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.
npx skills add rossumai/claude-marketplace --skill email-body-converter-referencegit clone --depth 1 https://github.com/rossumai/claude-marketplaceWrote 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/skills/rossumai/claude-marketplace/email-body-converter-reference)<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/email-body-converter-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/email-body-converter-reference/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/skills/rossumai/claude-marketplace/email-body-converter-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/email-body-converter-reference.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 | $0.00313 | $0.00821 |
| Opus 5 | $0.00156 | $0.00411 |
| Sonnet 5 | $0.00063 | $0.00164 |
| Haiku 4.5 | $0.00031 | $0.00082 |
Grade A, and why
email-body-converter-reference 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 12d 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
Email Body Converter Reference
The Email Body Converter is a Rossum-maintained hosted webhook ("A simple extension that can convert the email HTML body into a PDF and upload it to a queue as a new document") that exists to work around a platform default: "Rossum does not process the body of the email itself" — only attachments are imported. When the invoice, order, or other data arrives in the email body, this extension renders the body as a PDF so it enters the queue as a normal document and gets extracted. It can also convert HTML/TXT attachments to PDF, and (via a second, undocumented mode) HTML/TXT uploads.
See reference.md for the full reference. Consult it when:
- Setting the extension up — it is a manually created Webhook on
email.receivedpointing at a Rossum-hosted service URL, with a region table (EU1 + US only) and an admin token owner requirement. - Choosing settings — all 12
configurations[]keys, including the seven that the KB article does not document (each tagged by how it was verified). - Building "convert the body only when nothing else is processable" recipes (
skip_if_supported_files_present), attachment conversion, or PDF styling. - Wiring the
upload.created→/convert-filesmode to convert uploaded HTML/TXT files. - Troubleshooting: body-only emails bouncing as "no processable attachments", nothing imported, replies being converted, attachments not converting.
Read this first: the extension is not in the Rossum Store — you create the webhook yourself (Extensions → My extensions). The service is hosted in EU1 and US; orgs in other regions (EU2 Frankfurt, Japan Tokyo) point their webhook at one of those URLs cross-region. The webhook needs a token owner with Admin access.
Cross-references:
rossum-reference— inbox/email API, theemail.receivedpayload/response contract, and the field-level email sources (email_body:text_html,email_header:subject,email:*inrir_field_names) which populate fields on an existing annotation; this extension instead creates a new document.sfi-reference— structured XML/JSON/e-invoice import (a different extension for machine-readable formats).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 25 lines · 313 tokens per session scan A 6a1400746089
email-body-converter-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It adds 313 tokens to every session and 821 once invoked, about $0.0016 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 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.