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 laurigates/claude-plugins --skill comfy-subgraphs-app-modegit 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-subgraphs-app-mode)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfy-subgraphs-app-mode"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-subgraphs-app-mode/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/laurigates/claude-plugins/comfy-subgraphs-app-mode"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-subgraphs-app-mode.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 | $0.00055 | $0.01850 |
| Opus 5 | $0.00028 | $0.00925 |
| Sonnet 5 | $0.00011 | $0.00370 |
| Haiku 4.5 | $0.00006 | $0.00185 |
Grade A, and why
comfy-subgraphs-app-mode 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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
comfy-subgraphs-app-mode
Three frontend features for reusing and simplifying workflows, each version-gated:
| Feature | Frontend gate |
|---|---|
| Subgraphs (group → super-node) | 1.24.3+ |
| Subgraph Parameters Panel ("Edit Subgraph Widgets") | 0.3.66+ |
| Subgraph Blueprints (publish to node library) | 1.27.7+ |
| App Mode (a.k.a. "linear mode") | 1.41.13+ |
Check the running frontend if any of these ever appear missing:
<venv>/bin/python -c "import comfyui_frontend_package as p; print(p.__version__)"
The editor-side mechanics (the JSON shape of definitions.subgraphs[] and
its internal link table) live in comfy-workflow-json — that skill is
the authority for programmatic subgraph edits. This skill is about the
interactive features and what they mean for reuse.
When to Use This Skill
| Use this skill when... | Use instead when... |
|---|---|
| Deciding whether to package part of a workflow as a subgraph, Blueprint, or App Mode UI | Editing the JSON shape of a subgraph programmatically -> comfy-workflow-json |
Subgraphs — the basics
A subgraph packages selected nodes into a single collapsible "super node" with exposed input/output slots. Authoring is interactive:
- Create: select nodes → click the subgraph icon in the selection toolbox. ComfyUI auto-exposes the relevant inputs/outputs.
- Edit: double-click empty space inside the subgraph (not on a widget), or use its edit button. A navigation bar shows the current level; Esc or the nav bar exits. Right-click a slot to rename/delete/disconnect; the slot labeled 1 is the spare for adding a new connection.
- Parameters Panel (0.3.66+): select the subgraph and click Edit Subgraph Widgets to reorder/hide its surfaced widgets without entering it.
- Nesting: subgraphs can contain subgraphs; the nav bar tracks depth.
- Unpack: right-click → Unpack subgraph (or the toolbox button) flattens it back to loose nodes.
- Bypass / color / rename: a subgraph behaves like any node.
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.
- 4d ago First seen · 159 lines · 55 tokens per session scan A caee5404a4eb
comfy-subgraphs-app-mode is a skill published in the GitHub repository laurigates/claude-plugins (58 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,850 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 2026-09-03.
Other skills, from other repositories
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.
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…
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.
sonoscli
Control Sonos speakers (discover/status/play/volume/group).
spotify-player
Terminal Spotify playback/search via spogo (preferred) or spotifyplayer.