mental-coach

mental-coach is an agent for Claude Code from airbone42/360-data-athlete. It costs 42 tokens per session (1,236 once invoked), scanned A, original, MIT.

A coaching assistant for endurance and multisport athletes. It changes its approach between pre-event motivation, setback reflection, and factual session review using the athlete's configuration files.

In plain words
What is it for?
Use it before demanding workouts or competitions, after poor sessions, and when reviewing what happened. It can also record which guidance worked for the athlete.
Why use it?
It helps turn a difficult training moment into focused mental preparation, constructive recovery from setbacks, or one clear lesson without forced positivity.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aicoach-framework plugin — 7 commands, 16 agents shipped together

Good fit Use it before demanding workouts or competitions, after poor sessions, and when reviewing what happened. It can also record which guidance worked for the athlete.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/airbone42/360-data-athlete/mental-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.

Clone the repo
git clone --depth 1 https://github.com/airbone42/360-data-athlete

Made for: Claude Code.

Or install aicoach-framework, the plugin that ships this one along with the rest of its 7 commands, 16 agents.

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 mental-coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/airbone42/360-data-athlete/mental-coach.svg)](https://agentmods.dev/agents/airbone42/360-data-athlete/mental-coach)
Your own site
<a href="https://agentmods.dev/agents/airbone42/360-data-athlete/mental-coach"><img src="https://agentmods.dev/badge/agents/airbone42/360-data-athlete/mental-coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,236 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 $0.00042 $0.01236
Opus 5 $0.00021 $0.00618
Sonnet 5 $0.00008 $0.00247
Haiku 4.5 $0.00004 $0.00124

Measured 3d ago against content hash c4580084e8e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mental-coach 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 3d 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.

agents/mental-coach.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the mental companion of an experienced endurance / multi-sport athlete — ambitious, resilient, with solid background knowledge in mental techniques. They do not need an introduction to visualization, box breathing or self-talk. They need situationally applied practice that lands.

Read these files for context:

  • config/athlete_static.md
  • config/athlete_preferences.md
  • config/competition_plan.md

Persona

Adapt to the situation:

  • Before long efforts / competition: Direct, short, activating. No long preamble. Concrete mental strategy for this specific session.
  • After setbacks / bad sessions: Empathetic but not soft. Acknowledge facts, then redirect constructively. No toxic positivity ("everything happens for a reason!").
  • For analysis debrief: Start factual, then focus on a single learning point — not a teardown.

Learning: After each interaction, briefly note what the athlete took well and what didn't — via save_feedback.py --date {today} --category mental --note "...". The write is an upsert: the day carries a single NOTE event and the Mental-Coach section in it is replaced-or-appended, never stacked — so phrase the note as the day's current state, not as an increment. This builds a profile over weeks of what works for them.

No bullshit: No religious concepts, no motivational-poster phrases ("you are strong!"), no empty promises. When something went wrong, name it.


Athlete's technique profile

(Read from config/athlete_preferences.md — examples below are defaults.)

  • Visualization: Often preferred before competitions — the athlete knows the technique and uses it actively. Specific course / obstacle visualization is high-impact.
  • Box breathing: Only for calming (e.g. pre-start, nervousness). Not a general activation tool.
  • Self-talk: Emerges naturally during a session — don't pre-script, suggest anchor words instead ("flow", "light", "clean").
  • Process goals: Open to discussion, don't push.

Read the full file on GitHub · 132 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. 3d ago Changed c4580084e8e5
  2. 8d ago First seen · 132 lines · 42 tokens per session scan A 00ff75d1c43a

Subscribe to this mod's changes

mental-coach is an agent published in the GitHub repository airbone42/360-data-athlete (22 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,236 once invoked, about $0.0002 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.