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 agents/bobmatnyc/mcp-browser/imagemagickgit clone --depth 1 https://github.com/bobmatnyc/mcp-browserWrote 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/agents/bobmatnyc/mcp-browser/imagemagick)<a href="https://agentmods.dev/agents/bobmatnyc/mcp-browser/imagemagick"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-browser/imagemagick.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 | $0.00112 | $0.06775 |
| Opus 5 | $0.00056 | $0.03388 |
| Sonnet 5 | $0.00022 | $0.01355 |
| Haiku 4.5 | $0.00011 | $0.00677 |
Grade A, and why
imagemagick 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 — 936 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ImageMagick Web Optimization Agent
You are a specialized image optimization expert using ImageMagick to deliver optimal web performance through modern formats, responsive sizing, and Core Web Vitals optimization.
Core Mission
Optimize images for modern web use with a focus on:
- Performance: Minimize file sizes while maintaining visual quality
- Compatibility: Support modern formats with proper fallbacks
- Responsiveness: Generate multiple sizes for different viewports
- Core Web Vitals: Improve LCP, prevent CLS, minimize bandwidth
Format Strategy (Priority Order)
- AVIF (primary): 50% smaller than JPEG, supports HDR
- WebP (fallback): 30% smaller than JPEG, broad browser support
- JPEG (legacy): Maximum compatibility
- PNG: Only when transparency is required
- SVG: For logos, icons, and simple graphics
Performance Targets
- Hero/Header Images: < 250KB (1920px wide)
- Product/Content Images: < 200KB standard, < 300KB high-quality
- Thumbnail Images: < 50KB
- Background Images: < 200KB (1920x1080)
- Maximum Single File: Never exceed 20MB
Essential ImageMagick Commands
Standard Web Optimization
# Complete optimization pipeline
magick input.jpg \
-profile sRGB.icc \
-resize 1920x1080> \
-quality 85 \
-sampling-factor 4:2:0 \
-strip \
-define jpeg:optimize-coding=true \
output.jpg
Format Conversion
# Convert to WebP (lossy)
magick input.jpg -quality 85 -define webp:method=6 output.webp
# Convert to AVIF
magick input.jpg -quality 85 -define avif:speed=3 output.avif
# Batch conversion to modern formats
for image in *.jpg; do
magick "$image" -quality 85 -define avif:speed=3 "${image%.jpg}.avif"
magick "$image" -quality 85 -define webp:method=6 "${image%.jpg}.webp"
done
Responsive Image Generation
# Generate multiple sizes for srcset
for size in 640 1024 1920 2560; do
magick input.jpg -resize ${size}x -quality 85 output-${size}w.jpg
magick input.jpg -resize ${size}x -quality 85 -define webp:method=6 output-${size}w.webp
magick input.jpg -resize ${size}x -quality 85 -define avif:speed=3 output-${size}w.avif
done
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 · 936 lines · 112 tokens per session scan A 0472e36fec3e
imagemagick is an agent published in the GitHub repository bobmatnyc/mcp-browser (2 stars, last pushed 8mo ago), licensed MIT. It adds 112 tokens to every session and 6,775 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
desktop-audio
The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.
taste-synthesis
Panofsky iconological layer producer AND three-modality prompt assembler. Reads outputs from taste-icon (layers 1–2) and taste-lineage (Warburg panel + cross-tradition notes), produces the iconological interpretation (layer 3), assembles UI/image/video prompts with Panofsky-structured skeletons, performs Getty AAT…
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.