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/plugins/coltonbearden/carrel/carrel-convert)<a href="https://agentmods.dev/plugins/coltonbearden/carrel/carrel-convert"><img src="https://agentmods.dev/badge/plugins/coltonbearden/carrel/carrel-convert/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/plugins/coltonbearden/carrel/carrel-convert"><img src="https://agentmods.dev/badge/plugins/coltonbearden/carrel/carrel-convert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
carrel-convert 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 1mo 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
{
"name": "carrel-convert",
"description": "Convert, OCR, thumbnail, edit, extract images from, and narrate local files with the carrel CLI: /convert, /ocr, /thumb, /edit, /extract-images, /audiobook, plus a doc-converter batch agent.",
"version": "0.5.0",
"author": { "name": "Colton Bearden" },
"license": "MIT",
"keywords": ["files", "convert", "pdf", "ocr", "thumbnails", "edit", "images", "audiobook", "tts"]
}
What it installs
The manifest is a name and a version. 6 commands, 1 agent travel with it, and installing the plugin installs all of them — 237 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago Changed 24f893db868a
- 1mo ago Changed 543bf23fea7c
- 1mo ago Changed 29229d1485bd
- 1mo ago Changed 83a625a08cfc
- 1mo ago Changed 497807349c14
- 1mo ago First seen · 9 lines scan A f89d9cda17aa
carrel-convert is a plugin published in the GitHub repository coltonbearden/carrel (2 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
kordoc marketplace
Single-plugin marketplace shipping kordoc — Korean official-document toolkit (.hwp/.hwpx/.hml + PDF/DOCX/XLS/XLSX) for Claude.
kordoc
A document tool for reading, creating, filling, patching, comparing, checking, and rendering Korean official files such as HWP, HWPX, PDF, DOCX, and spreadsheets.
deckprobe
Inspect PDF, Microsoft Office, and Apple iWork documents with bounded, deterministic probes.
geml
Block-addressed docs: read or replace one section of an existing Markdown file instead of loading the whole thing. Adds per-block history and a code-graph navigator.
kreuzberg
Extract document text, tables and metadata with the legacy Kreuzberg 4.x CLI and MCP tools.
import
Import external documentation locally - bypass AI-blocking sites via Context7, WebFetch, or Playwright.