fitness-and-nutrition

fitness-and-nutrition is a skill for Claude Code, Codex from androoAGI/starnet. It costs 44 tokens per session (1,326 once invoked), scanned A, original, MIT.

A general-information planner for weekly exercise and eating around one stated goal. It uses your available time, equipment, food preferences, and logged results, but is not medical advice.

In plain words
What is it for?
Use it to plan training and meals, estimate energy needs with shown calculations, record sessions and body weight, and revise the plan from the log.
Why use it?
It turns a broad fitness goal into a plan that fits your real circumstances and can be adjusted from your records. It also screens for situations where a doctor or other health professional should be involved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan training and meals, estimate energy needs with shown calculations, record sessions and body weight, and revise the plan from the log.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/androoagi/starnet/fitness-and-nutrition
About the project

StarNet is a local-first desktop harness for creating AI agents and arranging them in a pixel-art space station whose layout represents their capabilities, permissions, and workflow. It lets people run real model calls and tools through multiple bounded agents, using their own provider keys or accounts and optionally messaging the station through chat services. The catalogue entries are skills that extend or support work performed by StarNet agents.

androoAGI/starnet · 1,468 stars · on GitHub

Install

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.

Any agent
npx skills add androoAGI/starnet --skill fitness-and-nutrition
Clone the repo
git clone --depth 1 https://github.com/androoAGI/starnet

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for fitness-and-nutrition

README.md
[![agentmods](https://agentmods.dev/badge/skills/androoagi/starnet/fitness-and-nutrition/github.svg)](https://agentmods.dev/skills/androoagi/starnet/fitness-and-nutrition)
Your own site
<a href="https://agentmods.dev/skills/androoagi/starnet/fitness-and-nutrition"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/fitness-and-nutrition/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.

agentmods 80×15 button for fitness-and-nutrition

Your own site · 80×15
<a href="https://agentmods.dev/skills/androoagi/starnet/fitness-and-nutrition"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/fitness-and-nutrition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01326
Opus 5.5 $0.00018 $0.00530
Sonnet 5.5 $0.00009 $0.00265
Haiku 4.5 $0.00004 $0.00133

Measured 12d ago against content hash fa9902e69691, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fitness-and-nutrition 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.

skills-catalog/skills/fitness-and-nutrition/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan training and eating for one stated goal, then let the log steer it. The bar: a plan the Commander can follow this week with the time and equipment they really have, numbers whose arithmetic is shown, and no advice that belongs to a doctor.

Method

  1. Screen before you plan. Ask plainly: any pain or injury, recent surgery, a diagnosed condition (heart, blood pressure, diabetes, other), medication that affects exercise or appetite, pregnancy or a recent birth, a history of disordered eating, or under 18? For any yes, stop the part it touches and say which professional to see (doctor, physiotherapist, registered dietitian). Plan only inside what that professional has cleared.
  2. Collect the basics. One main goal (lose fat, gain muscle, get stronger, finish an event, general health) and a date if there is one. Training history. Days per week and minutes per session. Equipment. Movements and foods they like, dislike or cannot have; allergies; budget and cooking time. Age, height, weight and sex, only for the energy formula. Sleep and how active the working day is. Ask; do not assume.
  3. Estimate energy with a named formula and show the sums. Use Mifflin-St Jeor in code.run and print each line: resting energy = 10 × kg + 6.25 × cm − 5 × age, then + 5 for men or − 161 for women. Daily maintenance = resting energy × an activity factor: 1.2 mostly sitting, 1.375 light activity, 1.55 moderate, 1.725 very active. Say it is an estimate that can miss by ten percent or more; the log corrects it.
  4. Set a modest target. Fat loss: 10 to 20 percent under maintenance, aiming at roughly half a percent of body weight a week. Muscle gain: 5 to 10 percent over. Otherwise maintenance. Protein: people who train commonly use 1.2 to 2.0 g per kg of body weight a day; pick a figure their normal food can reach. Build the day from meals they already eat, with vegetables, fibre and water, and offer portions instead of numbers if they prefer.
  5. Build the week. Fit the days they have. Each session: a warm-up, four to six exercises, sets × reps, how hard (stop one to three reps before failure), rest, and total minutes. Across the week cover push, pull, squat, hinge and trunk. A beginner starts with two or three full-body days. Work toward the World Health Organization baseline of 150 minutes of moderate activity a week. Keep at least one full rest day, and give a swap for every exercise that needs equipment or bothers a joint.
  6. Write the overload rule into the plan. When every set reaches the top of its rep range with good form at the target effort, add the smallest load step next time; otherwise repeat the session. Change one thing at a time, raise weekly volume by about ten percent at most, and plan a lighter week every four to eight weeks.
  7. Save the plan and start the log. fs.write the plan to fitness/plan.md. Log with fs.append: fitness/log.csv (date, session, exercise, sets, reps, load, effort 1-10, notes) and fitness/weight.csv (date, weight). Read each entry back after writing.
  8. Adjust from the log, never from a guess. At least two weeks apart: compute weekly average weight and each lift's trend in code.run. Move calories in steps of 100 to 200 only when two weeks agree. Change a lift's plan after it stalls three sessions running. Poor sleep, soreness and falling numbers together mean less work, not more. No log, no change: ask for the data.

Read the full file on GitHub · 39 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 12d ago First seen · 39 lines · 44 tokens per session scan A fa9902e69691

Subscribe to this mod's changes

fitness-and-nutrition is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 1,326 once invoked, about $0.0002 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 2026-10-04.

Related

Other skills, from other repositories

orbit-general

Open Orbit briefing skill — selected by the Orbit pipeline when the user has two or more connectors connected. Pulls the past 24 hours of activity from every authenticated connector (GitHub, Linear, Notion, Slack, 飞书, Calendar, Gmail, Drive, Sentry, Vercel, …) and renders a single adaptive bento-grid dashboard at the…

nexu-io/open-design · 162 tokens

orbit-gmail

Open Orbit briefing skill — selected by the Orbit pipeline when Gmail is the user's only connected connector, or when the user explicitly scopes their daily digest to Gmail. Pulls the past 24 hours of inbox activity (replies awaited, mentions, cc, auto- categorized bulk) from the user's authenticated Gmail connection…

nexu-io/open-design · 115 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

discovery-question-form

Structured clarification form for unresolved material requirements.

nexu-io/open-design · 13 tokens

cron

Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/update/pause/resume/delete/run, and always pass --agent-id explicitly.

agentscope-ai/QwenPaw · 39 tokens

cron

A procedure for creating and managing tasks that run automatically at a future time or repeat on a schedule. It uses QwenPaw's scheduling commands and requires an agent identifier.

agentscope-ai/QwenPaw · 49 tokens