obsidian-pkm-plugin: Instructions file for Claude Code

CLAUDE.md

obsidian-pkm-plugin CLAUDE.md is an instructions file for Claude Code from AdrianV101/obsidian-pkm-plugin. It costs 4,656 tokens per session, scanned A, original, MIT.

Development instructions for an Obsidian knowledge-management plugin that connects coding agents to an Obsidian vault. Obsidian is a note-taking app that stores linked notes as local files.

In plain words
What is it for?
Use them when developing or maintaining the MCP server, vault setup wizard, hooks, note-reading tools, tests, and linting.
Why use it?
They explain how the plugin is organized, installed, tested, and run, including its tools for two-way vault access.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is AdrianV101/obsidian-pkm-plugin's own configuration. It tells Claude Code how to work on obsidian-pkm-plugin 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-pkm-plugin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AdrianV101/obsidian-pkm-plugin. 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/AdrianV101/obsidian-pkm-plugin/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AdrianV101/obsidian-pkm-plugin

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-pkm-plugin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adrianv101/obsidian-pkm-plugin/claude-md.svg)](https://agentmods.dev/instructions/adrianv101/obsidian-pkm-plugin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/adrianv101/obsidian-pkm-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/adrianv101/obsidian-pkm-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,656 This file is loaded in full into every session.
When invoked 4,656 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 $0.04656 $0.04656
Opus 5 $0.02328 $0.02328
Sonnet 5 $0.00931 $0.00931
Haiku 4.5 $0.00466 $0.00466

Measured 7d ago against content hash 4d78623490e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

obsidian-pkm-plugin 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 7d 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 · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PKM: 01-Projects/Obsidian-MCP

CLAUDE.md

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

Project Overview

This is a Claude Code plugin that provides an MCP server and supporting tools for bidirectional knowledge flow between Claude Code and an Obsidian vault. It packages 20 MCP tools, Claude Code hooks, and a setup skill under the vault-pkm plugin identity.

Commands

# Install dependencies
npm install

# Run the MCP server (for testing)
VAULT_PATH="/path/to/your/vault" node cli.js

# Vault scaffolding wizard (templates, PARA folders)
node cli.js init

# Start the server
npm start

# Run unit tests
npm test

# Run linter
npm run lint

Architecture

The project consists of three parts:

MCP Server: A Node.js ES module server implementing the Model Context Protocol. The main entry point is index.js (tool definitions and request routing), with pure helper functions extracted to helpers.js. It provides 20 tools for vault interaction:

  • vault_read - Read note contents (supports pagination: heading, tail, tail_sections [with optional section_level param, default: 2], chunk, lines; auto-redirects to peek data for files >80k chars; force bypasses redirect)
  • vault_peek - Inspect file metadata/structure without reading full content (size, frontmatter, indented heading tree, preview)
  • vault_write - Create new notes from templates (enforces frontmatter; settable fields: status, priority, project, deciders, due, source; variables param for custom <%...%> substitution in template body)
  • vault_append - Add content to existing files, with optional positional insert (after/before heading, end of section)
  • vault_edit - Surgical string replacement (exact match, single occurrence)
  • vault_update_frontmatter - Update YAML frontmatter fields atomically (set, create, remove fields)
  • vault_search - Full-text search across markdown files
  • vault_semantic_search - Semantic similarity search using OpenAI embeddings (requires VAULT_PKM_OPENAI_KEY or OPENAI_API_KEY)
  • vault_suggest_links - Suggest relevant notes to link based on content similarity; graph_context: true for graph-semantic blending (requires VAULT_PKM_OPENAI_KEY or OPENAI_API_KEY)
  • vault_list / vault_recent - Directory listing and recent files
  • vault_links - Wikilink analysis ([[...]] syntax)
  • vault_neighborhood - Graph context exploration via BFS wikilink traversal
  • vault_query - Query notes by YAML frontmatter (type, status, tags [ALL must match], tags_any [ANY must match], dates, custom_fields for arbitrary field matching, sort_by/sort_order for result ordering)
  • vault_tags - Discover all tags with per-note counts; supports folder scoping, glob patterns, inline #tag parsing
  • vault_activity - Query/clear activity log (all tool calls with timestamps and session IDs)
  • vault_trash - Soft-delete to .trash/ (Obsidian convention), warns about broken incoming links
  • vault_move - Move/rename files with automatic wikilink updating across vault (update_links: false to skip)
  • vault_add_links - Add annotated wikilinks to a note's section with deduplication (default: ## Related)
  • vault_link_health - Graph health report: orphans, broken links, weakly connected notes, ambiguous links

Read the full file on GitHub · 346 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. 7d ago First seen · 346 lines · 4,656 tokens per session scan A 4d78623490e3

Subscribe to this mod's changes

obsidian-pkm-plugin CLAUDE.md is an instructions file published in the GitHub repository AdrianV101/obsidian-pkm-plugin (13 stars, last pushed 1mo ago), licensed MIT. It adds 4,656 tokens to every session, about $0.0233 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.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens