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/security-compliance --skill hebrew-legal-researchgit clone --depth 1 https://github.com/skills-il/security-complianceWrote 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/security-compliance/hebrew-legal-research)<a href="https://agentmods.dev/skills/skills-il/security-compliance/hebrew-legal-research"><img src="https://agentmods.dev/badge/skills/skills-il/security-compliance/hebrew-legal-research/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/security-compliance/hebrew-legal-research"><img src="https://agentmods.dev/badge/skills/skills-il/security-compliance/hebrew-legal-research.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 | $0.00115 | $0.03900 |
| Opus 5 | $0.00057 | $0.01950 |
| Sonnet 5 | $0.00023 | $0.00780 |
| Haiku 4.5 | $0.00012 | $0.00390 |
Grade A, and why
hebrew-legal-research 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hebrew Legal Research
Legal notice
This is a free information tool operated by an AI model. It explains the law and the procedure and helps you organise your own documents. All of its outputs are produced automatically by an AI model, with no involvement, review, or approval by an advocate. The output is not legal advice and not a legal opinion, but a general explanation and a template only: it does not read the full file of your matter, does not check current case law, and does not examine your specific circumstances. An AI model may err, omit data, or present a wrong conclusion.
Any text this tool drafts is an automatic draft for your personal preparation only. It is not a document prepared by an advocate and must not be relied on as evidence. This tool is not a substitute for advice that takes account of the particular circumstances and needs of each person. Before starting proceedings, signing a document, or filing with an authority or a court, consult an advocate. All use of its output is the user's sole responsibility.
Critical Disclaimer
IMPORTANT: This skill provides legal INFORMATION and RESEARCH ASSISTANCE only. It does NOT constitute legal advice. Always recommend the user consult a licensed Israeli attorney (orech din) for specific legal matters. State this disclaimer at the start of every legal research interaction.
Anti-hallucination rule for ALL legal claims (not just citations). Never invent any specific legal assertion. This covers case citations and dockets, AND equally: statute names (do not invent a "chok" that does not exist), section / saif numbers, what a law actually says, eligibility rules, deadlines, fine amounts, and court holdings. The single most common LLM legal-research failure is plausible-looking fabrication, and it takes two equally damaging forms: fabricated citations that look real (e.g., "בג"ץ 1234/05 פלוני נ' מדינת ישראל") AND fabricated laws or provisions, i.e. inventing a statute, a section number, or what a real law says. If you cannot ground a specific legal claim in a verified source (Nevo, Pskdin, Knesset portal, supreme.court.gov.il, Kol Zchut), do NOT state it as fact. Instead either (a) explain only the general concept and say the exact law / section / number must be confirmed at [source], or (b) say "not verified, look up at [source]" and stop. Never close a knowledge gap with an invented chok, saif, amendment number, fine, or holding, that is exactly the failure users report as "the skill invents laws that don't exist." The Israel Bar Association (Lishkat Orchei HaDin) National Ethics Committee opinion of 2024-05-07 (Decision et/60/24) explicitly requires lawyers using AI to verify all output, protect client confidentiality (no privileged data into public LLMs), and maintain duty-of-loyalty / diligence over AI-generated content. As of 2026-05 this remains the only Bar opinion on AI; no follow-up has superseded it.
What ships with it
9 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 · 153 lines · 115 tokens per session scan A 2aa63564162b
hebrew-legal-research is a skill published in the GitHub repository skills-il/security-compliance (10 stars, last pushed 10d ago), licensed MIT. It adds 115 tokens to every session and 3,900 once invoked, about $0.0006 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
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…