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/form)<a href="https://agentmods.dev/commands/coltonbearden/carrel/form"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/form.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 | $0.00037 | $0.00877 |
| Opus 5 | $0.00018 | $0.00439 |
| Sonnet 5 | $0.00007 | $0.00175 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
form 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 yesterday.
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
Handle this form request: $ARGUMENTS
Run the carrel CLI via Bash. carrel form is a group with fields, fill and build; map the user's request onto the real subcommands and flags in the --help blocks below (regenerated from the CLI by scripts/sync_plugins.py; if the installed carrel form --help differs, trust the installed version — never invent flags):
Usage: carrel form [OPTIONS] COMMAND [ARGS]...
Build HTML forms from JSON specs; list and fill PDF AcroForms.
Options:
--json Machine-readable JSON output.
--help Show this message and exit.
Commands:
build Render a JSON form spec into clean, standalone, print-friendly HTML.
fields List a PDF's AcroForm fields (name, type, current value).
fill Fill a PDF's AcroForm fields from a JSON object {field: value}.
Usage: carrel form build [OPTIONS] SPEC.JSON
Render a JSON form spec into clean, standalone, print-friendly HTML.
Options:
-o, --out PATH Output HTML file. Default: SPEC stem + .html.
--pdf Also render the HTML to PDF (weasyprint).
--force Allow overwriting existing output files.
--json Machine-readable JSON output.
--help Show this message and exit.
Usage: carrel form fields [OPTIONS] SRC
List a PDF's AcroForm fields (name, type, current value).
Options:
--json Machine-readable JSON output.
--help Show this message and exit.
Usage: carrel form fill [OPTIONS] SRC DATA.JSON
Fill a PDF's AcroForm fields from a JSON object {field: value}.
Options:
-o, --out PATH Output PDF. [required]
--force Allow overwriting an existing output file.
--json Machine-readable JSON output.
--help Show this message and exit.
- fields SRC.pdf: lists AcroForm fields as
{name, type, value}. Always run this first before filling — the user's labels ("Name", "date signed") rarely equal the internal field names. - fill SRC.pdf DATA.json -o OUT.pdf: DATA is a flat JSON object
{field_name: value}using the exact names fromfields; checkboxes take their export value (seefields).-ois required; the original is never modified;--forceonly when the user explicitly wants an existing output replaced. Write DATA.json with the Write tool or a heredoc, then fill. - build SPEC.json: renders a JSON form spec into standalone, print-friendly HTML (
SPEC-stem.htmlby default);--pdfalso renders a PDF via weasyprint (exit 3 → relay the install hint). If the user has no spec yet, draft one from their description, show it, then build.
Use --json and report the output path plus, after fill, re-run fields on the output to show the user the filled values. Exit code 4 means the PDF has no AcroForm (a flat/scanned form) — suggest carrel ocr to get text and a build-generated form instead.
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.
- yesterday First seen · 71 lines · 37 tokens per session scan A 92eb1a34f1c0
form is a command published in the GitHub repository coltonbearden/carrel (1 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 877 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 2026-09-05.
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.
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.
specify
Create or update the feature specification from a natural language feature description.