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 israeli-cyber-regulationsgit 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/israeli-cyber-regulations)<a href="https://agentmods.dev/skills/skills-il/security-compliance/israeli-cyber-regulations"><img src="https://agentmods.dev/badge/skills/skills-il/security-compliance/israeli-cyber-regulations/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/israeli-cyber-regulations"><img src="https://agentmods.dev/badge/skills/skills-il/security-compliance/israeli-cyber-regulations.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 | $0.00206 | $0.07765 |
| Opus 5 | $0.00103 | $0.03882 |
| Sonnet 5 | $0.00041 | $0.01553 |
| Haiku 4.5 | $0.00021 | $0.00777 |
Grade A, and why
israeli-cyber-regulations 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Israeli Cyber Regulations
Legal notice
This is a free information tool operated by an artificial-intelligence model. It maps which Israeli cybersecurity regulatory instruments apply to an organisation, summarises their published requirements, and helps prepare gap analyses and audit evidence lists. All of its output is produced automatically, without the involvement, review or approval of a lawyer, a compliance officer, or any licensed professional.
The output is not legal advice and not a legal opinion, and any text it drafts is not a document prepared by a lawyer. It is a summary of published regulatory material. The tool does not read the organisation's contracts, licences or supervisory correspondence, does not know its licence conditions, its designation status, or which instruments actually bind it. Regulatory instruments are amended, consolidated and repealed frequently, sometimes with effect from a date later than this tool's information, and an artificial-intelligence model may err, omit an instrument, or cite one no longer in force.
Do not rely on this output to determine a reporting obligation, a filing deadline, or whether an incident is disclosable. Verify every directive, regulation and statute against the regulator's own current publication, and before any filing, disclosure, board representation or approach to a regulator, consult a lawyer or a qualified compliance professional. This tool is not a substitute for advice that takes account of the particular data and needs of each person. Any use of the output is the sole responsibility of the user.
Scope note. For privacy-law compliance (data protection, consent, PPA registration) use the israeli-privacy-compliance skill; only the cyber-facing breach-notification duty is carried here.
Instructions
Step 1: Identify Applicable Regulatory Framework
Determine which Israeli cybersecurity regulations apply to the user's organization.
| Framework | Applies To | Regulator | Key Focus |
|---|---|---|---|
| INCD National Directives | All organizations, mandatory for critical infrastructure | Ma'arach HaSyber (INCD) | Risk management, incident reporting, baseline controls |
| BOI Directive 364 (IN FORCE since 18/05/2026) | Banking corporations, credit-card companies, and a payment-service provider of systemic importance. NOT insurers | Bank of Israel (BOI) | "Management of IT, Information Security and Cyber Protection Risks". Published 18/11/2024 (circular 2799). The operative framework. On 18/05/2026 it repealed Directives 357, 361 and 363. Map all control programs to 364 |
| BOI Directives 357 / 361 / 363 | -- | Bank of Israel (BOI) | REPEALED on 18/05/2026 by 364. Historical only. 361 was Cyber Defense Management, 357 was IT Management, 363 was supply-chain cyber risk. Do NOT write a control program against these |
| BOI Directive 366 (updated 17/06/2026) | Banks | Bank of Israel (BOI) | "Reporting of technological-failure, information-security and cyber-attack events", circular 2848, update 4. The incident-reporting hook. Update 4 added a duty to report a serious security event as defined in section 31 of the Financial Information Service Law, 5782-2021, with a parallel change to reporting directive 880 |
| BOI Directive 362 (updated 17/06/2026) | Banks (cloud) | Bank of Israel (BOI) | "Cloud Computing", circular 2849, version 5. Now written as complementing 364. Internal board/management approval by materiality, plus annual reporting to Banking Supervision under reporting directive 881. See the Gotcha: this is not a prior-approval regime |
| BOI Directive 368 (01/09/2025) | Banks | Bank of Israel (BOI) | "Open Banking in Israel", circular 2826. Open Banking is now a directive, no longer only a roadmap |
| Institutional Bodies Circular 2016-9-14 | Insurers, pension and provident bodies (גופים מוסדיים) | Capital Market, Insurance and Savings Authority, not BOI | "Cyber risk management in institutional bodies", 31/08/2016. Issued under the Supervision of Financial Services (Insurance) Law 5741-1981 and the Provident Funds Law 5765-2005. This, not Directive 364, is the instrument for an insurer |
| Payment Services and Payment Initiation Law, 5783-2023 | Non-bank payment-service and payment-initiation licensees | Israel Securities Authority, which the Law defines as "הרשות" | Licensing conditions include information security, cyber protection, risk management and business continuity "according to rules the Authority set in regulator instructions" (הוראות מאסדר) |
| ISA Cyber Requirements | TASE-listed companies | Israel Securities Authority (ISA/Rashut) | Disclosure, board oversight, cyber risk reporting |
| MOH Health Cyber | Hospitals, HMOs, health-tech | Ministry of Health | Patient data protection, medical device security |
| CDPA Telecom Rules | Telecom providers | Ministry of Communications | Network security, lawful intercept, data retention |
What ships with it
8 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 · 297 lines · 206 tokens per session scan A e25c8449951a
israeli-cyber-regulations is a skill published in the GitHub repository skills-il/security-compliance (10 stars, last pushed 10d ago), licensed MIT. It adds 206 tokens to every session and 7,765 once invoked, about $0.0010 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…