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-expense-categorizergit 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-expense-categorizer)<a href="https://agentmods.dev/skills/skills-il/accounting/israeli-expense-categorizer"><img src="https://agentmods.dev/badge/skills/skills-il/accounting/israeli-expense-categorizer/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-expense-categorizer"><img src="https://agentmods.dev/badge/skills/skills-il/accounting/israeli-expense-categorizer.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 | $0.00152 | $0.07565 |
| Opus 5 | $0.00076 | $0.03782 |
| Sonnet 5 | $0.00030 | $0.01513 |
| Haiku 4.5 | $0.00015 | $0.00756 |
Grade A, and why
israeli-expense-categorizer 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 11d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Israeli Expense Categorizer
Legal notice
This is a free information tool operated by an AI model. It explains the tax rules and helps you organise your own figures. All of its outputs are produced automatically by an AI model, with no involvement, review, or approval by a tax adviser or accountant. The output is not a tax opinion, not a return prepared by a licensed representative, and not professional advice, but a general calculation and explanation only: it does not examine the full extent of your income or your complete documents. An AI model may err, omit data, or present a wrong conclusion.
Any form or text this tool produces is an automatic draft for your personal preparation only, and is not a filed return. Responsibility for reporting and for paying the tax is yours, the binding computation is the Tax Authority's, and representation before the Tax Authority is reserved to those permitted by law. This tool is not a substitute for advice that takes account of the particular circumstances and needs of each person. Consult a tax adviser or accountant before filing or paying. All use of its output is the user's sole responsibility.
Instructions
Step 1: Gather expense data
Collect the expense information to categorize. Accept input in any of these formats:
- CSV or Excel file with columns: date, vendor, amount, description
- Bank/credit card statement export
- Free-text list of expenses
- Individual expense for quick classification
If a file path is provided, read the file. If expenses are described in text, parse them into structured records.
Step 2: Determine business entity type
Ask the user for their business registration type if not already known:
- Osek Patur (exempt dealer): Annual turnover under the threshold (NIS 122,833 for 2026, up from NIS 120,000 in 2025). Cannot charge or deduct VAT. Income tax deductions still apply.
- Osek Murshe (licensed dealer): Can charge and deduct VAT. Full income tax deductions apply.
- Company (Chevra Ba'am): Corporate tax rules apply. Full VAT deduction on eligible business expenses, but subject to the same תקנה 14 / תקנה 18 limits as an osek murshe (no input VAT on a private-car purchase, the 2/3 vs 1/4 split on running-cost VAT) and the same אירוח / meals VAT disallowance. A company is NOT exempt from these limits.
What ships with it
6 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.
- 11d ago First seen · 286 lines · 152 tokens per session scan A 190ede2d3759
israeli-expense-categorizer is a skill published in the GitHub repository skills-il/accounting (10 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 7,565 once invoked, about $0.0008 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
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.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
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.