What is bike-mcp-server CLAUDE.md?

Project instructions for bike-mcp-server, a server that lets AI assistants read and change outlines in Bike, a macOS outliner app. They describe the TypeScript structure, input validation, AppleScript connection, and tool logic.

Use them when building, testing, or modifying Bike document tools and the server that registers them.

They explain how requests travel from the assistant to Bike, reducing the risk of changes that break validation or macOS communication.

How hildersantos/bike-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hildersantos/bike-mcp-server. 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/hildersantos/bike-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hildersantos/bike-mcp-server

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/hildersantos/bike-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/hildersantos/bike-mcp-server/claude-md)

Your own site

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

Per session 640 This file is loaded in full into every session.

When invoked 640 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	$0.00640	$0.00640
Opus 5	$0.00320	$0.00320
Sonnet 5	$0.00128	$0.00128
Haiku 4.5	$0.00064	$0.00064

Measured 10d ago against content hash a443b1521303, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bike-mcp-server 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 10d 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 · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 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.

Overview

MCP (Model Context Protocol) server for the Bike outliner app on macOS. The server exposes Bike's functionality as tools that AI assistants can use to read and manipulate outlines.

Commands

npm run build      # Compile TypeScript to dist/
npm run dev        # Watch mode for development
npm start          # Run the compiled server

Architecture

src/
├── index.ts              # MCP server setup, tool registration
├── schemas/document.ts   # Zod schemas for tool input validation
├── services/applescript.ts # AppleScript execution utilities
└── tools/document.ts     # Tool implementations (business logic)

Core Flow

Tool Registration (src/index.ts): Registers MCP tools with the server, defines descriptions/schemas, and maps to implementation functions
Input Validation (src/schemas/document.ts): Zod schemas validate and type tool inputs
AppleScript Execution (src/services/applescript.ts): Executes multi-line AppleScript via osascript, handles result parsing
Tool Logic (src/tools/document.ts): Builds AppleScript strings dynamically based on input parameters

AppleScript Pattern

All Bike interactions go through AppleScript. The runAppleScriptMultiline function splits scripts by line and passes each as a -e argument to osascript. This handles complex scripts better than single-line escaping.

Row/Document ID Format

Documents: doc:XXX (root row ID)
Rows: row:XXX (row ID from Bike)

IDs are returned in human-readable format: - Row text [row:XXX]

Available Tools

Reading

bike_list_documents - List all open documents
bike_get_document_outline - Read document structure (supports max_depth)
bike_query_rows - Search rows using Bike's outline path syntax

Writing

bike_create_document - Create new document with optional structure
bike_create_rows - Add rows with nested children and positioning
bike_update_row - Edit row content and type (batch support)
bike_delete_row - Remove rows (batch support)
bike_group_rows - Group/move multiple rows under a parent

Read the full file on GitHub · 77 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.

10d ago First seen · 77 lines · 640 tokens per session scan A a443b1521303

Subscribe to this mod's changes

bike-mcp-server CLAUDE.md is an instructions file published in the GitHub repository hildersantos/bike-mcp-server (4 stars, last pushed 9mo ago), licensed MIT. It adds 640 tokens to every session, about $0.0032 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

bike-mcp-server: Instructions file for Claude Code