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.
npx agentmods add agents/gtapps/claude-code-hermit/strava-data-crunchergit clone --depth 1 https://github.com/gtapps/claude-code-hermitWrote 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.
[](https://agentmods.dev/agents/gtapps/claude-code-hermit/strava-data-cruncher)<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>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.
| Model | Per session | Once 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 |
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.
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-zonesonce 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
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.
- 3d ago First seen · 50 lines · 57 tokens per session scan A b424a573a17f
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.