agentmods.dev

igpsport-mcp: Instructions file for Claude Code

CLAUDE.md

igpsport-mcp CLAUDE.md is an instructions file for Claude Code from dengxuhui/igpsport-mcp. It costs 2,436 tokens per session, scanned A, original, MIT.

Project instructions for a local MCP server that lets an AI assistant analyze iGPSport cycling data using natural language. MCP is a standard way for AI applications to call external tools; the server also creates structured training workouts and sends them back to the iGPSport app.

In plain words
What is it for?
Use it when developing or maintaining the iGPSport data integration, cycling metrics such as NP, IF, TSS, CTL, ATL, and TSB, regional client behavior, or workout creation.
Why use it?
It gives contributors clear boundaries for the project, including its Python architecture, local-only data handling, regional support, and required formulas for training metrics. It prevents work from drifting into rejected features such as a web dashboard or remote server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is dengxuhui/igpsport-mcp's own configuration. It tells Claude Code how to work on igpsport-mcp 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 igpsport-mcp configures →

not rated 3repo 2mo ago A scan 2,436 tokens original MIT
View source ↗ dengxuhui/igpsport-mcp pypi.org
Reuse

Borrowing it

Nothing to install: this file belongs to dengxuhui/igpsport-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/dengxuhui/igpsport-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dengxuhui/igpsport-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.

agentmods badge for igpsport-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dengxuhui/igpsport-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dengxuhui/igpsport-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dengxuhui/igpsport-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dengxuhui/igpsport-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.

agentmods 80×15 button for igpsport-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dengxuhui/igpsport-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dengxuhui/igpsport-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,436 This file is loaded in full into every session.
When invoked 2,436 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02436 $0.02436
Opus 5 $0.01218 $0.01218
Sonnet 5 $0.00487 $0.00487
Haiku 4.5 $0.00244 $0.00244

Measured 9d ago against content hash c27c945107ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

igpsport-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 9d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

详细工程蓝图、开发计划与协议逆向笔记保存在本地工作文档(未随仓库提交)。本文件是面向贡献者的稳定速查 + 设计红线。

项目定位

一个本地运行的 MCP server,把 iGPSport 骑行数据接入 LLM 客户端(Claude Desktop / Claude Code 等),让用户用自然语言分析训练数据。差异化:派生训练指标(NP/IF/TSS/CTL/ATL/TSB)在 MCP 层算好返回,LLM 拿到的是可直接讲故事的数字,而非原始 stream。

主线是只读分析;唯一的写入路径是训练课程(workout)——用自然语言生成结构化训练课并推回 iGPSport App,闭合「分析 → 处方 → 执行」的工具链。

本地 stdio 部署,不做 remote;数据不外流。

不要做的事(已决策,勿回头)

任何"好心"的反向建议都应被拒绝:

  • ❌ 不加 Web UI / dashboard——走纯 MCP stdio,复用 LLM 客户端的对话界面。
  • ❌ 不用 TypeScript——选 Python 是因为 fitparse / pandas / 官方 mcp SDK。
  • ❌ 不做 remote MCP、多账号、导出 .fit/.zwo、webhook 实时同步、其它码表 provider。
  • ⚠️ 双区域以 profile 切换,不分叉第二套 client。CN/INTL 差异收敛在 client/region.py 的 RegionProfile dataclass 里(host / origin / signing / 路径 override)。实现方案见 docs/intl-support-plan.md。
  • ⚠️ 派生指标公式严格按权威定义实现,不要自己发挥。NP/IF/TSS/CTL/ATL/TSB 都有公认公式,且必须有单元测试验证(与 Strava/iGPSport 显示误差 < 2%)。
  • ⚠️ Compact format 是必需项不是优化项:stream 输出永远是 {channel: {unit, values: [...]}} 的裸数组形式,绝不返回 [{time, power}, ...] 这种逐点对象。从第一行 stream 代码就遵守。
  • ⚠️ 训练课程(workout)是唯一的写入特例(原 v1 不做训练计划生成的红线已撤销,它是工具链闭合的必要环节)。但写入路径要克制:① LLM 面向的是 workout/ir.py 的人类单位 IR,编译到 iGPSport 原生格式;② 破坏性操作(delete_workout)必须有 confirm 门槛,默认只返回预览;③ workout 这 3 个 mobile endpoint 实测用默认 web access-key 即可上传(_WO_HDR={}),iOS 签名(AKIDiOSApp2,_IOS_HDR)只是保留的备用通道,不要默认切过去(会导致上传失败),也不要把它扩散成「逆向更多 App 接口」的借口。

核心架构

LLM Client ──stdio(MCP)── igpsport-mcp ──HTTPS── iGPSport 私有 API

server 内部分层(自上而下):

  1. MCP Tool Layer(tools/)——见下 17 个 tool。
  2. Analysis Layer(analysis/)——派生指标服务端算好再返回。
  3. Workout IR(workout/ir.py)——人类单位 IR ↔ iGPSport 原生课程格式的编译/校验。
  4. FIT Parser(fit/parser.py)——fitparse 封装。
  5. Client(client/)——登录 + token 缓存、活动列表、FIT 下载、workout 读写。
  6. Local Cache(storage/,SQLite)——~/.cache/igpsport-mcp/。

关键洞察:拿到 FIT 文件后,所有 stream / 派生指标 / 圈数据全部本地解析,跟 iGPSport 服务器零交互。因此读取链路只需维护极少数核心 endpoint(登录、活动列表、FIT 下载)。这是抗 API 漂移的设计核心,不要为了"省事"去逆向更多详情/统计接口。workout 是有意为之的写入特例(3 个 mobile endpoint,实测复用 web 签名),除此之外不扩张 API 面。

Read the full file on GitHub · 105 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. 9d ago First seen · 105 lines · 2,436 tokens per session scan A c27c945107ad

Subscribe to this mod's changes

igpsport-mcp CLAUDE.md is an instructions file published in the GitHub repository dengxuhui/igpsport-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 2,436 tokens to every session, about $0.0122 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.

Analytics and metricsLLMScientificclaudecyclingfit-filefitnessigpsport
Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens