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/ocr)<a href="https://agentmods.dev/commands/coltonbearden/carrel/ocr"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/ocr/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/coltonbearden/carrel/ocr"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/ocr.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 | $0.00020 | $0.00707 |
| Opus 5.5 | $0.00008 | $0.00283 |
| Sonnet 5.5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
ocr 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
OCR the file the user asked about: $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 ocr --help differs, trust the installed version — never invent flags):
Usage: carrel ocr [OPTIONS] SRC
OCR an image or PDF into text (txt/md) or a searchable PDF.
Images (jpg/png) run through tesseract; PDFs through ocrmypdf, which passes born-digital pages
through untouched unless --redo is given.
Options:
-o, --out PATH Output file. Default: SRC with the target extension (SRC.ocr.pdf for pdf →
pdf).
--lang LANG OCR language(s), tesseract codes, e.g. eng or eng+deu. [default: eng]
--to [txt|pdf|md] Output: extracted text (txt/md) or a searchable PDF. [default: txt]
--redo Re-OCR PDF pages even if they already have text (ocrmypdf --force-ocr; default
skips them).
--force Allow overwriting an existing output file.
--json Machine-readable JSON output.
--help Show this message and exit.
SRC: a jpg/png image (runs through tesseract) or a PDF (runs through ocrmypdf; born-digital pages pass through untouched).--to txt|pdf|md(default txt): extracted text, or a searchable PDF layer.-o/--out PATH: output file; default is SRC with the target extension (SRC.ocr.pdffor pdf → pdf).--lang LANG(default eng): tesseract language codes, e.g.engoreng+deu— set this when the user mentions a non-English document.carrel doctor --jsonlists the installedtesseract_langs.--redo: re-OCR PDF pages even if they already have text (only when the user says the existing text layer is bad).--force: only when the user explicitly wants an existing output overwritten.
Afterwards, tell the user where the output landed. For --to txt/md, offer to show or summarize the extracted text. Exit code 3 means tesseract/ocrmypdf is missing — relay the install hint from stderr verbatim — it names the package for the user's own platform, which is not always Debian. Exit code 4 means the input type isn't OCR-able.
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.
- 1mo ago Changed scan B → A f90906b7ebe4
- 1mo ago Changed · +19 lines 07c8b3a9b697
- 1mo ago Changed d6bdcbe64de5
- 1mo ago First seen · 25 lines · 20 tokens per session scan B ba6a3b5b914c
ocr is a command published in the GitHub repository coltonbearden/carrel (2 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 707 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
receipt
Upload and process receipt images or PDF invoices, extract line items, and match to bank transactions.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.
slides
A presentation-making command that creates slides from a topic using Manus Slides, with 24 stated visual styles. It can export the result as PPTX, PDF, or HTML files.
cabinet
Build a self-contained archive bundle for a single .eml — markdown, retained attachments, and source file in one directory.
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.