expense-categorizer

expense-categorizer is a skill for Claude Code from Ootto-AI/claude-invoice-skills. It costs 61 tokens per session (493 once invoked), scanned A, original, MIT.

An expense-sorting aid that classifies bank or card statement transactions, totals spending by category, and lists entries needing human review.

In plain words
What is it for?
Use it with statement data containing dates, descriptions, and amounts to categorize spending across areas such as software, payroll, travel, taxes, and fees.
Why use it?
It turns raw transaction rows into a bookkeeping-friendly summary and highlights uncertain, personal, duplicate, or otherwise questionable entries.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the claude-invoice-skills plugin — 5 skills shipped together

Good fit Use it with statement data containing dates, descriptions, and amounts to categorize spending across areas such as software, payroll, travel, taxes, and fees.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ootto-ai/claude-invoice-skills/expense-categorizer
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 Ootto-AI/claude-invoice-skills --skill expense-categorizer
Clone the repo
git clone --depth 1 https://github.com/Ootto-AI/claude-invoice-skills

Made for: Claude Code.

Or install claude-invoice-skills, the plugin that ships this one along with the rest of its 5 skills.

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 expense-categorizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ootto-ai/claude-invoice-skills/expense-categorizer/github.svg)](https://agentmods.dev/skills/ootto-ai/claude-invoice-skills/expense-categorizer)
Your own site
<a href="https://agentmods.dev/skills/ootto-ai/claude-invoice-skills/expense-categorizer"><img src="https://agentmods.dev/badge/skills/ootto-ai/claude-invoice-skills/expense-categorizer/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 expense-categorizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ootto-ai/claude-invoice-skills/expense-categorizer"><img src="https://agentmods.dev/badge/skills/ootto-ai/claude-invoice-skills/expense-categorizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 493 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 $0.00061 $0.00493
Opus 5.5 $0.00024 $0.00197
Sonnet 5.5 $0.00012 $0.00099
Haiku 4.5 $0.00006 $0.00049

Measured 2mo ago against content hash eae16c384c8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

expense-categorizer 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.

skills/expense-categorizer/SKILL.md · 56 lines

What it actually says

Expense Categorizer

Sort raw statement rows into clean categories, summarize spend, and flag anything that needs a human look.

When to use

You have a bank/card statement and want it categorized for bookkeeping or a quick read on where the money is going.

What you'll need

Statement rows (date, description, amount) pasted as text or CSV.

Instructions

Run this prompt with the user's transactions:

You are my bookkeeper. Categorize the transactions below into clean expense categories.

Transactions:
[paste statement rows: date, description, amount]

Use these categories (pick the best fit, don't invent new ones unless nothing fits):
Software & subscriptions, Advertising & marketing, Contractors & freelancers,
Payroll, Rent & utilities, Travel, Meals & entertainment, Office supplies,
Bank & payment fees, Taxes, Owner draw / personal, Other.

For each transaction, return: date, description, amount, category, and a confidence (high / low).

Then give me:
1. A summary table of total spend per category, sorted highest to lowest.
2. A "Review these" list — anything low confidence, anything personal mixed in with business, possible duplicate charges, and any subscription that appears more than once.
3. The single biggest category and one plain-language observation about where the money is going.

Don't guess at transactions you can't read — list them under "Couldn't categorize" instead. No tax advice, just categorization.

Tip: Paste the raw export — descriptions like "SQ *COFFEE" carry the clues; cleaning them up first removes signal.


Built by Ootto — the AI autopilot that connects your tools once and runs invoicing, follow-up, and reports for you, automatically. Book a demo →

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 · 56 lines · 61 tokens per session scan A eae16c384c8a

Subscribe to this mod's changes

expense-categorizer is a skill published in the GitHub repository Ootto-AI/claude-invoice-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 493 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.

Related

expense-categorizer compared with skills from other repositories

expense-categorizer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
expense-categorizerOotto-AI/claude-invoice-skillsSkill14mo agoMITA61Claude Code
pandadoc-invoice-handoffPandaDoc/mcp-server-guideSkill3yesterdayMITA65Claude Code
visma-eaccountingjiraporn-junext/visma-eaccounting-skillSkill19mo agoMITB90Claude Code, Codex
ma-playbookalirezarezvani/claude-skillsSkill29k3d agoMITA29Claude Code
fiscalisteromainsimon/paperasseSkill2.6k2d agoMITA320Claude Code, Codex
comptableromainsimon/paperasseSkill2.6k2d agoMITA153Claude Code, Codex
syndicromainsimon/paperasseSkill2.6k2d agoMITA204Claude Code, Codex