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/group-by-camera)<a href="https://agentmods.dev/commands/danielrosehill/claude-image-production-plugin/group-by-camera"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-image-production-plugin/group-by-camera.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 5.1 | $0.00000 | $0.00428 |
| Opus 5 | $0.00000 | $0.00214 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
group-by-camera 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 8d 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
Group Images by Camera
Cluster images by EXIF camera Make + Model.
Task
-
Ask which folder to operate on — default is the current working directory. Confirm recursion; default flat.
-
Read camera metadata for each image:
exiftool -s -s -s -Make -Model -LensModel "image.jpg"Build a bucket label of the form
{Make}_{Model}with spaces and slashes replaced by hyphens (e.g.NIKON-CORPORATION_NIKON-D850,Apple_iPhone-15-Pro,SONY_ILCE-7M3). -
Bucket files:
{Make}_{Model}/— one folder per unique (Make, Model) pairno-exif/— images with no readable camera metadata (screenshots, scrubbed photos, generated art)unknown/— EXIF present but Make or Model missing
-
Preview before acting — table of bucket label → count, plus a sample filename per bucket. Wait for user confirmation. Offer to merge near-duplicate bucket names (common:
NIKON CORPORATIONvsNIKON). -
Prefer symlinks or CSV manifest over physical moves:
- Option A: symlinked subfolders
- Option B:
metadata/camera-buckets.csvwithfilename,make,model,bucket - Option C: physical move on explicit confirmation
-
Log to
notes/group-by-camera-{timestamp}.mdwith bucket counts and the no-EXIF / unknown tallies.
Notes
- Lens model is interesting but produces fragmented buckets — include it in the CSV manifest but not in the folder label.
- Phone photos often have consistent Make/Model but many firmware variants; don't try to split on firmware.
- If a user's library is dominated by
no-exif/, that usually means it was previously scrubbed — note this in the log.
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.
- 8d ago First seen · 34 lines · 0 tokens per session scan A 88c9ba9c9c81
group-by-camera is a command published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (16 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 428 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.