Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/eddmann/obsidian-mcp/claude-mdgit clone --depth 1 https://github.com/eddmann/obsidian-mcpWrote 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.
[](https://agentmods.dev/instructions/eddmann/obsidian-mcp/claude-md)<a href="https://agentmods.dev/instructions/eddmann/obsidian-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/eddmann/obsidian-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03223 | $0.03223 |
| Opus 5 | $0.01612 | $0.01612 |
| Sonnet 5 | $0.00645 | $0.00645 |
| Haiku 4.5 | $0.00322 | $0.00322 |
Grade A, and why
obsidian-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 352 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
An MCP (Model Context Protocol) server that provides LLM access to git-backed Obsidian vaults. The server supports three deployment modes: stdio (local), HTTP (local with OAuth), and AWS Lambda (remote with OAuth + DynamoDB).
Workspace Structure
This is an npm workspace monorepo with two packages:
packages/app- Core MCP server implementation (stdio, HTTP, Lambda handlers)packages/cdk- AWS CDK infrastructure stack for Lambda deployment
Development Commands
Building
# Build everything (TypeScript + all bundles)
npm run build
# Build specific bundles
npm run build:app # All app bundles
npm run build:lambda # Lambda bundle only
npm run build:cdk # CDK infrastructure
# Clean build artifacts
npm run clean
Running Locally
# Stdio mode (for Claude Desktop, Cursor)
npm run dev
# HTTP mode with OAuth (for ChatGPT, remote clients)
npm run dev:http
Testing
# Run all tests
npm test
# Watch mode
npm run test:watch
Linting & Formatting
# Lint TypeScript files
npm run lint
npm run lint:fix
# Format all files
npm run format
npm run format:check
AWS Deployment
# Synthesize CloudFormation template
npm run cdk:synth
# Deploy to AWS
npm run cdk:deploy
# Destroy stack
npm run cdk:destroy
Architecture
Core Concepts
VaultManager Interface: Abstract interface for vault operations (read, write, delete, move files). Implemented by GitVaultManager which handles git clone/pull/commit/push automatically.
Transport Modes: The MCP server supports two transports selected at runtime:
- Stdio: Standard input/output for local MCP clients (no OAuth)
- HTTP: Streamable HTTP with OAuth 2.0 for remote access
Three Server Implementations:
packages/app/src/server/local/stdio.ts- Local stdio mode with pre-configured credentialspackages/app/src/server/local/http.ts- Local HTTP mode with in-memory session storagepackages/app/src/server/lambda/index.ts- Lambda handler with DynamoDB session storage
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.
- 4d ago First seen · 352 lines · 3,223 tokens per session scan A b7d67c48cd06
obsidian-mcp CLAUDE.md is an instructions file published in the GitHub repository eddmann/obsidian-mcp (14 stars, last pushed 9mo ago), licensed MIT. It adds 3,223 tokens to every session, about $0.0161 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 2026-08-30.
Other instructions, from other repositories
hermes-agent AGENTS.md
AGENTS.md instructions for NousResearch/hermes-agent, covering hermes agent - development guide, what hermes is, contribution rubric — what we want / what we don't, what we want and what we don't want (rejected even when well-built).
mem0 AGENTS.md
AGENTS.md instructions for mem0ai/mem0, covering agents.md, do not, where to look, repository map and setup.
repomix copilot-instructions.md
Copilot instructions for yamadashy/repomix, a project described as: 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini…
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
ruby_llm AGENTS.md
AGENTS.md instructions for crmne/ruby_llm, covering agents.md, what this is, ground rules, setup and commands.
awesome-ChatGPT-repositories CLAUDE.md
Claude Code instructions for taishi-i/awesome-ChatGPT-repositories, covering awesome-chatgpt-repositories — claude code guide, repository structure, plugin skill (when installed via /plugin), local standalone command (when repo is cloned) and compact data format (plugins/awesome-chatgpt-search/data/).