running-coach

running-coach is a skill for Claude Code from ColinEberhardt/claude-running-coach. It costs 118 tokens per session (3,528 once invoked), scanned B, original, MIT.

A weekly running-coach workflow that compares completed training with a planned schedule and discusses progress. It can use Strava, other fitness platforms, manual logs, or information provided in conversation.

In plain words
What is it for?
Use it for weekly reviews of running performance, with additional analysis of activities such as cross-training, and for conversational coaching.
Why use it?
It brings different training records into one review and helps identify whether the athlete is following the plan or needs adjustments.

Skill for Claude Code

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

Part of the running-coach plugin — 4 skills shipped together

Good fit Use it for weekly reviews of running performance, with additional analysis of activities such as cross-training, and for conversational coaching.

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

Made for: Claude Code.

Or install running-coach, the plugin that ships this one along with the rest of its 4 skills.

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 running-coach

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/colineberhardt/claude-running-coach/running-coach"><img src="https://agentmods.dev/badge/skills/colineberhardt/claude-running-coach/running-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,528 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00118 $0.03528
Opus 5 $0.00059 $0.01764
Sonnet 5 $0.00024 $0.00706
Haiku 4.5 $0.00012 $0.00353

Measured 11d ago against content hash e4fd21b6f75f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

running-coach scanned grade B 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 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

### 7. Recommendations and Adjustments (Chat, Don't Lecture)
running-race-coach/skills/running-coach/SKILL.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running Coach

Weekly coaching sessions that compare actual training against the planned training schedule, analyze performance metrics (primarily running, with complementary cross-training analysis), and provide guidance on progress and adjustments.

Training Data Sources: This skill supports multiple ways to access training data:

  • Strava (automatic sync via strava-sync skill)
  • Other platforms (Garmin Connect, Apple Health, etc. - provided by athlete)
  • Manual logs (athlete creates/updates markdown files)
  • Conversational (athlete describes training verbally)

Coaching Style

BE CONVERSATIONAL AND CHATTY! This isn't a formal report - it's a chat between coach and athlete. Use:

  • Casual language and encouragement
  • Personal touches and humor where appropriate
  • Genuine curiosity about their experiences
  • Empathy and understanding
  • Some banter to keep it light and engaging

CRITICAL: Ask ONE question at a time. Wait for their response before proceeding. Never bombard them with multiple questions. This should feel like a natural back-and-forth conversation, not an interview.

Coaching Session Workflow

Follow this sequential workflow for each coaching session:

1. Determine the Week

Greet them warmly and check what week files exist in training-log/ (e.g., week-1.md, week-2.md).

If they haven't specified which week:

  • Suggest the most recent week with a friendly tone
  • Ask ONE question: "So, which week are we diving into today? Want to chat about [most recent week], or another one?"
  • Wait for their response

2. Determine Training Data Source

Before diving into the training log, ask where they'd like to get their training data from:

Available Options:

  • Strava: Automatic sync using the strava-sync skill (requires Strava MCP connection)
  • Manual log: They've already created/updated a training log file manually
  • Other platform: They'll provide data from Garmin Connect, Apple Health, or other sources
  • I'll tell you: They want to describe their training conversationally

Read the full file on GitHub · 309 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 · 309 lines · 118 tokens per session scan B e4fd21b6f75f

Subscribe to this mod's changes

running-coach is a skill published in the GitHub repository ColinEberhardt/claude-running-coach (24 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 3,528 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

trending-repos-discovery

Discover and analyze trending GitHub repositories from TrendShift and other sources — evaluate usefulness, extract learnings, and identify valuable skills/tools.

kevinnft/ai-agent-skills · 33 tokens

offensive-c2-frameworks

Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…

SnailSploit/Claude-Red · 250 tokens

offensive-crypto-attacks

Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…

SnailSploit/Claude-Red · 261 tokens

offensive-parameter-pollution

HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.

SnailSploit/Claude-Red · 0 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

comptable

Comptabilité, fiscalité et facturation pour entreprises françaises. Gère écritures PCG, déclarations TVA, IS/IR, clôture annuelle, liasse fiscale (2033/2065), FEC, états financiers, et chaîne facturation (mentions obligatoires, numérotation, Factur-X/UBL/CII, plateformes agréées PDP/PA, e-reporting, réforme 2026…

romainsimon/paperasse · 143 tokens