ClaudeCyclingMCP: Skill for Claude Code

.claude/skills/mywhoosh-upload/SKILL.md

mywhoosh-upload is a skill for Claude Code from elias-ramzi/ClaudeCyclingMCP. It costs 154 tokens per session (5,186 once invoked), scanned A, original, MIT.

A tool for turning a described cycling session into a structured workout and adding it to MyWhoosh, an indoor cycling training app.

In plain words
What is it for?
It helps create interval, endurance, threshold, VO2, sweet-spot, and ramp-test workouts, then load them into your MyWhoosh library through the browser.
Why use it?
It avoids manually rebuilding intervals in MyWhoosh. It also highlights that your FTP, the power level used to scale workouts, must be correct before uploading.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is elias-ramzi/ClaudeCyclingMCP's own configuration. It tells Claude Code how to work on ClaudeCyclingMCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ClaudeCyclingMCP configures →

Part of the claude-cycling-mcp plugin — 2 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to elias-ramzi/ClaudeCyclingMCP. 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/elias-ramzi/ClaudeCyclingMCP/main/.claude/skills/mywhoosh-upload/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/elias-ramzi/ClaudeCyclingMCP

Made for: Claude Code.

Or install claude-cycling-mcp, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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 mywhoosh-upload

README.md
[![agentmods](https://agentmods.dev/badge/skills/elias-ramzi/claudecyclingmcp/mywhoosh-upload/github.svg)](https://agentmods.dev/skills/elias-ramzi/claudecyclingmcp/mywhoosh-upload)
Your own site
<a href="https://agentmods.dev/skills/elias-ramzi/claudecyclingmcp/mywhoosh-upload"><img src="https://agentmods.dev/badge/skills/elias-ramzi/claudecyclingmcp/mywhoosh-upload/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 mywhoosh-upload

Your own site · 80×15
<a href="https://agentmods.dev/skills/elias-ramzi/claudecyclingmcp/mywhoosh-upload"><img src="https://agentmods.dev/badge/skills/elias-ramzi/claudecyclingmcp/mywhoosh-upload.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,186 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00154 $0.05186
Opus 5 $0.00077 $0.02593
Sonnet 5 $0.00031 $0.01037
Haiku 4.5 $0.00015 $0.00519

Measured 11d ago against content hash 065b94539772, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mywhoosh-upload 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 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.

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.

.claude/skills/mywhoosh-upload/SKILL.md · 424 lines

How it starts

The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Getting a workout into MyWhoosh

MyWhoosh has no API. The only supported route is the browser flow below, driven through Claude in Chrome. Everything here was confirmed in a real session.

Two things make this different from an ordinary browser task:

  1. EXPORT TO MYWHOOSH spends a slot credit. Credits are finite and there is no undo. You must stop and get explicit confirmation before clicking it.
  2. It is UI automation, so it will rot when MyWhoosh redesigns something. Each step below says what you should expect to see. If what you see doesn't match, stop and report which step's expectation failed and what was on screen instead. Do not improvise around a mismatch — a stray click on the chart creates phantom blocks in the workout.

Why the FTP has to come first

A .zwo stores power only as fractions of FTP. The watts actually ridden are fraction × the FTP MyWhoosh has. So if the session is "3 x 10 min at 232 W" and you render against 255 W but MyWhoosh is set to 200 W, every target is ridden at 182 W — about 22% too easy — and nothing anywhere reports a problem. The file is valid; it is just scaled to a different athlete.

Unless the session is written in percentages. If every block is power_pct, the percentages are the intent: they render to the same fractions under any FTP, so the builder's FTP changes only the watts displayed and the TSS/IF figures — nothing stored is rescaled. Still read it and still report a disagreement, but do not halt over one. The FTP is load-bearing exactly when the athlete gave watts.

get_cycling_ftp reads Garmin's profile, which is a different number and frequently stale. It is a starting point, not the answer.

Since you are opening the browser anyway, read MyWhoosh's own FTP out of the builder and render against that (Step 3). That makes the fractions correct by construction, rather than correct by assumption.

Consequence for ordering: draft the session first, but do not render until after Step 3. If the athlete gave targets in watts, those watts are the fixed intent, and the FTP is what converts them.

Read the full file on GitHub · 424 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 · 424 lines · 154 tokens per session scan A 065b94539772

Subscribe to this mod's changes

mywhoosh-upload is a skill published in the GitHub repository elias-ramzi/ClaudeCyclingMCP (0 stars, last pushed 18d ago), licensed MIT. It adds 154 tokens to every session and 5,186 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

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

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