loonheffingen

loonheffingen is a command for Claude Code from johnhout/knowledge-work-belastingzaken. It costs 10 tokens per session (391 once invoked), scanned A, original, MIT.

A workflow for Dutch payroll taxes, including periodic controls and checks related to WKR, the Dutch scheme for employee expenses and benefits.

In plain words
What is it for?
Use it to prepare a payroll-tax review for a reporting period, reconcile payroll totals, investigate unusual changes, flag possible WKR or worker-classification issues, and identify missing payroll exports.
Why use it?
It structures the evidence-gathering and reconciliation work needed for a payroll-tax review. It also directs users to verify deadlines and legal references with official Dutch sources.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is If placeholders are unclear, see [CONNECTORS.md](../CONNECTORS.md)..

Part of the belastingadviseur plugin — 8 skills, 8 commands, 5 MCP servers shipped together

Good fit Use it to prepare a payroll-tax review for a reporting period, reconcile payroll totals, investigate unusual changes, flag possible WKR or worker-classification issues, and identify missing payroll exports.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/johnhout/knowledge-work-belastingzaken
agentmods
npx agentmods add commands/johnhout/knowledge-work-belastingzaken/loonheffingen

Made for: Claude Code.

Or install belastingadviseur, the plugin that ships this one along with the rest of its 8 skills, 8 commands, 5 MCP servers.

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 loonheffingen

README.md
[![agentmods](https://agentmods.dev/badge/commands/johnhout/knowledge-work-belastingzaken/loonheffingen/github.svg)](https://agentmods.dev/commands/johnhout/knowledge-work-belastingzaken/loonheffingen)
Your own site
<a href="https://agentmods.dev/commands/johnhout/knowledge-work-belastingzaken/loonheffingen"><img src="https://agentmods.dev/badge/commands/johnhout/knowledge-work-belastingzaken/loonheffingen/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 loonheffingen

Your own site · 80×15
<a href="https://agentmods.dev/commands/johnhout/knowledge-work-belastingzaken/loonheffingen"><img src="https://agentmods.dev/badge/commands/johnhout/knowledge-work-belastingzaken/loonheffingen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 391 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 $0.00010 $0.00391
Opus 5 $0.00005 $0.00196
Sonnet 5 $0.00002 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 9d ago against content hash eaf56fb2cd95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

loonheffingen 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 9d 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.

commands/loonheffingen.md · 55 lines

What it actually says

Loonheffingen / Payroll Taxes

If placeholders are unclear, see CONNECTORS.md.

Important / Belangrijk: This workflow support is not legal or fiscal advice. Require review by a qualified Dutch tax professional.

Prepare payroll tax workflow including periodic controls and WKR attention points.

Usage

/belastingadviseur:loonheffingen <tijdvak>

Workflow

  1. Confirm payroll scope:
  • Reporting period and employer entity
  • Active payroll setups and known exceptions
  1. Gather payroll evidence:
  • Payroll runs, wage summaries, and benefits overview
  • WKR-related expense data and categorization support
  1. Control framework:
  • Reconcile payroll tax totals with payroll administration
  • Check unusual deviations by period and employee groups
  • Flag potential WKR or classification issues for review
  1. Official-source verification:
  • Verify payroll filing timing and procedural obligations on belastingdienst.nl
  • Verify legal interpretation references on wetten.overheid.nl where needed
  • Capture URL and retrieval date
  1. Fallback behavior:
  • If ~~salarisadministratie is not connected, request period export files
  • If evidence is incomplete, classify as non-final draft
  • If official verification cannot be completed, mark affected guidance as unverified

Required Output Format (Use Exactly)

  1. Context / Context
  2. Assumptions / Aannames
  3. Required Documents / Benodigde stukken
  4. Step-by-step / Stappenplan
  5. Checks & Risks / Controles en risico's
  6. Next Actions / Volgende acties
  7. Sources (official) / Bronnen (officieel)
  8. Professional Review Disclaimer / Disclaimer deskundige beoordeling
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. 9d ago First seen · 55 lines · 10 tokens per session scan A eaf56fb2cd95

Subscribe to this mod's changes

loonheffingen is a command published in the GitHub repository johnhout/knowledge-work-belastingzaken (6 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 391 once invoked, about $0.0001 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.