comfyui-screenshot-pipeline

comfyui-screenshot-pipeline is a skill for Claude Code from laurigates/claude-plugins. It costs 47 tokens per session (2,175 once invoked), scanned A, original, MIT.

A Docker-and-Playwright tool for taking repeatable screenshots of ComfyUI custom-node packs, including dialogs and temporary interface elements.

In plain words
What is it for?
It helps create and commit README screenshots for ComfyUI packs, including screenshots of modal windows, gesture controls, and node interfaces.
Why use it?
It avoids screenshots changing because of different ComfyUI versions, themes, or installed models on each developer's machine.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

Part of the comfyui-plugin plugin — 17 skills shipped together

Good fit It helps create and commit README screenshots for ComfyUI packs, including screenshots of modal windows, gesture controls, and node interfaces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/laurigates/claude-plugins/comfyui-screenshot-pipeline
Install

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.

Any agent
npx skills add laurigates/claude-plugins --skill comfyui-screenshot-pipeline
Clone the repo
git clone --depth 1 https://github.com/laurigates/claude-plugins

Made for: Claude Code.

Or install comfyui-plugin, the plugin that ships this one along with the rest of its 17 skills.

Wrote 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.

agentmods badge for comfyui-screenshot-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfyui-screenshot-pipeline/github.svg)](https://agentmods.dev/skills/laurigates/claude-plugins/comfyui-screenshot-pipeline)
Your own site
<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfyui-screenshot-pipeline"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfyui-screenshot-pipeline/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.

agentmods 80×15 button for comfyui-screenshot-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfyui-screenshot-pipeline"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfyui-screenshot-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,175 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 99
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • low Tool Misuse · line 99
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.02175
Opus 5 $0.00023 $0.01087
Sonnet 5 $0.00009 $0.00435
Haiku 4.5 $0.00005 $0.00217

Measured 6d ago against content hash dc0825cc6054, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

comfyui-screenshot-pipeline 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (add_screenshots.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

comfyui-plugin/skills/comfyui-screenshot-pipeline/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

comfyui-screenshot-pipeline

Add the containerized README-screenshot generator to a ComfyUI usability pack. It is the deferred piece from comfyui-node-scaffold (which intentionally does not emit it). The same pattern ships in comfyui-gallery-loader, comfyui-sampler-info, comfyui-touch-numeric, comfyui-prompt-editor, comfyui-model-gallery, comfyui-touch-resize, and comfyui-touch-connect — those are the living reference implementations.

When to Use This Skill

Use this skill when... Use the alternative when...
Adding a reproducible README-screenshot generator to an existing ComfyUI pack — Docker + Playwright driver, just screenshots, committed docs/<out>.png Bootstrapping a brand-new pack repo → comfyui-node-scaffold (it intentionally defers the screenshot pipeline)
Capturing the pack's real frontend deterministically (modal dialog, gesture affordance, or transient overlay) Running the full idea→registry lifecycle → comfy-node

Why containerized

The shot must not depend on whatever models / theme / frontend a dev machine happens to have. A Docker image pins the ComfyUI release (hence the frontend bundle) and the Playwright/Chromium revision (the largest source of cross-host font-rendering drift), boots ComfyUI headless on CPU with no models, drives the pack's real public surface, and writes a PNG to a mounted docs/. Re-runs are deterministic.

Pick the archetype

Archetype Use when the pack… What the driver does
modal opens an HTML dialog over a widget (the modal "vein": gallery-loader, sampler-info, touch-numeric, prompt-editor, model-gallery) load a workflow with the target node, wait for the pack's patch flag on the widget, invoke widget.onPointerDown, wait for .cmp-dialog, screenshot it
gesture-affordance is a canvas gesture whose only static surface is a painted affordance (touch-resize's corner-hint bracket) select a node directly (no selectNode → no Vue toolbox) so onDrawForeground paints, optionally inject an illustrative callout overlay, clip the canvas region around the node
gesture-overlay shows a transient overlay only during a live gesture that can't run headlessly (touch-connect's magnifier loupe) force the canvas state (connecting_links etc.), dispatch a synthetic touch pointer the pack listens for, then screenshot the activated overlay element

Read the full file on GitHub · 142 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago First seen · 142 lines · 47 tokens per session scan A dc0825cc6054

Subscribe to this mod's changes

comfyui-screenshot-pipeline is a skill published in the GitHub repository laurigates/claude-plugins (58 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 2,175 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.

Related

Other skills, from other repositories

image-prompt

Create production-quality image generation prompts for Nano Banana (Google's AI image generator). Guides through brand selection, concept exploration, prompt crafting, and iterative revision. Use when asked to 'create an image prompt', 'make a featured image', 'generate image for blog', or similar.

animalzinc/claude-plugins · 60 tokens

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…

aiman-labs/ergouzi-agent-skills · 90 tokens

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.

aiman-labs/ergouzi-agent-skills · 76 tokens

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…

2ykwang/agent-skills · 111 tokens

sonoscli

Control Sonos speakers (discover/status/play/volume/group).

SafeAI-Lab-X/ClawKeeper · 16 tokens

spotify-player

Terminal Spotify playback/search via spogo (preferred) or spotifyplayer.

SafeAI-Lab-X/ClawKeeper · 17 tokens