obsidian-claude-code-mcp: Instructions file for Claude Code

CLAUDE.md

obsidian-claude-code-mcp CLAUDE.md is an instructions file for Claude Code from iansinnott/obsidian-claude-code-mcp. It costs 1,557 tokens per session, scanned A, original, 0BSD.

Development instructions for an Obsidian plugin that connects Obsidian vaults to Claude Code and Claude Desktop through MCP servers.

In plain words
What is it for?
Installing dependencies, running a development build, producing a release build, updating versions, linting, and working on the WebSocket or HTTP/SSE servers.
Why use it?
They explain the project structure, supported connection methods, and commands needed to build and check the plugin.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is iansinnott/obsidian-claude-code-mcp's own configuration. It tells Claude Code how to work on obsidian-claude-code-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 obsidian-claude-code-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to iansinnott/obsidian-claude-code-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/iansinnott/obsidian-claude-code-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/iansinnott/obsidian-claude-code-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 obsidian-claude-code-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/iansinnott/obsidian-claude-code-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iansinnott/obsidian-claude-code-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,557 This file is loaded in full into every session.
When invoked 1,557 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 $0.01557 $0.01557
Opus 5.5 $0.00623 $0.00623
Sonnet 5.5 $0.00311 $0.00311
Haiku 4.5 $0.00156 $0.00156

Measured 2mo ago against content hash e9823cc160f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

obsidian-claude-code-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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 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.

Project Overview

This is an Obsidian plugin that implements MCP (Model Context Protocol) servers to enable Claude Code and Claude Desktop integration with Obsidian vaults. The plugin provides both WebSocket (for Claude Code CLI) and HTTP/SSE (for Claude Desktop) transports for maximum compatibility.

Development Commands

  • bun install - Install dependencies
  • bun run dev - Start compilation in watch mode
  • bun run build - Type check and build for production
  • bun run version patch|minor|major - Bump version and update manifest files
  • eslint main.ts - Run linting

Architecture

Core Components

  • main.ts - Plugin entry point that orchestrates initialization, settings management, and server lifecycle
  • src/settings.ts - Comprehensive settings management with real-time server status display
  • src/mcp/ - MCP protocol implementation
    • dual-server.ts - Manages both WebSocket and HTTP servers with tool registry
    • server.ts - WebSocket server for Claude Code CLI integration
    • http-server.ts - HTTP/SSE server for Claude Desktop (uses MCP spec 2024-11-05)
    • handlers.ts - Request routing with separation of IDE/MCP concerns
    • types.ts - TypeScript interfaces for MCP protocol
  • src/ide/ - Claude Code IDE-specific functionality
    • ide-handler.ts - Handles IDE-specific requests (ide_connected, etc.)
    • ide-tools.ts - IDE-specific tool implementations (openDiff, close_tab, etc.)
  • src/shared/ - Common functionality
    • tool-registry.ts - Automatic tool registration and validation system
  • src/obsidian/ - Obsidian API integration
    • workspace-manager.ts - Tracks active file and selection using DOM events
    • utils.ts - Path normalization and validation utilities
  • src/tools/ - MCP tool implementations
    • file-tools.ts - File read/write operations
    • general-tools.ts - General workspace and file manipulation tools
  • src/terminal/ - Optional embedded terminal feature
    • terminal-view.ts - Terminal UI implementation using xterm.js
    • pseudoterminal.ts - Platform-specific terminal spawning
    • python-detection.ts - Python environment detection

Read the full file on GitHub · 154 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. 2mo ago First seen · 154 lines · 1,557 tokens per session scan A e9823cc160f3

Subscribe to this mod's changes

obsidian-claude-code-mcp CLAUDE.md is an instructions file published in the GitHub repository iansinnott/obsidian-claude-code-mcp (359 stars, last pushed 1y ago), licensed 0BSD. It adds 1,557 tokens to every session, about $0.0062 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 2026-08-30.

Related

obsidian-claude-code-mcp CLAUDE.md compared with instructions from other repositories

obsidian-claude-code-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
obsidian-claude-code-mcp CLAUDE.mdiansinnott/obsidian-claude-code-mcpInstructions file3591y ago0BSDA1,557Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode