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-metadatanpx skills add laurigates/claude-plugins --skill comfy-metadatagit 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-metadata)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfy-metadata"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-metadata.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 | $0.00054 | $0.02960 |
| Opus 5 | $0.00027 | $0.01480 |
| Sonnet 5 | $0.00011 | $0.00592 |
| Haiku 4.5 | $0.00005 | $0.00296 |
Grade A, and why
comfy-metadata 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI output metadata
Every image/video/audio file ComfyUI emits embeds the API-form prompt and the UI-form workflow that produced it. The encoding varies by file format and by which save-node wrote it (core vs. kijai vs. VHS). This skill is the canonical reference for where the data lives, how to read it back, and a small Python toolkit to do it reliably across every format on disk in this install.
When to Use This Skill
| Use this skill when... | Use instead when... |
|---|---|
| Figuring out what prompt/settings produced an existing output file | Inspecting a live in-graph value during a run -> comfy-debug-preview |
| Scanning, organizing, or comparing a directory of outputs | Auto-arranging the layout of a workflow JSON -> comfy-workflow-layout |
Quick reference
| Format | Saved by | Where the JSON lives | Encoding |
|---|---|---|---|
| PNG still | core SaveImage, kijai PNG path |
tEXt chunks (PIL Image.info["prompt"] and ["workflow"]) |
each value is a JSON string |
| Animated PNG | core SaveAnimatedPNG |
iTXt chunks (same keys) |
each value is a JSON string |
| WebP still + animated | core SaveAnimatedWEBP |
EXIF tags: 0x0110 (Model) holds "prompt:<json>", 0x010F (Make) holds "workflow:<json>", lower tags hold further extra_pnginfo keys |
one EXIF string per key, "key:json" prefix |
| MP4 native | core SaveVideo |
Container metadata, separate keys: prompt, workflow, plus any extra |
each value is a JSON string |
MP4 kijai (WanVideoWrapper_*.mp4) |
WanVideoWrapper.save_video |
Container metadata, single key comment |
one JSON object: {"prompt": "<json>", "workflow": "<json>"} (double-encoded) |
| WebM / Matroska | core SaveVideo; kijai/MMAudio |
Container metadata: per-key (native) or single COMMENT (kijai) |
same patterns as MP4 |
| FLAC / OGG / MP3 / WAV | core SaveAudio |
Container metadata: prompt, extra_pnginfo* keys |
each value is a JSON string |
.latent |
core SaveLatent |
safetensors header metadata: prompt, workflow |
each value is a JSON string |
What ships with it
2 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.
- today First seen · 245 lines · 54 tokens per session scan A 5910a7a38bbd
comfy-metadata is a skill published in the GitHub repository laurigates/claude-plugins (57 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 2,960 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
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.
sonoscli
Control Sonos speakers (discover/status/play/volume/group).
songsee
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.