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 israeli-insurance-duplication-checkergit 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/israeli-insurance-duplication-checker)<a href="https://agentmods.dev/skills/skills-il/tax-and-finance/israeli-insurance-duplication-checker"><img src="https://agentmods.dev/badge/skills/skills-il/tax-and-finance/israeli-insurance-duplication-checker/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/israeli-insurance-duplication-checker"><img src="https://agentmods.dev/badge/skills/skills-il/tax-and-finance/israeli-insurance-duplication-checker.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 | $0.00210 | $0.07373 |
| Opus 5 | $0.00105 | $0.03687 |
| Sonnet 5 | $0.00042 | $0.01475 |
| Haiku 4.5 | $0.00021 | $0.00737 |
Grade A, and why
israeli-insurance-duplication-checker 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Israeli Insurance Duplication Checker
Legal notice
This skill is not insurance advice (ייעוץ ביטוחי) and not insurance marketing (שיווק ביטוחי), and it is not delivered by a licensed agent, advisor or marketer. It maps cover the user already holds and explains the statutory rules that decide whether two policies can pay twice for the same event. It does not recommend buying, replacing or surrendering a named product, does not exercise professional discretion on anyone's behalf, and does not replace a licensed insurance agent or advisor, the insurer, or the kupat cholim. Nothing here is legal advice. Cancelling underwritten cover is irreversible in practice: state the conclusion, then tell the user to confirm it with the insurer or a licensed agent, and never let them cancel before replacement cover is confirmed active.
Problem
Israelis routinely pay for the same cover in three or four places at once: a שב"ן plan plus a private health policy, an employer group policy over both, a service subscription that is also a home-policy rider and a card benefit. About 37% of the statutorily insured public, roughly 3.4 million people, hold commercial health cover alongside שב"ן, and the State Comptroller puts the overpayment at a floor of hundreds of millions of shekels a year. הר הביטוח holds no שב"ן data at all, so the official tool structurally cannot see the most common overlap in the country. And some of what looks like duplication is not waste: cancelling it destroys cover the user can never buy back.
The three-tier test (apply this before anything else)
Israeli law sorts insurance by PAYMENT MECHANISM, not by subject matter. Getting this wrong is the single biggest failure mode. Do not reason from "these two policies both mention surgery"; reason from how each one pays.
Tier the BENEFIT, not the policy. A tier is a property of a CLAIM, not of an inventory line, and one policy can sit in two tiers at once. The kupot group סיעוד policy is the clearest case: it pays "פיצוי כספי של 5,000 ש"ח לחודש למשך 60 חודשים אם הוא שוהה בביתו, ושיפוי כספי בסך 10,000 ש"ח לחודש למשך 60 חודשים אם שוהה במוסד סיעודי". Fixed sum at home, reimbursement in an institution, one contract. A private health policy that carries a fixed-sum מחלות קשות rider alongside reimbursement ניתוחים cover has the same shape.
What ships with it
13 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.
- evidence.json 43 KB
- metadata.json 1.2 KB
- optimization-log.json 3.3 KB
- references/cancellation-letter-he.md 3.0 KB
- references/claims-and-escalation.md 2.4 KB
- references/domain-checklist.md 7.1 KB
- references/line-by-line-detail-he.md 9.1 KB
- references/line-by-line-detail.md 22 KB
- references/reference-links-he.md 3.6 KB
- references/reference-links.md 2.9 KB
- references/worked-examples-he.md 10 KB
- references/worked-examples.md 7.6 KB
- SKILL_HE.md 52 KB
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 · 216 lines · 210 tokens per session scan A f8fe6be19440
israeli-insurance-duplication-checker is a skill published in the GitHub repository skills-il/tax-and-finance (34 stars, last pushed 3d ago), licensed MIT. It adds 210 tokens to every session and 7,373 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.