agentmods.dev

activity-deep-dive

activity-deep-dive is a skill for Claude Code, Codex from gtapps/claude-code-hermit. It costs 63 tokens per session (3,193 once invoked), scanned C, original, MIT.

A per-workout coaching analysis from Strava, a service that records activities such as runs and rides. It distinguishes interval and steady workouts as well as road and trail terrain, then summarizes relevant training measures and recovery.

In plain words
What is it for?
Use it after a workout or with a specific activity ID to create a coaching note, review the latest activity, examine training zones, and estimate recovery.
Why use it?
It avoids treating every workout the same, so the review can focus on interval recovery, steady-work efficiency, or the different demands of trail terrain.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-code-fitness-hermit plugin — 5 skills, 1 agent shipped together

not rated 73 today C scan 63 tokens original MIT
View the source file gtapps/claude-code-hermit
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.

agentmods
npx agentmods add skills/gtapps/claude-code-hermit/activity-deep-dive
Any agent
npx skills add gtapps/claude-code-hermit --skill activity-deep-dive
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code, Codex.

Or install claude-code-fitness-hermit, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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 activity-deep-dive

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/activity-deep-dive.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/activity-deep-dive)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/activity-deep-dive"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/activity-deep-dive.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00063 $0.03193
Opus 5 $0.00032 $0.01597
Sonnet 5 $0.00013 $0.00639
Haiku 4.5 $0.00006 $0.00319

Measured 4d ago against content hash bfd6ef3e8e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

activity-deep-dive scanned grade C 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 4d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

old_string: "<!-- Anything unexpected found during work. Proposal-worthy items get their own file. -->"
plugins/claude-code-fitness-hermit/skills/activity-deep-dive/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Activity Deep-Dive

Produces a standardised per-activity coaching note. All deterministic statistics (session-kind detection, terrain, zones, cadence, efficiency, cardiac drift, VAM/GAP, recovery estimate) are computed by scripts/fitness-lab.ts — this skill runs it once, interprets the JSON, and writes the coaching narrative. Raw Strava streams never enter context: the script fetches and reduces them; the skill only sees the reduced metrics.

Interval sessions get work-interval HR progression and between-bout recovery quality; steady sessions get pace/HR efficiency and cardiac drift. Trail sessions swap pace/HR efficiency for VAM and a grade-adjusted-pace estimate, reframe cardiac drift against the altitude profile, and extend the recovery window for descent load. Both get zone breakdown, recovery estimate, and a coaching note. Saves a compiled artifact and returns a compact summary.

Usage

/claude-code-fitness-hermit:activity-deep-dive <activity-id>
/claude-code-fitness-hermit:activity-deep-dive latest

Steps

  1. Resolve subjective RPE. Read .claude-code-hermit/state/activity-notes.json. If it exists and has an entry for the resolved activity ID (or, for latest, hold the check until step 2 returns the ID), keep rpe and notes for the output template and artifact frontmatter. The script does NOT read RPE — this is the skill's job.

  2. Run the analysis script. Issue a single Bash call:

    bun ${CLAUDE_PLUGIN_ROOT}/scripts/fitness-lab.ts analyze <activity-id|latest>

    The script fetches details, laps, streams, athlete zones, and the recent summary activities (for the efficiency baseline), then emits one JSON object. Handle the error contract:

    • {"error":"strava_auth","message":"…"} (exit 1) → the token is missing or expired. Relay the message verbatim to the operator and stop. Do not compute anything.
    • {"error":"fetch","message":"…"} (exit 1) → report the message and stop.
    • Success (exit 0) → parse the JSON and continue.

Read the full file on GitHub · 152 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. 4d ago First seen · 152 lines · 63 tokens per session scan C bfd6ef3e8e89

Subscribe to this mod's changes

activity-deep-dive is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 3,193 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metricsaiai-agentanthropicclaudeclaude-codeclaude-code-plugin
Related

Other skills, from other repositories

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

codex-test-gen

Generate unit tests for specified functions using Codex MCP.

sd0xdev/sd0x-harness · 15 tokens

brand-docx

Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…

ferdinandobons/brand-docs · 144 tokens

extract-resume

Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.

suxrobGM/jobpilot · 32 tokens