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-image-utilsgit 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-image-utils)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfy-image-utils"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-image-utils/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-image-utils"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-image-utils.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 | $0.00063 | $0.02601 |
| Opus 5.5 | $0.00025 | $0.01040 |
| Sonnet 5.5 | $0.00013 | $0.00520 |
| Haiku 4.5 | $0.00006 | $0.00260 |
Grade A, and why
comfy-image-utils 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 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.
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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI image utilities
Image manipulation that doesn't go through a diffusion model. Plus image-to-text inference (Florence-2, WD14, BLIP, DeepDanbooru), which is included here because the input is an image and the node-level setup (model downloads, ONNX dependencies, HF cache paths) is the bulk of the work.
The split:
| Pack | Niche |
|---|---|
comfyui-kjnodes |
Batch ops, resize-v2, crop-by-mask, channel split/merge, Get*SizeAndCount, LoadAndResizeImage (exposes image_path) |
comfyui_essentials |
Resize / Flip / Crop / Tile-Untile / Composite, list↔batch conversion, Mask family (Blur, Flip, FromColor, BoundingBox) |
comfyui-easy-use |
imageCount, imageInsetCrop, imagesCountInDirectory |
comfyui-tooling-nodes |
Base64 load, image cache, ApplyMaskToImage, WebSocket send, Tile Extract/Merge |
ComfyUI-Crystools |
CImageGetResolution, CImageLoadWithMetadata, CImageSaveWithExtraMetadata |
bjornulf_custom_nodes |
ResizeImage, ResizeImagePercentage, GrayscaleTransform, RemoveTransparency, LoadImageWithTransparency |
comfyui_yvann-nodes |
RepeatImageToCount |
comfyui-custom-scripts (pysssss) |
ConstrainImage (max-dimensions resize with aspect-preserve) |
comfyui-various |
image_ops / channel_ops / color_ops / image_sequence / mask_sequence_ops modules |
comfyui-florence2 |
Florence-2 vision-language for captioning (PromptGen LoRAs) |
comfyui-wd14-tagger |
WD14 ONNX booru-style tagger |
comfyui-art-venture |
BLIP captioner, DeepDanbooru anime tagger |
When to Use This Skill
| Use this skill when... | Use instead when... |
|---|---|
| Manipulating images/masks outside of model inference (resize, crop, tile, batch) | Running a diffusion/inference node on an image -> the relevant model-family skill |
| Generating a caption/tag from an image (Florence-2, WD14, BLIP) | Extracting metadata already embedded in an output -> comfy-metadata |
Sources of truth
custom_nodes/comfyui-kjnodes/nodes/image_nodes.py— batch / resize / channel / size+countcustom_nodes/comfyui_essentials/image.pyandmask.py— Image*/Mask* familycustom_nodes/comfyui-tooling-nodes/— base64, cache, websocket, tilingcustom_nodes/comfyui-florence2/— Florence-2 loaders + caption nodescustom_nodes/comfyui-wd14-tagger/— WD14 ONNX wrappercustom_nodes/comfyui-art-venture/modules/interrogate/— BLIP, DeepDanbooru
What ships with it
4 files 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.
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 Changed · -237 lines 3ab041f3afe4
- 1mo ago First seen · 428 lines · 63 tokens per session scan A c51f5f4cc457
comfy-image-utils is a skill published in the GitHub repository laurigates/claude-plugins (60 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 2,601 once invoked, about $0.0003 per session on Opus 5.5. 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
extract-ssot
Deduplicate repeated markdown (rule files, skill bodies, ADRs, docs) into one named source of truth and migrate every call site to cite it by exact heading. Use when the same prose, literal, or concept recurs across files: 'DRY this prose', 'extract a shared rule', 'single source of truth for X', a value-bump diff…
feature-branch-pr-writing
Use this skill when the user asks to write, draft, create, or improve a PR description for a Shopware core repository PR — AND that PR targets a non-trunk feature branch (not trunk itself). Trigger phrases like "write a PR description", "draft the PR", "what should I put in the PR body". The skill detects the target…
repo-activity
Scan all git repositories under /repos and report recent activity — last commit age, branch, uncommitted changes — in age-bucketed tables. Use when the user asks for a repo activity overview, "what have I been working on", portfolio status, or which repos are active/dormant.
oslog
Read, stream, and analyze Apple unified logs (OSLog) for iOS/macOS apps. Auto-detects subsystem from Logger usage or bundle identifier. Supports live log show, real-time streaming, and .logarchive analysis with full predicate reference. Use when the user asks to check app logs, stream console output, debug with OSLog…
renovate-triage
Use when triaging open Renovate PRs across your own repos into merge / close / defer. Activates on "renovate triage", "review dep PRs", "monthly deps", or on the 1st of a month if deps are grouped monthly.
use-class-for-state
For complex state: encapsulate multiple interacting variables, stateful algorithms, backtracking search state.