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.
git clone --depth 1 https://github.com/sandyup/comfyui-mcpWrote 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/commands/sandyup/comfyui-mcp/gallery)<a href="https://agentmods.dev/commands/sandyup/comfyui-mcp/gallery"><img src="https://agentmods.dev/badge/commands/sandyup/comfyui-mcp/gallery/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/commands/sandyup/comfyui-mcp/gallery"><img src="https://agentmods.dev/badge/commands/sandyup/comfyui-mcp/gallery.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00008 | $0.00691 |
| Opus 5.5 | $0.00003 | $0.00276 |
| Sonnet 5.5 | $0.00002 | $0.00138 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
gallery 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 1mo 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.
This is a copy
86% identical to gallery — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/comfy-gallery — Browse Generated Outputs
The user wants to browse images that ComfyUI has generated, inspect their metadata, and optionally re-run or modify workflows.
Instructions
-
Determine the output directory. Call
get_system_statsto check for a custom--output-directoryargument. If not set, use the default ComfyUI output directory (typically~/Documents/ComfyUI/output/or theoutput/folder relative to the ComfyUI installation). -
List image files. Use the Glob tool to find image files in the output directory:
- Pattern:
**/*.png(ComfyUI saves as PNG by default) - Also check for
**/*.jpg,**/*.webpif needed - Sort by modification time, newest first
- Pattern:
-
Apply filters. The argument is: $ARGUMENTS
Parse the filter:
last NorN: show only the N most recent imagestoday: images created today (compare file dates)yesterday: images from yesterday- Filename pattern: glob match against filenames (e.g.,
ComfyUI_00123*) - No filter: default to showing the last 10 images
-
Present image details. For each image, show:
- Filename
- File size (human-readable: KB/MB)
- Creation/modification date and time
- Use the Read tool to display the image thumbnail if the file is a supported image format
-
Extract workflow metadata. When the user selects an image or asks for details:
- Use
workflow_from_imageto extract the embedded workflow JSON from the PNG metadata - Show key parameters: checkpoint used, prompt, negative prompt, seed, steps, CFG, sampler, dimensions
- Offer to visualize the workflow with
visualize_workflow
- Use
-
Offer actions. For any selected image, offer to:
- Re-run: execute the same workflow again (new seed for variation)
- Modify and re-run: let the user change parameters (prompt, seed, steps, etc.) and run a modified version
- Upscale: create an upscale workflow using the image as input
Example
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.
- 1mo ago First seen · 62 lines · 8 tokens per session scan A ea50a3c92076
gallery is a command published in the GitHub repository sandyup/comfyui-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 691 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to gallery, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.