdlib, no deps. Visual goal is "the
editor is readable again with comparable density to a hand-tuned
layout" — link routing is left to ComfyUI.
In practice on Wan 2.2 workflows in this install, output bounding-box area ranges from −13% to +23% of a hand-arranged layout (typically within ±10%), with 0 node overlaps. Without median layering it would be 2× larger.
When to Use This Skill
| Use this skill when... | Use instead when... |
|---|---|
| A workflow's nodes overlap, are messy/cramped, or were imported and need tidying | Editing the graph's wiring/links -> comfy-workflow-json |
Pipeline (default mode)
- Detect group membership by which nodes' centers sit in each group's authored bounding box. Tie-break to the smallest group.
- Absorb leaf singletons — ungrouped nodes whose neighbors are ≥2/3 in one group join that group's membership for layout purposes. Single-pass; central hub nodes (whose connections fan out across many groups) stay as singletons.
- Median layering — each node's column index is the average of its longest-path-from-sources and longest-path-from-sinks depth. Source nodes whose only consumer is at depth 8 land near depth 7, not 0. Sink nodes whose only producer is at depth 1 land near 1.
- Barycenter sweep within each layer to minimize edge crossings.
- Group-cohesion clustering — within each layer, re-permute so nodes sharing a group sit contiguously. Cluster order within a layer follows each cluster's median barycenter index.
- Vertically center each column around the layer band's midpoint so short columns float to center rather than top-align.
- Recompute group bounding boxes to wrap the final positions
(skip with
--no-groups).
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 First seen · 253 lines · 43 tokens per session scan A 6276a837d65e
comfy-workflow-layout is a skill published in the GitHub repository laurigates/claude-plugins (57 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 2,569 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
html-visual
Generate an interactive single-file HTML visualization — mockup, wireframe, ERD, flowchart, chart, slides, architecture diagram, dashboard, timeline, mindmap, kanban, or table. Use when the user wants something rendered rather than described: a UI mockup or wireframe, a database schema as an ERD, business logic as a…
ergouzi-image-gen
Submit and complete Ergouzi image generation, editing, virtual try-on, upscaling, and background-removal tasks through ergouzi.life, including tasks that use local image files or HTTPS URLs. Use when Codex must call an ergouzi/e-image or ergouzi/e-rmbg model, poll the asynchronous task, download its outputs, resume a…
ergouzi-video-gen
Submit and complete Ergouzi video generation, animation, avatar, and person-replacement tasks through ergouzi.life, including tasks that use local media files or HTTPS URLs. Use when Codex must call an ergouzi/e-video model, poll the asynchronous task, download its output, resume a task ID, or cancel a video task.
image-prompt
Skill "image-prompt" from animalzinc/claude-plugins, covering image prompt creator, plugin root, phase 1: brief, step 1 — brand selection and step 2 — input intake.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.