fitness-coach

fitness-coach is a skill for Claude Code from philipyaz/cos. It costs 226 tokens per session (1,037 once invoked), scanned B, original, MIT.

A fitness request router that directs general questions to the right fitness tool. The available tools cover training plans, daily readiness, weekly reviews, sleep and performance analysis, health data, and athlete profiles.

In plain words
What is it for?
Use it for broad requests such as getting fit, training better, or finding out what the fitness add-on can do.
Why use it?
It helps when you know you need fitness support but have not worked out which specific task to ask for.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it for broad requests such as getting fit, training better, or finding out what the fitness add-on can do.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/philipyaz/cos/fitness-coach
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 philipyaz/cos --skill fitness-coach
Clone the repo
git clone --depth 1 https://github.com/philipyaz/cos

Made for: Claude Code.

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-coach

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

agentmods 80×15 button for fitness-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/philipyaz/cos/fitness-coach"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 226 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,037 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00226 $0.01037
Opus 5 $0.00113 $0.00518
Sonnet 5 $0.00045 $0.00207
Haiku 4.5 $0.00023 $0.00104

Measured 11d ago against content hash 4b7a91dc3049, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

fitness-coach scanned grade B with 2 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 11d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

lands in the history feed. Never tell the user to "click Generate" for a plan/review/brief.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **The `fitness` MCP** is the only path to health DATA (never `bash`/`curl`) — 18 thin tools
board/.claude/skills/fitness-coach/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fitness (the add-on index / router)

This is the overview for the Fitness add-on. It exists to route a vague request to the right focused skill — it no longer carries the per-feature procedures (those moved into the six skills below). When the user names a job, defer to that skill. When the ask is generic ("help me with my fitness", "what can this do"), give the short map below and ask which they want.

The six focused skills — pick one

  • fitness-training-plan — generate a weekly plan (one session per day, with rotation / variety and progression, intensity adapted to recovery).
  • fitness-pre-workout-brieftoday's readiness / "should I train today?" training brief (go / go easy / rest).
  • fitness-weekly-review — review the past week (training load, sleep, form, advice for next week).
  • fitness-correlationssleep vs performance analysis (board-computed stats you interpret).
  • fitness-health-datalog / query Apple Watch data (push canonical workout/sleep/HRV/resting-HR/steps/VO2max entries, read summaries + trends) and push a health report to the vault.
  • fitness-athlete-profile — set the training focus (sport/event) / weekly availability / equipment / sports (the training-focus half everything else personalises against).
  • body-profile (the body add-on) — set/read the body goal (free text), identity (sex / DOB / height), training status (novice|intermediate|advanced), and weigh-ins + composition. The body half moved off the athlete profile in v14: the coaching skills READ it via the body MCP (get_body_profile / get_body_status / get_body_objective); send the user here (or /body) to SET their goal / training status / weight.

Cross-cutting reminders (true for all of the above)

  • The board is a state machine; YOU are the intelligence. The board never calls an LLM — nothing is "generated on the board". The agent FETCHES inputs via the fitness MCP, GENERATES the artifact in its own reasoning, and PERSISTS it via a save_* tool so it lands in the history feed. Never tell the user to "click Generate" for a plan/review/brief.
  • NOT MEDICAL ADVICE. Plans, reviews, briefs, and correlations are informational fitness guidance — say so, and defer injuries / medical conditions / abnormal symptoms / pregnancy / an under-18 user to a physician, physiotherapist, or qualified coach.
  • The /fitness/* pages are history FEEDS over the persisted artifacts (latest-by-default, page-back) — /fitness (profile), /fitness/training-plan, /fitness/weekly-review, /fitness/pre-workout-brief, /fitness/correlations, and /fitness/health (the Apple Watch dashboard). The human glances; the agent does the work.
  • The fitness MCP is the only path to health DATA (never bash/curl) — 18 thin tools (reads + save_* writes); writes are add-on-gated and need the add-on ENABLED. The detailed tool list, the canonical taxonomy, and the setup live in /fitness-mcp-setup — point there rather than restating it here.

Read the full file on GitHub · 65 lines

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. 11d ago First seen · 65 lines · 226 tokens per session scan B 4b7a91dc3049

Subscribe to this mod's changes

fitness-coach is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 226 tokens to every session and 1,037 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 2 findings (subtle steering, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

wiki-lint

Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…

tboome33/obsidian-mcp-router · 119 tokens

opencode-plugin-idioms

Event hook payload shapes, session lifecycle timing, toast/TUI-route render boundaries, and child-session tagging conventions for OpenCode server (@opencode-ai/plugin) and TUI (@opencode-ai/plugin/tui) plugins, grounded in the vendored OpenCode source at references/opencode.

kagan-sh/kagan · 64 tokens

meta-sync-template

Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…

tboome33/obsidian-mcp-router · 159 tokens

save

File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…

tboome33/obsidian-mcp-router · 112 tokens

wiki-export

Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…

tboome33/obsidian-mcp-router · 129 tokens

wiki-boundary

Rank the "frontier" pages of a wiki — the crossroads many pages link to that stay thin inside — so you can decide where research would pay off most. Use when the user says "what should I write about next", "where are the gaps", "which pages need work", "find the thin hub pages", "boundary pages", "/wiki-boundary"…

tboome33/obsidian-mcp-router · 141 tokens