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 skills add danielrosehill/Claude-Image-Production-Plugin --skill scrub-metadatagit 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/skills/danielrosehill/claude-image-production-plugin/scrub-metadata)<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/scrub-metadata"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/scrub-metadata/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/skills/danielrosehill/claude-image-production-plugin/scrub-metadata"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/scrub-metadata.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 | $0.00084 | $0.01380 |
| Opus 5.5 | $0.00034 | $0.00552 |
| Sonnet 5.5 | $0.00017 | $0.00276 |
| Haiku 4.5 | $0.00008 | $0.00138 |
Grade B, and why
scrub-metadata scanned grade B with 1 finding 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 2mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
command -v exiftool || echo "exiftool not installed — install with: sudo apt install libimage-exiftool-perl" How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrub Image Metadata
Remove EXIF / IPTC / XMP metadata from images in place (or to a copy), with preview and logging. Wraps exiftool — do not hand-roll metadata parsing.
When to use
- Before publishing photos to a public blog, social media, or client deliverable.
- Bulk-cleaning an archive that may contain GPS or serial-number metadata.
- Preparing reference images for distribution where only orientation should be preserved.
Procedure
1. Establish scope
Ask the user (and confirm before touching files):
- Target path — single file, folder, or recursive tree. Default: current working directory.
- Recursive? If the target is a folder, ask whether to descend into subfolders. Default no (flat, current folder only) unless the user says "recursive" or supplies a root.
- Backup first? Default yes —
exiftoolkeeps_originalsidecars automatically, but offer an explicitbackup/copy for the nervous case. - Whitelist — fields to preserve. Common sensible default: keep
Orientationso the image renders right-way-up. Ask if the user wants to preserve anything else (ColorSpace, ICC profile, copyright). - Dry run vs apply — always preview first.
2. Check tooling
command -v exiftool || echo "exiftool not installed — install with: sudo apt install libimage-exiftool-perl"
Abort if missing.
3. Preview what will be stripped
Run a read-only pass and show the user a summary:
# Show metadata currently present on a sample file
exiftool -G1 -a -s "sample.jpg"
# Count files that would be touched
find <target> -maxdepth <1|999> -type f \
\( -iname '*.jpg' -o -iname '*.jpeg' -o -iname '*.png' \
-o -iname '*.heic' -o -iname '*.webp' -o -iname '*.tif' \
-o -iname '*.tiff' \) | wc -l
Print:
- File count by extension.
- Which tag groups will be removed (EXIF, GPS, IPTC, XMP, MakerNotes, Thumbnail).
- Which tags will be kept (the whitelist).
- Whether a
backup/copy will be made.
Wait for user confirmation.
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.
- 2mo ago First seen · 125 lines · 84 tokens per session scan B 1e9ab30127c5
scrub-metadata is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (21 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,380 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
scrub-metadata compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| scrub-metadatadanielrosehill/Claude-Image-Production-Plugin | Skill | 21 | yesterday | MIT | B | 84 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |