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.
git clone --depth 1 https://github.com/johnhout/knowledge-work-belastingzakennpx agentmods add commands/johnhout/knowledge-work-belastingzaken/aftrekcheckWrote 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.
[](https://agentmods.dev/commands/johnhout/knowledge-work-belastingzaken/aftrekcheck)<a href="https://agentmods.dev/commands/johnhout/knowledge-work-belastingzaken/aftrekcheck"><img src="https://agentmods.dev/badge/commands/johnhout/knowledge-work-belastingzaken/aftrekcheck/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.
<a href="https://agentmods.dev/commands/johnhout/knowledge-work-belastingzaken/aftrekcheck"><img src="https://agentmods.dev/badge/commands/johnhout/knowledge-work-belastingzaken/aftrekcheck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00005 | $0.00372 |
| Opus 5 | $0.00003 | $0.00186 |
| Sonnet 5 | $0.00001 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
aftrekcheck 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 8d 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.
What it actually says
Aftrekcheck / Deduction Check
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.
Assess potential deductions and scheme eligibility for individual and business contexts.
Usage
/belastingadviseur:aftrekcheck <belastingjaar> [doelgroep]
Workflow
- Define taxpayer context:
- Individual household context, ZZP context, or BV context
- Financial and operational facts relevant to deductions
- Build deduction candidate list:
- Identify likely relevant deduction categories
- Distinguish high-confidence vs uncertain candidates
- Evidence and eligibility validation:
- Map every candidate to required supporting documents
- Flag missing evidence or conflicting data
- Official-source verification:
- Verify qualification criteria, thresholds, and limitations on
belastingdienst.nl - Verify legal references on
wetten.overheid.nlwhen statutory wording matters - Cite exact URL and retrieval date
- Fallback behavior:
- Without connectors, use user-provided data with clear assumptions
- Do not label any deduction as final if key eligibility or source verification is missing
Required Output Format (Use Exactly)
Context / ContextAssumptions / AannamesRequired Documents / Benodigde stukkenStep-by-step / StappenplanChecks & Risks / Controles en risico'sNext Actions / Volgende actiesSources (official) / Bronnen (officieel)Professional Review Disclaimer / Disclaimer deskundige beoordeling
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.
- 8d ago First seen · 53 lines · 5 tokens per session scan A f0e9f23d2c4e
aftrekcheck is a command published in the GitHub repository johnhout/knowledge-work-belastingzaken (6 stars, last pushed 6mo ago), licensed MIT. It adds 5 tokens to every session and 372 once invoked, about $0.0000 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.
Other commands, from other repositories
tax-review
Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.
billing-rate
Gestiona tarifas y facturas de servicios legales. Subcomandos: set (definir tarifa), calculate (calcular honorarios), invoice (generar factura), report (análisis), list (listar tarifas).
filings
Scan recent filings on a company and surface material events (director changes, new charges, capital events, insolvency markers). Works on GB / IE / CA / IS / FI / IM / LI / MX / KR.
monitor
AML transaction monitoring and suspicious activity reporting.
tax-planning
Optimize tax liability or ensure tax compliance.
child-support-calc
A calculator for Japanese child support and marital living costs, using the revised standard calculation method published in 2019. Child support is money paid for a child after divorce; marital living costs are shared living expenses while spouses live apart.