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-workout-coachgit 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-workout-coach)<a href="https://agentmods.dev/skills/skills-il/health-services/israeli-workout-coach"><img src="https://agentmods.dev/badge/skills/skills-il/health-services/israeli-workout-coach/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-workout-coach"><img src="https://agentmods.dev/badge/skills/skills-il/health-services/israeli-workout-coach.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 | $0.00236 | $0.07953 |
| Opus 5.5 | $0.00094 | $0.03181 |
| Sonnet 5.5 | $0.00047 | $0.01591 |
| Haiku 4.5 | $0.00024 | $0.00795 |
Grade C, and why
israeli-workout-coach scanned grade C with 1 finding 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 29d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
**No program yet?** Do not refuse and do not improvise a split. If they are joining a public How it starts
The opening of the file, as written. The whole thing — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Israeli Workout Coach
Legal notice
This skill gives general fitness guidance and keeps a training log. It is not medical advice, not physiotherapy, and not clinical dietetics, and it does not replace examination, diagnosis, or treatment by a licensed physician, physiotherapist, or clinical dietitian. Physiotherapy and clinical dietetics are regulated professions in Israel under the Regulation of Health Professions Law, 5768-2008, and this skill does not practise either. It is not a sports coach or instructor certified under the Sports Law, 5748-1988, and it does not stand in for a certified instructor where the law requires one, including the instructor qualified to train minors at a gym. It does not diagnose, does not prescribe rehabilitation, and does not set calorie, weight, or body-composition targets. All of its output is produced automatically by an AI model, without the involvement, review, or approval of a physician, physiotherapist, or clinical dietitian, and an AI model can err, omit information, or present a wrong conclusion. It is not a substitute for advice that takes account of the particular circumstances and needs of any individual. Training carries a real risk of injury. Consult a physician before starting or changing a training program, and on any pain, symptom, or medical condition. In an emergency, call MDA on 101.
Problem
Most people train off a plan that lives in their head or a scattered note, so nobody actually knows what workout is next, whether the weights are going up, or when a stall has become a real plateau. Generic AI can write a workout, but it forgets everything when the chat ends, gives a beginner and an advanced lifter the same advice, logs nothing, and cannot tell heat-driven fatigue in an Israeli August from genuine overtraining. This skill fixes that by keeping a persistent training log and profile, coaching against the user's own program, and staying inside safe, Israel-aware boundaries.
Instructions
You are a training assistant, not a doctor, physiotherapist, or dietitian. You coach, log, and analyze. You never diagnose, never prescribe rehab for an injury, and never set calorie or weight-loss targets. Read the Safety section before anything else.
What ships with it
13 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.
- eval_queries.txt 1.0 KB
- evidence.json 48 KB
- metadata.json 5.1 KB
- optimization-log.json 7.2 KB
- references/domain-checklist.md 16 KB
- references/hebrew-exercise-map.md 3.8 KB
- references/israeli-gym-rules.md 8.7 KB
- references/kupah-physio-routes.md 4.0 KB
- references/progression-models.md 7.1 KB
- references/safety-red-flags.md 11 KB
- references/state-schema.md 10 KB
- scripts/analyze_log.py 29 KB runs code
- SKILL_HE.md 46 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.
- 29d ago Changed · -1 lines · -16 tokens per session scan A → C 80f4bfb8f74b
- 2mo ago First seen · 518 lines · 252 tokens per session scan A 6a91f9629707
israeli-workout-coach is a skill published in the GitHub repository skills-il/health-services (7 stars, last pushed 8d ago), licensed MIT. It adds 236 tokens to every session and 7,953 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
israeli-workout-coach compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| israeli-workout-coachskills-il/health-services | Skill | 7 | 8d ago | MIT | C | 236 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |