A post-run report that examines workout data from Intervals.icu. It reviews power, threshold-zone adherence, heart-rate changes between the first and second halves, and recovery information.

Use it after a run to inspect pace, power, heart rate, cadence, training load, equipment, and the details of work and recovery intervals.

A run's total distance and pace do not show whether the effort was controlled or became less efficient. This report turns recorded workout measurements into a session review.

How hadidwirsty/intervals-icu-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to hadidwirsty/intervals-icu-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hadidwirsty/intervals-icu-mcp/main/.agents/skills/lapor-lari/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/hadidwirsty/intervals-icu-mcp

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hadidwirsty/intervals-icu-mcp/lapor-lari/github.svg)](https://agentmods.dev/skills/hadidwirsty/intervals-icu-mcp/lapor-lari)

Your own site

<a href="https://agentmods.dev/skills/hadidwirsty/intervals-icu-mcp/lapor-lari"><img src="https://agentmods.dev/badge/skills/hadidwirsty/intervals-icu-mcp/lapor-lari/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hadidwirsty/intervals-icu-mcp/lapor-lari"><img src="https://agentmods.dev/badge/skills/hadidwirsty/intervals-icu-mcp/lapor-lari.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,870 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.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.02870
Opus 5.5	$0.00026	$0.01148
Sonnet 5.5	$0.00013	$0.00574
Haiku 4.5	$0.00007	$0.00287

Measured today against content hash 1e996adffe4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lapor-lari 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 today.

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/skills/lapor-lari/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/lapor-lari — Laporan Pasca-Sesi Lari Komprehensif

Skill ini digunakan 15–30 menit setelah atlet menyelesaikan sesi lari untuk membedah telemetri latihan secara menyeluruh. Menggabungkan evaluasi kontrol daya lari (running power), kepatuhan zona ambang laktat, efisiensi jantung paruh 1 vs paruh 2 (Aerobic Decoupling), serta evaluasi kualitatif atlet.

1. Alur Kerja Otomasi Data (MCP Tools)

Saat perintah /lapor-lari dijalankan:

Ambil Data Aktivitas Terakhir:
- Panggil get_activities untuk tanggal hari ini atau rentang 2 hari terakhir dari Intervals.icu.
- Panggil garmin_search_activities dengan activityType: "running" dan limit: 1 untuk mendapatkan activityId aktivitas lari riil di Garmin Connect.
Ambil Detail Telemetri & Beban Sesi:
- Panggil get_activity_details dengan activityId yang didapat.
- Ekstrak: durasi bergerak (moving time), jarak aktual (km), rerata kecepatan/pace, daya rata-rata (icu_average_watts), daya tertimbang (icu_weighted_avg_watts), rerata HR, Max HR, kadensi langkah, TSS/Load (icu_training_load), dan gear/sepatu yang dipakai.
Analisis Dekomposisi Repetisi (Jika Sesi Kualitas / Sub-T):
- Panggil get_activity_intervals untuk melihat rincian tiap repetisi kerja dan jeda istirahat (rest jog).
- Verifikasi apakah repetisi kerja berada dalam koridor daya 85–95% CP dan apakah jeda istirahat jalan santai dipatuhi: Card A (3–4m): 30–60s, Card B (5–7m): 60–90s, Card C (10–12m): 90–120s.
Analisis Efisiensi Aerobik & Cardiac Drift (Dual-Engine Decoupling Cross-Validation):
- Panggil MCP tool analyze_cardiac_drift dari Intervals.icu dengan activityId.
- Panggil garmin_get_activity_details dari Garmin Connect MCP dengan parameter includeDecoupling: true. Garmin MCP v0.2.0 secara native menghitung stream-based Aerobic Decoupling ($Pw:HR$ atau $Pace:HR$), mengevaluasi tingkat keandalan (reliability assessment), dan secara cerdas membersihkan jeda/pause rekaman (recording gaps).
- Lakukan validasi silang antara kedua engine:
  - < 3.5%: Sangat Stabil (Mesin Aerobik Matang).
  - 3.5% – 5.0%: Optimal / Lolos Standar Emas.
  - > 5.0%: Terjadi Drift Signifikan (dehidrasi, glikogen menipis, atau melampaui ambang AeT).
Analisis Lanjutan & Pemulihan Dual-Engine (garmin-connect MCP v0.2.0):
- Sub-Integer VO2 Max (FIT message 140): Panggil garmin_get_activity_streams untuk aktivitas terkait guna mengekstrak nilai estimasi VO2 Max presisi tinggi dengan 2 desimal (misal 39.42 ml/kg/min) untuk memantau adaptasi kebugaran mikro.
- Komparasi Head-to-Head (garmin_compare_activities): Jika sesi ini merupakan pengulangan dari sesi sebelumnya (misal Sub-Threshold mingguan atau rute lari rutin), panggil tool ini untuk membandingkan delta pace, delta detak jantung, delta kadens, dan perubahan Efficiency Factor ($EF = \text{Speed}/\text{HR}$).
- Audit Rekor Terbaik (garmin_get_personal_records): Manfaatkan paginasi v0.2.0 (limit: 50, start: 0, dan periksa flag truncated) untuk memeriksa apakah sesi hari ini memecahkan Best Effort baru (1K, 1 Mile, 5K, 10K, HM, FM, atau Longest Run).
- Audit Rehidrasi Pasca-Lari (garmin_get_hydration_range): Panggil data hidrasi hari ini untuk memeriksa asupan cairan aktual vs target harian pasca-latihan guna mencegah defisit cairan berkepanjangan.

Read the full file on GitHub · 124 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.

today Changed · +1 lines 1e996adffe4a
8d ago First seen · 123 lines · 66 tokens per session scan A f5f76b959158

Subscribe to this mod's changes

lapor-lari is a skill published in the GitHub repository hadidwirsty/intervals-icu-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,870 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-26.

Analytics and metrics

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

intervals-icu-mcp: Skill for Claude Code