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/health-services --skill israeli-food-allergy-navigatorgit clone --depth 1 https://github.com/skills-il/health-servicesWrote 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/health-services/israeli-food-allergy-navigator)<a href="https://agentmods.dev/skills/skills-il/health-services/israeli-food-allergy-navigator"><img src="https://agentmods.dev/badge/skills/skills-il/health-services/israeli-food-allergy-navigator/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/health-services/israeli-food-allergy-navigator"><img src="https://agentmods.dev/badge/skills/skills-il/health-services/israeli-food-allergy-navigator.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 | $0.00224 | $0.07261 |
| Opus 5.5 | $0.00090 | $0.02904 |
| Sonnet 5.5 | $0.00045 | $0.01452 |
| Haiku 4.5 | $0.00022 | $0.00726 |
Grade A, and why
israeli-food-allergy-navigator 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 24d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Israeli Food Allergy Navigator
Legal notice
This is a free information tool operated by an artificial-intelligence model. It explains the bureaucratic entitlements of children and adults with food allergy in Israel, quotes the Ministry of Education standing instruction and the Bituach Leumi criterion, and drafts request letters to educational institutions. All of its output is produced automatically, without the involvement, review or approval of a physician, an allergy specialist, or any licensed medical professional.
The tool's output is not a medical diagnosis, not a medical opinion, not a prescription and not treatment. It is bureaucratic information about entitlements and documents only. Where the tool helps lay out an allergy action-plan card, that card is a transcription aid for the plan the treating physician wrote, it is not itself a medical instruction, and it must be reviewed and signed by the treating physician before use. The tool does not examine the child, does not interpret allergy test results, does not determine which allergens are involved, does not assess the degree of risk, does not decide whether an adrenaline auto-injector is required, and does not determine any dose. Those acts require the tools and experience of a physician specialising in allergy. An artificial-intelligence model may err, omit data, or present a wrong conclusion.
Do not rely on this tool for any medical decision, and do not use it to decide whether a reaction requires treatment. Where an anaphylactic reaction is suspected, inject adrenaline per the treating physician's instructions and call 101 immediately. Any text the tool drafts is an automatic draft for personal organisation only. It explains appeal routes and deadlines published by Bituach Leumi but does not draft or file an appeal, and is prepared without the involvement of a lawyer. This tool is not a substitute for advice that takes account of the particular data and needs of each person, and before any medical decision, the filing of a claim or an appeal you should consult the treating physician and the competent authority. Any use of the output is the sole responsibility of the user.
What ships with it
11 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 62 KB
- metadata.json 4.1 KB
- optimization-log.json 7.3 KB
- references/allergen-labelling.md 2.8 KB
- references/bituach-leumi-allergy-claim.md 7.8 KB
- references/document-templates.md 12 KB
- references/domain-checklist.md 16 KB
- references/injectors-and-oit.md 3.7 KB
- references/maon-ages-0-3.md 5.5 KB
- references/moe-standing-instruction-0042.md 15 KB
- SKILL_HE.md 42 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.
- 24d ago Changed · -2 lines 7ae061ceb858
- 2mo ago First seen · 271 lines · 224 tokens per session scan A 4dbfa6d0fd9e
israeli-food-allergy-navigator is a skill published in the GitHub repository skills-il/health-services (7 stars, last pushed 8d ago), licensed MIT. It adds 224 tokens to every session and 7,261 once invoked, about $0.0009 per session on Opus 5.5. 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.
israeli-food-allergy-navigator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| israeli-food-allergy-navigatorskills-il/health-services | Skill | 7 | 8d ago | MIT | A | 224 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |