What is coros-training-mcp CLAUDE.md?

A project instruction file for a COROS connector, where COROS is a fitness platform for workout and health data. It describes a fork intended to support editable scheduled running workouts.

Use it when developing the connector, especially for scheduled running workouts, workout variables such as pace or distance, date changes, authentication, daily metrics, sleep, HRV, and activities.

It clarifies the project's direction, supported data, boundaries, and implementation priorities for agents working on the code.

How dholliday3/coros-training-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dholliday3/coros-training-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/dholliday3/coros-training-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dholliday3/coros-training-mcp

Made for: Claude Code.

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/instructions/dholliday3/coros-training-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dholliday3/coros-training-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dholliday3/coros-training-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dholliday3/coros-training-mcp/claude-md/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/instructions/dholliday3/coros-training-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dholliday3/coros-training-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,267 This file is loaded in full into every session.

When invoked 1,267 The same file — it is already loaded in full.

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	$0.01267	$0.01267
Opus 5	$0.00633	$0.00633
Sonnet 5	$0.00253	$0.00253
Haiku 4.5	$0.00127	$0.00127

Measured 8d ago against content hash 46957446dc0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

coros-training-mcp CLAUDE.md 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 8d 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.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

COROS MCP Fork Plan

This repository is a local fork of cygnusb/coros-mcp intended to become a running-first, editable COROS MCP rather than a mostly read-only metrics/workout wrapper.

Actionable implementation tasks live in TODOS.md. Terminology for library workouts, scheduled entries, and plan containers lives in docs/workout-taxonomy.md.

Goals

Support first-class editing of scheduled running workouts.
Support running workout variables such as distance, pace, repeats, rest, and date changes.
Keep the MCP tool surface small and stable.
Hide sport-specific payload complexity behind a unified workout schema.
Preserve compatibility with upstream where it does not fight the fork's direction.

Non-Goals

Do not keep separate user-facing tool families for bike, run, and strength unless the backend makes a unified tool impossible.
Do not store raw account credentials in repo files.
Do not promise post-workout strength result logging until the write endpoint is verified.

Current State

The upstream project already supports:

Web and mobile auth against unofficial COROS endpoints
Daily metrics, sleep, HRV, activities
Workout creation and deletion
Schedule listing, schedule add, and schedule remove
Strength workout creation from the COROS exercise catalogue

The main gap is that workout creation is currently shaped around time-based, power-oriented workouts and does not expose a generic edit path for running workouts.

Product Direction

The fork should present a small set of MCP tools:

list_workouts
get_workout
create_run_workout
update_run_workout
create_bike_workout
update_bike_workout
create_workout as a compatibility path for simpler non-running construction
update_workout as the lower-level clone-and-patch primitive
delete_workout
list_scheduled_workouts
move_scheduled_workout
replace_scheduled_workout

Optional later tools:

clone_workout
log_strength_results
list_activity_results

Read the full file on GitHub · 170 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.

8d ago First seen · 170 lines · 1,267 tokens per session scan A 46957446dc0b

Subscribe to this mod's changes

coros-training-mcp CLAUDE.md is an instructions file published in the GitHub repository dholliday3/coros-training-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 1,267 tokens to every session, about $0.0063 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

coros-training-mcp: Instructions file for Claude Code