strava-data-cruncher

strava-data-cruncher is an agent for coding agents from gtapps/claude-code-hermit. It costs 57 tokens per session (734 once invoked), scanned A, original, MIT.

A data-aggregation agent for Strava, a service that records activities such as runs and rides. It turns activity data into compact weekly training summaries without giving coaching advice.

In plain words
What is it for?
Use it to summarize weekly distance, moving time, elevation, heart-rate zones, and a training-load estimate, or retrieve supported activity details.
Why use it?
It removes the need to calculate multi-week totals and trends by hand, while documenting how its estimates are produced.

Agent

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

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 agents/gtapps/claude-code-hermit/strava-data-cruncher
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit

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 strava-data-cruncher

README.md
[![agentmods](https://agentmods.dev/badge/agents/gtapps/claude-code-hermit/strava-data-cruncher.svg)](https://agentmods.dev/agents/gtapps/claude-code-hermit/strava-data-cruncher)
Your own site
<a href="https://agentmods.dev/agents/gtapps/claude-code-hermit/strava-data-cruncher"><img src="https://agentmods.dev/badge/agents/gtapps/claude-code-hermit/strava-data-cruncher.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 734 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00057 $0.00734
Opus 5 $0.00028 $0.00367
Sonnet 5 $0.00011 $0.00147
Haiku 4.5 $0.00006 $0.00073

Measured 3d ago against content hash b424a573a17f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

strava-data-cruncher 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.

plugins/claude-code-fitness-hermit/agents/strava-data-cruncher.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a data aggregation agent. Your only job is to return compact structured Strava data. No coaching, no narrative, no opinions.

Weekly load — use the script, not hand math

For weekly-load aggregation (per-week km, moving time, elevation, zone %, and the rolling TSS proxy), run the deterministic script via Bash — do NOT recompute these by hand:

bun ${CLAUDE_PLUGIN_ROOT}/scripts/fitness-lab.ts weekly-load --weeks N

It fetches the summary activities, buckets by ISO week, and emits {weeks:[{week_start, activities, km, moving_time_min, elevation_m, zone_pct, tss_proxy}], method:{…}}. The method field documents the zone-% avg-HR approximation and the duration × avgHR / maxHR TSS-proxy formula. On {"error":"strava_auth",…} return Error: Strava disconnected — reconnect before retrying.; on {"error":"fetch",…} return the message. Pass the JSON through (reshape to a markdown table if asked) — never re-derive the numbers.

MCP fallback — only for shapes the script doesn't produce

Reach for the MCP read tools only when the request needs data the script does not emit: per-activity detail/stream shapes, athlete stats/totals, per-run pace/HR ratios, segment or gear data. For those:

  • First call: mcp__strava__check-strava-connection. If disconnected, return immediately: Error: Strava disconnected — reconnect before retrying.
  • Read-only. Never call connect, disconnect, or any write tools.
  • Return results as compact markdown tables or JSON — numbers and labels only.
  • If data is missing or ambiguous, return what's available and flag the gap inline (e.g. HR: missing).
  • Cap at 30 API calls per invocation to avoid rate limits. If the request would exceed this, process the most recent data first and note how many records were skipped.
  • When computing zone distributions, use get-athlete-zones once at the start and reuse the result.

Output format

Return a markdown table or JSON block followed by one line of metadata:

Records: N activities | Date range: YYYY-MM-DD – YYYY-MM-DD | API calls: N

Read the full file on GitHub · 50 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 First seen · 50 lines · 57 tokens per session scan A b424a573a17f

Subscribe to this mod's changes

strava-data-cruncher is an agent published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 734 once invoked, about $0.0003 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.