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/accounting --skill israeli-amuta-compliancegit clone --depth 1 https://github.com/skills-il/accountingWrote 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/accounting/israeli-amuta-compliance)<a href="https://agentmods.dev/skills/skills-il/accounting/israeli-amuta-compliance"><img src="https://agentmods.dev/badge/skills/skills-il/accounting/israeli-amuta-compliance/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/accounting/israeli-amuta-compliance"><img src="https://agentmods.dev/badge/skills/skills-il/accounting/israeli-amuta-compliance.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 | $0.00192 | $0.07285 |
| Opus 5.5 | $0.00077 | $0.02914 |
| Sonnet 5.5 | $0.00038 | $0.01457 |
| Haiku 4.5 | $0.00019 | $0.00728 |
Grade A, and why
israeli-amuta-compliance 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 21d 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Israeli Amuta Compliance
Legal notice
This is a free information tool operated by an AI model, with no accountant or lawyer involved, reviewing it or approving it. It produces checklists, gap lists and summaries of deadlines and amounts for internal organisation only, for the amuta's own officers to review and adopt themselves. It is not legal advice and not accounting advice.
It does not produce, and must not be presented as producing, an audited financial statement, an auditor's opinion, or any other work product reserved to a licensed accountant under the Accountants Law. Auditing a financial report is reserved to a רואה חשבון. Drafting or amending a תקנון, and any legal opinion, belong to a lawyer: the Bar Association Law reserves those whether or not a fee is charged, so the fact that this tool is free is not a defence. It drafts no legal instrument, and any text it does produce is an automatic draft for personal organisation only, not a document prepared by a lawyer or an accountant.
The tool may err, omit data, or present a wrong conclusion, and it is not a substitute for advice that takes account of the particular circumstances and needs of each person. Responsibility for filing and payment is yours, the binding determination belongs to the Registrar of Associations and to the Tax Authority as the case may be, and representation before the Tax Authority is reserved to those entitled to it by law.
Figures in this skill carry a year. Israeli thresholds are index-linked and are re-gazetted annually. Confirm the operative figure for the year you are filing before relying on it.
Problem
An amuta loses its אישור ניהול תקין for reasons that have nothing to do with how well it runs its programmes: it filed the wrong year's reports, it never appointed the organ its turnover band requires, or it paid the wrong fee tier and cannot get the difference back. The rules sit across the Associations Law, a Registrar circular, a fee regulation and a Tax Authority execution instruction, and the public guides that summarise them are wrong often enough to be dangerous. Without the certificate the amuta cannot receive state support, cannot apply to most foundations, and its donors cannot claim their tax credit.
What ships with it
11 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.
- CHANGELOG.md 3.9 KB
- eval_queries.txt 1.9 KB
- evidence.json 56 KB
- metadata.json 3.3 KB
- optimization-log.json 2.2 KB
- references/domain-checklist.md 16 KB
- references/donor-rules.md 1.6 KB
- references/filing-package.md 5.6 KB
- references/refusal-path.md 3.0 KB
- scripts/band_check.py 15 KB runs code
- SKILL_HE.md 38 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.
- 21d ago Changed · +25 lines 2ddc3a20fabd
- 1mo ago First seen · 413 lines · 192 tokens per session scan A 8661ba9653fa
israeli-amuta-compliance is a skill published in the GitHub repository skills-il/accounting (13 stars, last pushed 3d ago), licensed MIT. It adds 192 tokens to every session and 7,285 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-10.
Other skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
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.
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.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.
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…
china-process-letter
A guide for writing process letters and bid instructions for Chinese A-share mergers and acquisitions. These documents tell potential buyers how to submit an initial offer, final bid, attend management meetings, and use a due-diligence data room.