delx-wellness-training

delx-wellness-training is a skill for Claude Code, Codex from davidmosiah/delx-wellness-hermes. It costs 23 tokens per session (390 once invoked), scanned A, original, MIT.

A training recommendation skill that uses recovery, sleep, recent activity, soreness, and exercise data to suggest how hard to train today.

In plain words
What is it for?
Use it to decide between hard, moderate, technique, mobility, or rest sessions, and to outline a workout or recovery routine based on available wellness data.
Why use it?
It helps avoid choosing a demanding workout when the body's recovery signals suggest lighter activity or rest.

Skill for Claude CodeCodex

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

Good fit Use it to decide between hard, moderate, technique, mobility, or rest sessions, and to outline a workout or recovery routine based on available wellness data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davidmosiah/delx-wellness-hermes/delx-wellness-training
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 davidmosiah/delx-wellness-hermes --skill delx-wellness-training
Clone the repo
git clone --depth 1 https://github.com/davidmosiah/delx-wellness-hermes

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 delx-wellness-training

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidmosiah/delx-wellness-hermes/delx-wellness-training/github.svg)](https://agentmods.dev/skills/davidmosiah/delx-wellness-hermes/delx-wellness-training)
Your own site
<a href="https://agentmods.dev/skills/davidmosiah/delx-wellness-hermes/delx-wellness-training"><img src="https://agentmods.dev/badge/skills/davidmosiah/delx-wellness-hermes/delx-wellness-training/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 delx-wellness-training

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidmosiah/delx-wellness-hermes/delx-wellness-training"><img src="https://agentmods.dev/badge/skills/davidmosiah/delx-wellness-hermes/delx-wellness-training.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 390 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 $0.00023 $0.00390
Opus 5 $0.00012 $0.00195
Sonnet 5 $0.00005 $0.00078
Haiku 4.5 $0.00002 $0.00039

Measured 12d ago against content hash 33f270823f74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

delx-wellness-training 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/delx-wellness-training/SKILL.md · 47 lines

What it actually says

Delx Wellness Training

When to Use

Use this when the user asks if they should train hard, rest, play tennis, lift, run, deload, or build a workout.

Procedure

  1. Pull recovery context with wellness_today, recommend_today_training, or provider tools.
  2. Consider recent strain, sleep quality, HRV/readiness, activity load, soreness, and user objective.
  3. If a workout is requested, call build_workout_from_recovery or Exercise Catalog tools when available.
  4. Choose one of: hard session, moderate session, technique session, mobility/recovery, rest.
  5. Explain why in practical language.

Output

  • Recommendation.
  • Intensity target.
  • Workout outline or recovery protocol.
  • Evidence from tools.
  • Confidence and data gaps.

Safety

  • Do not tell the user to train through injury, chest pain, fainting, fever, or concerning symptoms.
  • Ask a clarifying question if symptoms or injury risk are present.
  • Keep advice non-medical.

Verification

The recommendation should be traceable to live or recent wellness data, or clearly marked as low-confidence.

Dense time-series

Prefer garmin_activity_series, strava_activity_series, fitbit_heart_series, polar_heart_series (agent-safe-series/v1) over raw stream dumps.

Never dump raw continuous streams, full-resolution sample arrays, or unscoped export payloads unless the user gave explicit_user_intent for that dense dump. Default path is always the capped series tools.

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 · 47 lines · 23 tokens per session scan A 33f270823f74

Subscribe to this mod's changes

delx-wellness-training is a skill published in the GitHub repository davidmosiah/delx-wellness-hermes (19 stars, last pushed 17d ago), licensed MIT. It adds 23 tokens to every session and 390 once invoked, about $0.0001 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 2026-08-30.