grootboek-anomalie-detectie

grootboek-anomalie-detectie is a skill for Claude Code from iwebdevnl/exact-online-ai-connect. It costs 117 tokens per session (4,723 once invoked), scanned A, original, MIT.

A bookkeeping check for finding common irregularities in Exact Online, an online accounting system. It looks for uncleared accounts, unusual amounts, duplicate entries, and implausible balance totals using account types and descriptions.

In plain words
What is it for?
Checking ledger quality, preparing year-end work, investigating suspected errors, finding non-zero clearing accounts, and spotting duplicates or unusual balances.
Why use it?
It helps uncover accounting errors that can be hard to find by reviewing ledger entries manually, without assuming that account numbers mean the same thing everywhere.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the exact-online-ai-connect plugin — 10 skills, 4 commands, 1 MCP server shipped together

Good fit Checking ledger quality, preparing year-end work, investigating suspected errors, finding non-zero clearing accounts, and spotting duplicates or unusual balances.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iwebdevnl/exact-online-ai-connect/grootboek-anomalie-detectie
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 iwebdevnl/exact-online-ai-connect --skill grootboek-anomalie-detectie
Clone the repo
git clone --depth 1 https://github.com/iwebdevnl/exact-online-ai-connect

Made for: Claude Code.

Or install exact-online-ai-connect, the plugin that ships this one along with the rest of its 10 skills, 4 commands, 1 MCP server.

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 grootboek-anomalie-detectie

README.md
[![agentmods](https://agentmods.dev/badge/skills/iwebdevnl/exact-online-ai-connect/grootboek-anomalie-detectie/github.svg)](https://agentmods.dev/skills/iwebdevnl/exact-online-ai-connect/grootboek-anomalie-detectie)
Your own site
<a href="https://agentmods.dev/skills/iwebdevnl/exact-online-ai-connect/grootboek-anomalie-detectie"><img src="https://agentmods.dev/badge/skills/iwebdevnl/exact-online-ai-connect/grootboek-anomalie-detectie/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 grootboek-anomalie-detectie

Your own site · 80×15
<a href="https://agentmods.dev/skills/iwebdevnl/exact-online-ai-connect/grootboek-anomalie-detectie"><img src="https://agentmods.dev/badge/skills/iwebdevnl/exact-online-ai-connect/grootboek-anomalie-detectie.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,723 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 $0.00117 $0.04723
Opus 5 $0.00059 $0.02361
Sonnet 5 $0.00023 $0.00945
Haiku 4.5 $0.00012 $0.00472

Measured 11d ago against content hash 35a44337d5cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

grootboek-anomalie-detectie 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 11d 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/exact-online/skills/grootboek-anomalie-detectie/SKILL.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grootboek Anomalie-detectie

Automatische controle op veelvoorkomende boekingsfouten en onregelmatigheden. Bespaart de boekhouder uren handmatig speurwerk en verhoogt de betrouwbaarheid van de administratie. Deze skill werkt in elke administratie omdat hij classificeert op rekeningtype (GLAccount.Type) en op omschrijving-trefwoorden, niet op administratie-specifieke grootboeknummers of codebereiken.

Waarom dit generiek is (lees dit eerst)

Grootboeknummers verschillen per administratie: 1050 is niet altijd een kruispost, 4100 niet altijd kantoorkosten. Wat wél in elke Exact Online-administratie identiek is, is het veld Type op de grootboekrekening, een vaste platform-brede classificatie (bijv. 12 = Bank, 24 = VAT, 90 = General). Classificeer op Type en op omschrijving-trefwoorden, nooit op vast nummer of codebereik. Zo blijft de detectie correct, ongeacht het rekeningschema van de klant.

Vuistregel: haal de relevante rekeningen altijd eerst live op met GLAccounts (op Type), lees hun Code uit de response, en gebruik díe codes in de saldo-query's. Nooit een aangenomen bereik als 1050-1099 in een filter zetten.

Waarom anomalie-detectie

Zelfs in goed bijgehouden administraties sluipen fouten erin: een factuur op de verkeerde grootboekrekening, een dubbele boeking door een importfout, of een tussenrekening die vergeten is. Handmatig controleren is tijdrovend en foutgevoelig. Geautomatiseerde detectie pakt de meest voorkomende problemen op.

In alle voorbeelden hieronder staat <jaar> voor het boekjaar dat je controleert. Bepaal dat aan het begin (huidig boekjaar of wat de gebruiker vraagt) en vul het overal in, gebruik geen vast jaartal. <administratiecode> op de analyze_data-calls is optioneel: laat je division weg, dan gebruikt de tool de geselecteerde administratie.

Controle-categorieën

1. Tussenrekeningen die niet op nul staan

De belangrijkste controle. Tussenrekeningen (kruisposten, vraagposten, tussenrekening uitgestelde kosten/omzet, PSP-tussenrekeningen) horen op nul te staan aan het einde van een periode.

Read the full file on GitHub · 368 lines

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. 11d ago First seen · 368 lines · 117 tokens per session scan A 35a44337d5cd

Subscribe to this mod's changes

grootboek-anomalie-detectie is a skill published in the GitHub repository iwebdevnl/exact-online-ai-connect (0 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 4,723 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

erpclaw

AI-native ERP system. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial reporting (including P&L / trial balance / spend grouped by department, project, cost center, location, or fund). 496 actions across 14…

avansaber/erpclaw · 136 tokens

tax-calculator

Calculate tax implications of trades and generate tax reports.

Signal-Execution-Labs/forex-trading-ai-agent · 13 tokens

jangbu-import

A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.

kimlawtech/korean-jangbu-for · 97 tokens

jangbu-tax

A financial-reporting tool that summarizes categorized transactions into a profit-and-loss statement and a simplified balance sheet. A profit-and-loss statement covers income and expenses over a period; a balance sheet shows assets, liabilities, and equity at a date.

kimlawtech/korean-jangbu-for · 82 tokens

accountant-expert

Expert-level accounting, tax, financial reporting, and accounting systems. Use when the user mentions accounting, tax, financial reporting, GAAP, or IFRS, or when the task involves Accounting Principles, Financial Statements, Tax & Compliance, or Accounting Systems.

personamanagmentlayer/pcl · 56 tokens

sap-co

This skill handles all SAP CO (Controlling) topics: cost center accounting, profit center accounting, internal orders, product costing, profitability analysis (CO-PA), assessment and distribution cycles, actual vs plan postings, settlement, and CO period-end closing. Use when user mentions CO, cost center, profit…

BoxLogoDev/sapstack · 127 tokens