What is rossum-reference?

A reference guide for Rossum.ai, a platform that automates document processing through APIs, schemas, queues, and extensions. It explains the platform's concepts and available API operations.

Use it when answering Rossum questions or building integrations that configure queues and schemas, process documents, use hooks, or call the API.

It reduces guesswork about Rossum's API and requires technical decisions to be checked against official documentation or live read-only data.

rossum-reference — Skill for Claude Code by rossumai

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 rossum-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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/rossum-reference/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/rossum-reference)

Your own site

<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/rossum-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/rossum-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/rossum-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/rossum-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 805 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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.00805
Opus 5.5	$0.00020	$0.00322
Sonnet 5.5	$0.00010	$0.00161
Haiku 4.5	$0.00005	$0.00081

Measured 27d ago against content hash c85cf7d683d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rossum-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 27d 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/rossum-reference/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rossum.ai Platform Reference

This skill provides comprehensive reference documentation for the Rossum.ai document automation platform. For complete details, see reference.md.

Which Rossum API operations the rossum-api MCP server wraps is tracked in api-coverage.md (auto-generated). Read (GET) operations without a dedicated tool are still reachable through the generic rossum_get tool (shown as ✅ via rossum_get); ⬜ pending = an uncovered write with no MCP tool yet.

Verification Rule (read first)

Do not make assumptions. All technical decisions must be grounded in verified facts, and when uncertain you must ask before acting. API endpoints, field names, hook events, and operations payloads must be verified against the official docs at https://rossum.app/api/docs/openapi/guides/getting-started/#introduction or a live read-only probe before being written into code or documentation. If you must guess, label the claim Unverified — confirm before relying on this. Full rationale in ../__shared/verification-rules.md.

Safety Rules

Do not call write/mutating API tools without explicit user approval. This applies to all rossum_create_*, rossum_patch_*, rossum_delete_* tools, all data_storage write tools (insert, update, delete, replace, bulk_write, drop), and prd2 push/prd2 deploy / rdc sync (without --dry-run or --no-push) commands. Read-only tools (list, get, find, aggregate, whoami) are fine without confirmation. When in doubt, describe what you intend to do and ask first.

Edit local .py files, not JSON. When modifying hook code or formula logic in a prd project, only edit the .py file. Never edit the code field in hook JSON or the formula property in schema.json — prd2 push syncs .py files into JSON automatically. Do not use rossum_patch_hook or rossum_patch_schema to push code changes that should go through prd2 push instead.

Read the full file on GitHub · 37 lines

Files

What ships with it

2 files 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.

27d ago Changed · +2 lines c85cf7d683d0
2mo ago First seen · 35 lines · 51 tokens per session scan A 0005785ba83b

Subscribe to this mod's changes

rossum-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 805 once invoked, about $0.0002 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.

Backend and APIs

rossum-reference next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rossum-referencerossumai/claude-marketplace	Skill	5	5d ago	MIT	A	51	Claude Code
mem0-oss-to-platformmem0ai/mem0	Skill	69k	5d ago	Apache-2.0	A	217	Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code
fastapi-router-pymicrosoft/skills	Skill	3.2k	yesterday	MIT	A	46	Claude Code
api-designericrisco/rsc-harness	Skill	579	yesterday	MIT	A	105	Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1	Skill	257	2d ago	MIT	A	106	Claude Code
telnyx-messaging-hosted-curlteam-telnyx/ai	Skill	225	yesterday	MIT	A	45	Claude Code