vaultforge: Instructions file for Claude Code

CLAUDE.md

vaultforge CLAUDE.md is an instructions file for Claude Code from blacksmithers/vaultforge. It costs 894 tokens per session, scanned A, original, MIT.

A local MCP server for managing an Obsidian vault, which is a folder of linked Markdown notes used by the Obsidian note-taking app. It communicates with Claude Desktop through the local computer without HTTP or network access.

In plain words
What is it for?
Use it to read, create, edit, delete, append, search, list, and batch-process notes, manage daily notes, check vault status, and work with Obsidian canvas files.
Why use it?
It gives an AI assistant structured tools for working with notes and folders instead of relying on manual file handling. Its local design keeps vault operations on the computer.

Instructions file for Claude Code

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

This is blacksmithers/vaultforge's own configuration. It tells Claude Code how to work on vaultforge 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 vaultforge configures →

Reuse

Borrowing it

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

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 vaultforge CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/blacksmithers/vaultforge/claude-md"><img src="https://agentmods.dev/badge/instructions/blacksmithers/vaultforge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 894 This file is loaded in full into every session.
When invoked 894 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 $0.00894 $0.00894
Opus 5.5 $0.00358 $0.00358
Sonnet 5.5 $0.00179 $0.00179
Haiku 4.5 $0.00089 $0.00089

Measured 2mo ago against content hash ec4d4ab7b60e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vaultforge 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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 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

vaultforge is a local MCP (Model Context Protocol) server for Obsidian vault operations. It communicates via stdio transport with Claude Desktop — no HTTP, no network.

Commands

npm install          # Install dependencies
npm run build        # Compile TypeScript (tsc) → dist/
npm run dev          # Run directly via tsx (no build step)
npm start            # Run compiled output (must build first)

There are no tests, linter, or formatter configured.

Architecture

src/index.ts — MCP server entry point. Registers 16 tools using @modelcontextprotocol/sdk. The 12 vault tools (read_note, write_note, edit_note, delete_note, append_note, list_dir, search_vault, search_content, recent_notes, vault_status, batch, daily_note) are defined inline. The 4 canvas tools are registered via imported functions from src/tools/canvas/.

src/vault-index.ts — VaultIndex class maintains three in-memory Maps:

  • files: relPath → FileEntry (size, mtime, extension)
  • byName: lowercase filename stem → Set of relPaths (enables fuzzy resolution)
  • byDir: directory → Set of child paths

Built by recursive readdir on startup, kept in sync via fs.watch (recursive). Ignores .obsidian, .git, .trash, node_modules, dotfiles.

src/tools/canvas/ — Canvas tools module (4 tools). Each tool file exports a register* function called from index.ts.

  • types.ts — TypeScript interfaces for JSON Canvas spec (nodes, edges, semantic input types)
  • canvas-utils.ts — Shared utilities: ID generation, text height estimation, edge side calculation, fuzzy node matching, relative positioning
  • layout-engine.ts — dagre wrapper for DAG layout (Sugiyama algorithm). Converts dagre center-origin coordinates to canvas top-left origin
  • canvas-create.ts — canvas_create tool: agent provides semantic graph (labels + edges), tool calculates all geometry via dagre
  • canvas-read.ts — canvas_read tool: reads .canvas JSON and returns semantic representation (labels, connections, stats)
  • canvas-patch.ts — canvas_patch tool: add/remove/update nodes and edges with relative positioning
  • canvas-relayout.ts — canvas_relayout tool: re-layout existing canvas via dagre without changing content

Read the full file on GitHub · 53 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 · 53 lines · 894 tokens per session scan A ec4d4ab7b60e

Subscribe to this mod's changes

vaultforge CLAUDE.md is an instructions file published in the GitHub repository blacksmithers/vaultforge (14 stars, last pushed 7mo ago), licensed MIT. It adds 894 tokens to every session, about $0.0036 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

vaultforge CLAUDE.md compared with instructions from other repositories

vaultforge CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vaultforge CLAUDE.mdblacksmithers/vaultforgeInstructions file147mo agoMITA894Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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