agentmods.dev

sfi-reference

sfi-reference is a skill for Claude Code from rossumai/claude-marketplace. It costs 115 tokens per session (422 once invoked), scanned A, original, MIT.

A setup and configuration guide for Rossum’s Structured Formats Import extension, which processes machine-readable files such as XML, JSON, and electronic invoices. It can map values into fields and render structured data for human review.

In plain words
What is it for?
Use it to configure imports for XML, JSON, EDI, ZUGFeRD, or X-Rechnung files, including field mapping, value conversion, dates, splitting, and PDF output.
Why use it?
It removes the need to work out file selectors, formats, MIME types, document splitting, and PDF rendering settings from scratch.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the rossum-sa plugin — 35 skills, 4 hooks shipped together

not rated 5repo 5d ago A scan 115 tokens original MIT

Good fit Use it to configure imports for XML, JSON, EDI, ZUGFeRD, or X-Rechnung files, including field mapping, value conversion, dates, splitting, and PDF output.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rossumai/claude-marketplace/sfi-reference
View source ↗ rossumai/claude-marketplace
Install

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.

Any agent
npx skills add rossumai/claude-marketplace --skill sfi-reference
Clone the repo
git clone --depth 1 https://github.com/rossumai/claude-marketplace

Made for: Claude Code.

Or install rossum-sa, the plugin that ships this one along with the rest of its 35 skills, 4 hooks.

Wrote 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.

agentmods badge for sfi-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/sfi-reference/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/sfi-reference)
Your own site
<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/sfi-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/sfi-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.

agentmods 80×15 button for sfi-reference

Your own site · 80×15
<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/sfi-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/sfi-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.00422
Opus 5.5 $0.00046 $0.00169
Sonnet 5.5 $0.00023 $0.00084
Haiku 4.5 $0.00012 $0.00042

Measured 2mo ago against content hash 2caa909015d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sfi-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 2mo 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.

plugins/rossum-sa/skills/sfi-reference/SKILL.md · 28 lines

What it actually says

Structured Formats Import (SFI) Reference

This skill provides the complete setup and configuration reference for Structured Formats Import (SFI), Rossum's extension for processing non-visual structured documents (XML, JSON, EDI) and rendering them as PDFs for human review.

For the full configuration guide, selector syntax, feature reference, and production-ready examples, see reference.md.

Use this knowledge when:

  • Setting up SFI for the first time on a queue (MIME types, hook creation, environment URLs)
  • Writing field mappings with XPath selectors for XML documents
  • Writing field mappings with JSONPath/JMESPath selectors for JSON documents
  • Configuring German e-invoicing (ZUGFeRD, X-Rechnung) — both UBL and CII formats
  • Building address concatenation selectors using XPath 1.0 patterns
  • Setting up value transformation mappings (e.g., invoice type codes to enum values)
  • Configuring date parsing with custom formats
  • Setting up document splitting for multi-document files
  • Configuring PDF rendering from embedded base64 content or generated from extracted data
  • Handling non-existing schema IDs gracefully with skip_non_existing_schema_ids
  • Debugging XPath selector issues or testing selectors locally
  • Understanding trigger conditions and how multiple configurations are matched
  • Upper/lower case conversions in XPath 1.0 and JSON selectors
  • String concatenation in XPath and JMESPath selectors
Files

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.

Changes

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.

  1. 2mo ago First seen · 28 lines · 115 tokens per session scan A 2caa909015d0

Subscribe to this mod's changes

sfi-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 422 once invoked, about $0.0005 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.

Documents
Related

sfi-reference compared with skills from other repositories

sfi-reference next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sfi-referencerossumai/claude-marketplaceSkill55d agoMITA115Claude Code
orbit-notionnexu-io/open-designSkill107ktodayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35ktodayApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill50ktodayMITA48Claude Code
report-to-pdfasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A17Claude Code, Codex
legal-holdanthropics/claude-for-legalSkill10.0k3d agoApache-2.0A68Claude Code
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A54Claude Code, Codex