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-nutrition-plannergit 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-nutrition-planner)<a href="https://agentmods.dev/skills/skills-il/health-services/israeli-nutrition-planner"><img src="https://agentmods.dev/badge/skills/skills-il/health-services/israeli-nutrition-planner/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-nutrition-planner"><img src="https://agentmods.dev/badge/skills/skills-il/health-services/israeli-nutrition-planner.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 | $0.00240 | $0.07646 |
| Opus 5 | $0.00120 | $0.03823 |
| Sonnet 5 | $0.00048 | $0.01529 |
| Haiku 4.5 | $0.00024 | $0.00765 |
Grade A, and why
israeli-nutrition-planner 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Israeli Nutrition Planner
Problem
Planning balanced meals in Israel means navigating the Ministry of Health's Nutritional Rainbow, reading the front-of-package red and green labels on every product, and working within kosher, halal, and holiday constraints that shape both what goes in a meal and when it can be eaten. Most people either ignore the labels or cannot translate the rainbow's frequency-based recommendations into an actual weekly menu, and default to convenience foods carrying red labels for sugar, sodium, or saturated fat.
Instructions
Step 1: Assess Needs and Clear the Medical Gates
Ask the user about their dietary context before planning:
| Question | Why it matters |
|---|---|
| How many people are you planning for? | Portion scaling |
| Any food allergies or intolerances? | Exclusion list |
| Do you keep kosher or halal? At what level? | Meat-dairy separation, permitted foods |
| Budget preference (economy, moderate, flexible)? | Ingredient selection |
| Any health conditions? Ask by name: diabetes, kidney disease, high blood pressure, celiac, pregnancy or breastfeeding, a past or present eating disorder | Blocking gate, see below |
| Any regular medication? | Food and drug interactions, see Step 8.5 |
| Cooking skill level? | Recipe complexity |
This is a blocking gate, not a disclaimer. If any of the following is present, you constrain or withhold the plan. Do not generate a full menu and then attach a warning at the end.
| Condition | What you do |
|---|---|
| Diabetes (any type, including gestational) | Do not set carbohydrate targets or exchange counts. Give the rainbow framework only, and route to the kupat cholim dietitian under the National Diabetes Program (Step 8). |
| Kidney disease | Withhold the meal plan. Renal diets restrict protein, potassium, phosphorus and sodium in combinations only a renal dietitian can set, and this skill's defaults (legumes at every meal, dark leafy greens, tahini, salt substitutes) are actively harmful here. Route to the nephrologist and renal dietitian. |
| Pregnancy or breastfeeding | You may plan, but you must apply Step 8.7 (pregnancy food safety) to every menu item, and never set a weight target. |
| Celiac | Plan with the Step 8.6 gluten exclusions, and route to the kupat cholim dietitian, covered for celiac with a doctor referral. |
| Eating disorder, past or present | Stop. Do not plan. Go to Step 1.5. |
| Chronic medication | Apply Step 8.5 before recommending any supplement or any food in quantity. |
What ships with it
7 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 · 318 lines · 240 tokens per session scan A d9ea7aa345bd
israeli-nutrition-planner is a skill published in the GitHub repository skills-il/health-services (5 stars, last pushed 10d ago), licensed MIT. It adds 240 tokens to every session and 7,646 once invoked, about $0.0012 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…