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.
npx skills add cyanxxy/nl-tax-agent-skills --skill nl-tax-box2git clone --depth 1 https://github.com/cyanxxy/nl-tax-agent-skillsWrote 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/skills/cyanxxy/nl-tax-agent-skills/nl-tax-box2)<a href="https://agentmods.dev/skills/cyanxxy/nl-tax-agent-skills/nl-tax-box2"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-box2/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/skills/cyanxxy/nl-tax-agent-skills/nl-tax-box2"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-box2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.01546 |
| Opus 5 | $0.00023 | $0.00773 |
| Sonnet 5 | $0.00009 | $0.00309 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
nl-tax-box2 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NL Tax Box 2
Background helper for Box 2 substantial-interest preparation notes.
Use this skill only for source-backed preparation support for:
annual_2025: annual actual Box 2 inputs from taxpayer evidence.provisional_2026: estimated or baseline-derived Box 2 inputs for a provisional assessment.
This helper may be called through a Skill/Task tool or inlined by an owning workflow when no such tool exists. The same output contract applies either way.
Read first
Resolve every workspace/... path against workspace_root from
session-progress.yaml (or profile.yaml); never create a second
workspace/ tree. _shared/ is the plugin-shared folder at this skill's
../_shared/. Read ../_shared/runtime-contract.md first. Resolve bundled
files relative to this skill directory with the host's skill-resource or file
tools. Do not depend on shell visibility or vendor-specific environment
variables.
reference/box2-annual-2025.mdreference/box2-provisional-2026.md
Python is optional. Do not ask the taxpayer to install Python and do not make
completion depend on it. The agent owns classification, questions, and the
workpack. If an already-resolved bundled script is available, the agent may run
scripts/calculate_box2_tax.py input.json as a mechanical cross-check after it
has built an explicit, source-backed payload. The script validates before it
calculates and records check_performed_by: checked_by_script.
Whether or not the script is run, apply this same checklist and record
check_performed_by: checked_by_agent for the manual path:
- Require explicit
workflowand matching integertax_year; never infer one from the other. - Require
substantial_interest_pct, actual booleans forresident_full_yearandstandard_ab_case, and explicit source-backed values forregular_benefits,disposal_benefit, andloss_setoff. - Reject unknown payload fields instead of treating a misspelled amount as zero. Other amount fields may be included only when collected from evidence.
- Stop before calculation for a non-standard residence/AB case or any complex marker listed under Never.
- When
loss_setoffis greater than zero, calculate only after a reviewer has confirmed it and the payload recordsloss_setoff_reviewed: trueplus a non-emptyloss_setoff_source; otherwise return it as a review question. - For a partner allocation, require an actual
full_year_fiscal_partner: trueboolean and percentages totaling 100%. - Apply the year-pinned lower bracket before the upper bracket, then apply Dutch dividend withholding tax as a credit. Treat the result as indicative.
What ships with it
4 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.
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.
- 12d ago First seen · 126 lines · 45 tokens per session scan A e9918b0b2866
nl-tax-box2 is a skill published in the GitHub repository cyanxxy/nl-tax-agent-skills (10 stars, last pushed 17d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,546 once invoked, about $0.0002 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 skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
regulatory-analysis
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.