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/danielrosehill/Claude-Image-Production-PluginWrote 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/danielrosehill/claude-image-production-plugin/scrub-small-images)<a href="https://agentmods.dev/commands/danielrosehill/claude-image-production-plugin/scrub-small-images"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-image-production-plugin/scrub-small-images/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/danielrosehill/claude-image-production-plugin/scrub-small-images"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-image-production-plugin/scrub-small-images.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 | $0.00000 | $0.00468 |
| Opus 5 | $0.00000 | $0.00234 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
scrub-small-images 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 10d 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.
What it actually says
Scrub Small Images
Identify and move images below a configurable size threshold — typically thumbnails, icons, favicons, chat-app previews, and web-sidebar gunk that clutters a library import.
Task
-
Confirm threshold — default longest edge < 500 px. Ask if the user wants a different cutoff (200 px for aggressive scrub, 1000 px to cull everything non-print-worthy).
-
Ask which folder to operate on — default is the current working directory. Confirm recursion; default recursive (small images usually hide in subfolders).
-
Probe every image for dimensions (respecting EXIF Orientation so portrait phone shots aren't miscategorised):
identify -auto-orient -format "%w %h %i\n" *.jpg *.png *.heic *.webp 2>/dev/null # or exiftool -s -s -s -ImageWidth -ImageHeight "image.jpg" -
Build a candidate list — images where
max(width, height) < threshold. Show the user a table: filename, dimensions, format, size on disk. -
Wait for confirmation before moving anything. This feels destructive — never auto-execute.
-
Move confirmed files to
small/(a sibling bucket in the target folder). Preserve relative subpaths if operating recursively. On filename collision, append a short suffix. Do not delete. -
Log to
notes/scrub-small-images-{timestamp}.md:- Threshold used
- Files moved / files kept
- Full list of moved files with dimensions
-
Offer a follow-up — if many images are borderline (e.g. 480–520 px at a 500 px cutoff), ask whether to review those manually before finalising.
Notes
- Use
max(width, height)(longest edge) rather than total pixel count — a 100×1000 column banner is more useful than a 300×300 icon even though they're the same pixel count. - Skip non-image files silently; list them in the log.
small/is the disposal bucket — the user decides when to empty it.
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.
- 10d ago First seen · 36 lines · 0 tokens per session scan A 790db74fed13
scrub-small-images is a command published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (16 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 tokens. 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 2026-08-30.
Other commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.
varyshop-carousel
Create a Varyshop multi-slide carousel (LIGHT style, hook → CTA).
imperium:create-video
Create startup video content. Supports pitch videos, product demos, social clips, investor updates, and hiring videos. Bridges to Remotion for rendering.