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/fields)<a href="https://agentmods.dev/commands/coltonbearden/carrel/fields"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/fields/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/fields"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/fields.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 | $0.00036 | $0.00784 |
| Opus 5 | $0.00018 | $0.00392 |
| Sonnet 5 | $0.00007 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
fields 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 today.
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 document fields the user asked about: $ARGUMENTS
Run the carrel CLI via Bash. Map the request onto the real flags in the --help block below (regenerated from the CLI by scripts/sync_plugins.py; if the installed carrel fields --help differs, trust the installed version — never invent flags):
Usage: carrel fields [OPTIONS] PATHS...
Extract vendor, invoice number, dates and totals from PATH... (invoices, receipts, statements).
Directories are walked like `refs`. Fields: vendor, invoice_no, po, date, due, subtotal, tax,
total, currency, iban, account_last4 — each with a confidence (high: after its label; medium:
heuristic; low: fallback) and the evidence line. Amounts are plain decimals, dates ISO. JSON
output is a list of {path, profile, fields: {name: {value, confidence, evidence}}}.
Options:
--profile [auto|invoice|receipt|statement]
Document kind; auto picks by keywords. [default: auto]
--date-order [mdy|dmy] How to read an ambiguous slashed date such as 03/04/2026.
[default: mdy]
--ocr OCR images and scanned PDFs (needs tesseract / ocrmypdf).
--set FIELD=VALUE Override an extracted field (repeatable).
--save Write the fields into the desk db under --root (source: fields).
--fail-empty Exit 5 when no file yielded any field.
--json Machine-readable JSON output.
--help Show this message and exit.
- Start with
carrel --json fields PATH...; every supported type works (PDF, docx, eml, txt, …). Each field carries aconfidence:highfollowed its label (Total Due,Invoice Date),mediumwas a heuristic (largest amount, first date),lowa fallback (file mtime, file name) — report the confidence with the value and never present alowfield as fact. - European dates (
10.09.2026meaning 10 September) need--date-order dmy; scans and images need--ocr. - Wrong guess?
--set vendor="Acme Corp"overrides a field for this run; with--savethe fields land in the desk db under the global--root(carrel meta ls FILEshows them,carrel meta find total>1000queries them,/carrel-organize:renamenames files from them). - A missing binary exits 3 with the install hint — report it rather than guessing.
Report the fields conversationally (vendor, number, dates, amounts with currency) and flag anything medium/low so the user can confirm it. Line items are not extracted — say so if asked.
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.
- today First seen · 45 lines · 36 tokens per session scan A f2df0b0ee8aa
fields is a command published in the GitHub repository coltonbearden/carrel (1 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 784 once invoked, about $0.0002 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 2026-09-11.
Other commands, from other repositories
clean
Turn messy or multi-format CSV exports into one clean, categorized, analysis-ready file.
payslip
Upload and process Danish payslips (lønsedler) for pension tracking, income analysis, and enhanced financial advice.
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.
numbers-to-excel
Convert a Numbers document to Excel.
add-skill
Add a new Skill to the current plugin with proper structure.