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 agentmods add skills/skills-il/localization/hebrew-ocr-formsnpx skills add skills-il/localization --skill hebrew-ocr-formsgit clone --depth 1 https://github.com/skills-il/localizationWrote 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/localization/hebrew-ocr-forms)<a href="https://agentmods.dev/skills/skills-il/localization/hebrew-ocr-forms"><img src="https://agentmods.dev/badge/skills/skills-il/localization/hebrew-ocr-forms.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.03774 |
| Opus 5 | $0.00057 | $0.01887 |
| Sonnet 5 | $0.00023 | $0.00755 |
| Haiku 4.5 | $0.00011 | $0.00377 |
Grade B, and why
hebrew-ocr-forms scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Solution: Install with `sudo apt-get install tesseract-ocr-heb` (Ubuntu) or `brew install tesseract-lang` (macOS). Verify with `tesseract --list-langs`. How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hebrew OCR Forms
Instructions
Step 1: Identify the Form Type
| Form Type | Source | Key Identifiers | Common Fields |
|---|---|---|---|
| Nesach Tabu | Land Registry | "נסח טאבו", "לשכת רישום המקרקעין" | Gush, Chelka, Owner, Liens |
| Tofes 106 | Tax Authority | "טופס 106", "דו״ח שנתי למעביד" | Salary, Tax, Employer |
| Ishur Nikui | Tax Authority | "אישור ניכוי מס במקור" | Tax rate, Validity, TZ |
| Tofes 857 | Tax Authority | "טופס 857", "רווח הון" | Transaction, Gain, Tax |
| Ishur Zkauyot | Bituach Leumi | "אישור זכאויות", "ביטוח לאומי" | Benefit type, Amount |
| Tofes 100 | Bituach Leumi | "טופס 100", "דין וחשבון" | Employees, Wages |
| Rishayon Rechev | Vehicle Licensing | "רישיון רכב" | Plate, Owner, Expiry |
Step 2: Preprocess the Scanned Image
See scripts/preprocess_image.py for the full preprocessing pipeline. Key steps:
- Convert to grayscale
- Deskew -- Israeli forms are often slightly rotated from scanning
- Binarize with adaptive threshold -- handles uneven lighting from scanners
- Remove noise with morphological operations
Step 3: Run Hebrew OCR with Tesseract
See scripts/extract_form_fields.py for the full extraction pipeline.
Tesseract configuration for Hebrew forms:
config = (
'--oem 1 ' # LSTM neural net (best for Hebrew)
'--psm 6 ' # Assume uniform block of text
'-l heb+eng ' # Hebrew + English (forms have both)
'-c preserve_interword_spaces=1' # Keep spacing for field alignment
)
- For tabular forms (Tabu, Tofes 106), use PSM 4 instead of PSM 6
- Always use LSTM mode (--oem 1) for best Hebrew accuracy
- Include both heb and eng languages since forms mix Hebrew and English/numbers
Step 4: Extract Fields by Form Type
Tabu Extract (Nesach Tabu) key fields:
- Gush (block) number: look for "גוש" followed by digits
- Chelka (parcel) number: look for "חלקה" followed by digits
- Sub-parcel (tat-chelka): mandatory for an apartment in a shared building; note it is NOT necessarily the apartment number
- Owner name: follows "בעלים" or "שם הבעלים"
- ID number (TZ): follows "ת.ז." or "מספר זהות", 9 digits
- Ownership share (chelek): a fraction of the whole, e.g. "1/2", "125/1000", or "בשלמות" (in full). Keep it verbatim, do NOT convert to a decimal
- Right type: "בעלות" (ownership), "חכירה" (lease), "חכירה לדורות" (generational lease)
What ships with it
10 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 7.0 KB
- metadata.json 1.4 KB
- optimization-log.json 983 B
- references/israeli-form-types.md 3.0 KB
- references/nesach-tabu-structure.md 7.2 KB
- scripts/extract_form_fields.py 9.0 KB runs code
- scripts/preprocess_image.py 5.1 KB runs code
- scripts/tabu_to_spreadsheet.py 13 KB runs code
- SKILL_HE.md 19 KB
- stderr.txt 0 B
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.
- 4d ago First seen · 204 lines · 114 tokens per session scan B d386e172cc29
hebrew-ocr-forms is a skill published in the GitHub repository skills-il/localization (23 stars, last pushed 10d ago), licensed MIT. It adds 114 tokens to every session and 3,774 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
translate-book
Translate books (PDF/DOCX/EPUB) into any language using parallel sub-agents. Converts input -> Markdown chunks -> translated chunks -> HTML/DOCX/EPUB/PDF.
docutranslate
Use when translating documents locally via LLM — PDF, Word, Excel, Markdown, SRT subtitles with format preservation. DocuTranslate: LLM-powered multi-format local file translation tool with MCP server support.
doc-translator
将 PDF 格式或 Web Page 格式的源文档转换成保持原排版格式的 Markdown 格式精译中文文档。.
translate-academic-paper
Full workflow for translating an academic paper PDF into a polished, self-contained HTML with a three-way view toggle (Chinese-only / bilingual / original-only). Covers document triage (native vs OCR'd-scan vs no-text-layer scan), column-aware text extraction, glossary building with web-verified standard term…
kolmopdf
Use when the user explicitly wants KolmoPDF cloud processing of a PDF/Markdown file — parse PDF to Markdown, layout-preserving PDF translation, Markdown export (DOCX/HTML/PDF/LaTeX), or parse-time reading aids (outline/summary). Prefer Jobs API v1 via curl/Bash when MCP tools are unavailable. Do NOT invent…
academic-pdf-translation
将学术 PDF 翻译并重建为可读、可检索、可逐页验收的目标语言版本。用于全文翻译、旧译本修复、版式与行距审查、图表和截图文字本地化、语义忠实度复核、批量文献画像、源译对照图生成及 Zotero 收尾。简体中文流程已通过代表样本验证；繁体中文、日语、韩语及拉丁字母语言提供实验性配置，须先验收代表页。.