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-shelter-guidegit 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-shelter-guide)<a href="https://agentmods.dev/skills/skills-il/security-compliance/israeli-shelter-guide"><img src="https://agentmods.dev/badge/skills/skills-il/security-compliance/israeli-shelter-guide/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-shelter-guide"><img src="https://agentmods.dev/badge/skills/skills-il/security-compliance/israeli-shelter-guide.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 | $0.00195 | $0.07496 |
| Opus 5 | $0.00097 | $0.03748 |
| Sonnet 5 | $0.00039 | $0.01499 |
| Haiku 4.5 | $0.00019 | $0.00750 |
Grade A, and why
israeli-shelter-guide 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Israeli Shelter Guide
Guidance on finding, preparing and using shelters in Israel during rocket and missile alerts. It is based on publicly available Pikud Ha'Oref (Home Front Command) guidance as of August 2026. All life-safety numbers below should be cross-checked against the live Pikud Ha'Oref site or the 104 hotline before acting on them in a real emergency.
Description
Helps users:
- Identify which type of protected space they have (mamad, mamak, maman, miklat) and what to do in buildings that have none.
- Look up their region's time-to-shelter (immediate / 15 / 30 / 45 / 60 / 90 seconds).
- Understand the multi-stage early warning system Pikud Ha'Oref publishes for missile fire (preliminary advisory, then alert, then release message), including the separate advisory for fire from Lebanon.
- Prepare an emergency kit (ערכת חירום) according to Pikud Ha'Oref recommendations.
- Apply the correct protocol when caught in a vehicle, outdoors, or in a building without a mamad.
- Navigate the process for inspecting or building a private mamad with a licensed engineer.
Shelter Types
Israel has four types of protected spaces, each designated by a Hebrew acronym:
| Type | Hebrew | Full Name | Location | Typical Use |
|---|---|---|---|---|
| Mamad (ממ"ד) | מרחב מוגן דירתי | Apartment Protected Space | Inside individual apartments | Most common in buildings built after 1992 |
| Mamak (ממ"ק) | מרחב מוגן קומתי | Floor Protected Space | Shared space on each floor | Older buildings retrofitted with floor-level shelters |
| Maman (ממ"מ) | מרחב מוגן מוסדי | Institutional Protected Space | Schools, offices, public institutions | Workplaces and educational facilities |
| Miklat (מקלט) | מקלט ציבורי | Public Shelter | Underground or standalone structures | Parks, community centers, public spaces |
Since 1992, Israeli building code requires all new residential construction to include a mamad. Buildings constructed before 1992 may lack a mamad entirely.
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.
- CHANGELOG.md 4.6 KB
- evidence.json 48 KB
- metadata.json 2.2 KB
- optimization-log.json 3.1 KB
- references/alert-response-guide.md 7.7 KB
- references/shelter-preparation-checklist.md 1.7 KB
- references/shelter-types-comparison.md 6.8 KB
- scripts/protection_times.json 25 KB
- scripts/shelter_finder.py 7.5 KB runs code
- SKILL_HE.md 40 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.
- 12d ago First seen · 354 lines · 195 tokens per session scan A 1e0500ec2189
israeli-shelter-guide is a skill published in the GitHub repository skills-il/security-compliance (10 stars, last pushed 10d ago), licensed MIT. It adds 195 tokens to every session and 7,496 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…