What is automation-report?

A process for turning Rossum queue analytics into a report about automated invoice processing. It identifies what prevents documents from being handled automatically and orders suggested fixes by their expected impact.

Use it to investigate low automation, decide which thresholds or rules to adjust, and produce a queue-specific recommendations report.

It replaces guesswork with findings based on the queue’s automation data and keeps report numbers tied to the analysis output.

automation-report — Skill for Claude Code by rossumai

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add rossumai/claude-marketplace

Claude Code

/plugin install rossum-sa

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/automation-report/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/automation-report)

Your own site

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

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,746 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	$0.00084	$0.01746
Opus 5.5	$0.00034	$0.00698
Sonnet 5.5	$0.00017	$0.00349
Haiku 4.5	$0.00008	$0.00175

Measured 2mo ago against content hash 739bdaa49d77, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

automation-report 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.

The scan reads SKILL.md. This mod also ships 2 executable files (analyze.py, tests/test_analyze.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/automation-report/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automation Report

Produce AUTOMATION-REPORT-[queue-name-or-id].md for one queue: where automation stands today, what exactly blocks it (split by remedy), and a numbered list of recommendations ordered by unlocked-document impact.

Follow skills/__shared/verification-rules.md: every claim grounded in fetched data. The Iron Rule: every number in the report comes from analyze.py output — no prose arithmetic. The script lives at ${CLAUDE_PLUGIN_ROOT}/skills/automation-report/analyze.py.

Phase 1 — Gather (silently; no report output yet)

Requires the rossum-api MCP connection (rossum_set_token first if needed). Resolve the queue ID from the argument (accepts a bare ID or any Rossum app URL containing /queues/<id>).

Insights (required). Call rossum_get_automation_insights with the queue ID. The digest lands in context; the full payload is cached to .rossum-cache/automation/queue_<id>_insights.json (path in full_payload_cache). If this fails, stop — there is no report without it.
Projections (optional, graceful). Call rossum_get_automation_projections. Branch on the response:
- available: true → full payload cached; the report gets threshold analysis.
- available: false → record status_code + reason verbatim and continue. Common modes (live-observed): HTTP 200 with no scenarios (queue lacks reviewed documents), 404 (queue not visible to this token). Do not retry or treat as an error.
Queue settings. rossum_get_queue → the automation configuration lives in top-level queue fields (live-verified; there is no settings.automation object): automation_enabled (bool), automation_level (never / confident / always), default_score_threshold, plus settings.suggested_edit (disable / ...). automation_level: never directly explains an automation_disabled document blocker.
Schema. rossum_get_schema (schema ID is in the queue payload) → which fields exist, which are formula/manual fields. Workflow fields (e.g. approval_name, sender_id_match) can carry validation errors that projections never model.
Compute. Run the helper on the cached payloads:

Read the full file on GitHub · 128 lines

Files

What ships with it

6 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.

2mo ago First seen · 128 lines · 84 tokens per session scan A 739bdaa49d77

Subscribe to this mod's changes

automation-report is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 84 tokens to every session and 1,746 once invoked, about $0.0003 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.

Analytics and metrics Finance and fintech

automation-report next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
automation-reportrossumai/claude-marketplace	Skill	5	5d ago	MIT	A	84	Claude Code
sector-rotationHKUDS/Vibe-Trading	Skill	38k	today	MIT	A	39	Claude Code, Codex
strategy-pivot-designertradermonty/claude-trading-skills	Skill	3.8k	yesterday	MIT	A	28	Claude Code, Codex
twitter-readerhimself65/finance-skills	Skill	3.5k	7d ago	MIT	A	110	Claude Code
energy-procurementhashgraph-online/awesome-codex-plugins	Skill	1.6k	yesterday	Apache-2.0	A	93	Claude Code, Codex
airdrop-hunting-guidenirholas/three.ws	Skill	273	yesterday	Apache-2.0	A	54	Claude Code, Codex
multi-expert-analyzerdigoal/blog	Skill	8.6k	today	GPL-2.0	A	292	Codex