agentmods.dev

lox-brain: Instructions file for Claude Code

CLAUDE.md

lox-brain CLAUDE.md is an instructions file for Claude Code from isorensen/lox-brain. It costs 2,199 tokens per session, scanned A, original, MIT.

Repository instructions for Lox, a personal knowledge system linking a local Obsidian note vault with a PostgreSQL database that supports meaning-based search. An MCP server lets an AI assistant access the system through a secure VPN connection.

In plain words
What is it for?
Use them when changing Lox’s note synchronization, semantic search, database, embedding service, MCP server, or VPN-connected infrastructure.
Why use it?
They explain which system is authoritative—the Obsidian vault—and how the database, embeddings, file watcher, and network connection fit together. This helps agents avoid treating the search index as the original notes.

Instructions file for Claude Code

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

This is isorensen/lox-brain's own configuration. It tells Claude Code how to work on lox-brain 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 lox-brain configures →

not rated 2repo yesterday A scan 2,199 tokens original MIT
View source ↗ isorensen/lox-brain
Reuse

Borrowing it

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

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 lox-brain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/isorensen/lox-brain/claude-md.svg)](https://agentmods.dev/instructions/isorensen/lox-brain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/isorensen/lox-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/isorensen/lox-brain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,199 This file is loaded in full into every session.
When invoked 2,199 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 $0.02199 $0.02199
Opus 5 $0.01099 $0.01099
Sonnet 5 $0.00440 $0.00440
Haiku 4.5 $0.00220 $0.00220

Measured 7d ago against content hash d11d8cf72676, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lox-brain 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 · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 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

Lox (formerly Open Brain) is a hybrid personal knowledge management system connecting a local Obsidian Vault with PostgreSQL+pgvector on a GCP VM, exposed via an MCP Server accessible through WireGuard VPN. Claude Code acts as a first-class client, reading/writing notes and performing semantic search.

Core principle: Obsidian Vault is the source of truth. pgvector is a read index derived from it.

Architecture

Local (Obsidian Desktop) <--git sync--> VM (GCE)
                                         |
                                         +-- PostgreSQL 16 + pgvector (localhost only)
                                         +-- Vault Watcher (chokidar, detects .md changes)
                                         +-- Embedding Service (OpenAI text-embedding-3-small)
                                         +-- MCP Server (TypeScript, stdio or HTTP transport)
                                         +-- WireGuard VPN (UDP 51820)

Client --VPN--> VM (10.10.0.1) --> MCP Server --> tools

Transports: The MCP server supports two transport modes controlled by MCP_TRANSPORT:

  • stdio (default) — used for single-user personal mode, launched by Claude Code directly
  • http — used for team mode; binds to MCP_HOST (default 127.0.0.1, set to VPN interface for multi-user), port MCP_PORT (default 3100). Uses session-based StreamableHTTPServerTransport. The caller's VPN IP is extracted from req.socket.remoteAddress for peer attribution.

Identity attribution (created_by): resolved server-side per request, never from client-supplied args. Resolution order: (a) trusted-proxy actor — a caller presenting a valid X-Lox-Proxy-Secret (matching LOX_TRUSTED_PROXY_SECRET) may forward an X-Lox-Actor header, for backend integrations that reach the MCP over the private network without being a registered WireGuard peer; (b) the caller's WireGuard peer, resolved from source IP; (c) stripped (anti-spoofing) when neither resolves. See packages/core/.env.example and packages/core/src/mcp/trusted-proxy.ts.

Read the full file on GitHub · 169 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 · 169 lines · 2,199 tokens per session scan A d11d8cf72676

Subscribe to this mod's changes

lox-brain CLAUDE.md is an instructions file published in the GitHub repository isorensen/lox-brain (2 stars, last pushed yesterday), licensed MIT. It adds 2,199 tokens to every session, about $0.0110 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.

DatabasesMemory and contextPostgreSQLobsidianopenbrainsecondbrain
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 · 5,153 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

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