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 skills-il/tax-and-finance --skill us-person-israeli-investment-checkgit clone --depth 1 https://github.com/skills-il/tax-and-financeWrote 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/skills-il/tax-and-finance/us-person-israeli-investment-check)<a href="https://agentmods.dev/skills/skills-il/tax-and-finance/us-person-israeli-investment-check"><img src="https://agentmods.dev/badge/skills/skills-il/tax-and-finance/us-person-israeli-investment-check/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/skills-il/tax-and-finance/us-person-israeli-investment-check"><img src="https://agentmods.dev/badge/skills/skills-il/tax-and-finance/us-person-israeli-investment-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 204 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00216 | $0.03675 |
| Opus 5 | $0.00108 | $0.01837 |
| Sonnet 5 | $0.00043 | $0.00735 |
| Haiku 4.5 | $0.00022 | $0.00367 |
Grade A, and why
us-person-israeli-investment-check 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
US-Person Israeli Investment Check
Legal notice
This is a free information tool operated by an artificial intelligence model. It applies published statutory tests and the criteria in a published Revenue Procedure to product features you describe, and produces a screening table. It does all of this without the involvement, review, or approval of a licensed tax adviser, accountant, or attorney.
It is not tax advice, it is not a filed return, and it is not a professional opinion. It does not, and cannot, give you a final classification of any product. The IRS has never issued guidance naming Israeli savings products, whether a particular arrangement is a foreign trust or a PFIC for US purposes turns on that specific plan's terms and on that specific fund's holdings, and practitioners genuinely differ. What this tool produces is a preliminary screening worksheet: which test a product appears to pass or fail, and the question to put to a preparer. It does not read your plan documents, does not examine any fund's actual holdings, does not make or evaluate any election, and does not prepare any form.
An AI model can err, omit data, or present a wrong conclusion. Any text it produces is an automatic draft for personal organisation only and must never be submitted to any authority as it stands.
Responsibility for reporting and for paying tax is yours, the binding assessment is made by the tax authority concerned, whether the Israeli Tax Authority or the IRS, and representation before a tax authority is reserved to those permitted to do so by law. This tool is not a substitute for advice that takes into account the particular data and needs of each person. Criteria and thresholds change, so verify each one against the primary sources under Reference Links before relying on it.
Problem
An Israeli employee is enrolled by default into exactly the products the US tax code treats worst. A keren hishtalmut is tax free in Israel and may be a reportable foreign trust in the US. A kranot neemanut or a TASE ETF is an ordinary savings choice in Israel and is very likely a PFIC, taxed under a punitive default regime designed to remove the benefit of deferral. Most people discover this years later, holding a decade of unreported positions, because nothing in the Israeli sales process mentions it and most online guidance either overstates the problem or waves it away.
What ships with it
7 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 · 237 lines · 216 tokens per session scan A 1f07af220bb4
us-person-israeli-investment-check is a skill published in the GitHub repository skills-il/tax-and-finance (34 stars, last pushed 3d ago), licensed MIT. It adds 216 tokens to every session and 3,675 once invoked, about $0.0011 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 2026-08-30.
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.