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/coltonbearden/carrelWrote 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/coltonbearden/carrel/extract-images)<a href="https://agentmods.dev/commands/coltonbearden/carrel/extract-images"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/extract-images.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 | $0.00025 | $0.00585 |
| Opus 5 | $0.00013 | $0.00293 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
extract-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 2d 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
Extract the images from: $ARGUMENTS
Run the carrel CLI via Bash. Map the user's request onto the real flags in the --help block below (regenerated from the CLI by scripts/sync_plugins.py; if the installed carrel extract-images --help differs, trust the installed version — never invent flags):
Usage: carrel extract-images [OPTIONS] SRC
Extract images embedded in / referenced by SRC (pdf, ico, html).
pdf uses pdfimages, ico uses icotool (or a Pillow fallback), html copies local <img src> files
that exist next to the document — remote URLs are never fetched. With --json, prints one JSON
object {"src", "out_dir", "count", "extracted"}.
Options:
--out-dir DIRECTORY Output directory [default: <SRC>-images next to the source].
--min-size INTEGER RANGE pdf mode: discard images smaller than this on either edge. [default:
32; x>=1]
--json Machine-readable JSON output.
--help Show this message and exit.
SRC: a pdf (via pdfimages), an ico (via icotool, Pillow fallback), or an html file — for html only local<img src>files that exist next to the document are copied; remote URLs are never fetched.--out-dir DIR(default<SRC>-imagesnext to the source): where the images land.--min-size N(pdf only, default 32): drop images smaller than N px on either edge — raise it when the user wants "the real figures, not icons".
Use --json and interpret {src, out_dir, count, extracted}: report how many images were written and where; offer carrel thumb on the output directory if the user wants a quick look. Exit code 3 means pdfimages (poppler-utils) or icotool is missing — relay the install hint from stderr. Exit code 4 means the input type has no extractable images.
Requires the carrel CLI on PATH. If carrel is not found, tell the user to install it with uv tool install carrel (see the repo's INSTALL notes), or run it as uv run carrel ... from the carrel repo root.
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.
- 2d ago First seen · 38 lines · 25 tokens per session scan A 2f857a811206
extract-images is a command published in the GitHub repository coltonbearden/carrel (1 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 585 once invoked, about $0.0001 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 2026-09-05.
Other commands, from other repositories
insights-deck
Archive an exported Claude Code insights HTML report and turn it into a timestamped Beamer presentation usable from either client. Use when the insights export is the source artifact for a presentation. Not for a general research talk; use $talk-deck.
export
A command for turning a set of SVG slide files into PDF documents, editable PPTX presentations, or both. SVG is a scalable image format, while PPTX is Microsoft PowerPoint’s file format.
imperium:create-slides
Create an HTML presentation. Zero dependencies — generates a single .html file that works as slides in any browser. 12 style presets available.
imperium:carousel
Create a PPTX carousel or slide deck. Choose from 6 types and 21 layouts with brand-applied styling.
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.