agentmods.dev

Cortex CLAUDE.md

Development instructions for Cortex, an open-source AI memory system that searches code using local PostgreSQL, vector search, and Ollama embeddings.

In plain words
What is it for?
Use them to start services, synchronize code files into the search database, install the sync hook, type-check the project, or manage its database.
Why use it?
They explain how to set up the database and services and warn which commands delete stored embeddings or Docker volumes.

Instructions file

6 7mo ago A scan 1,401 tokens original MIT
View the source file Remskill/Cortex
Install

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.

agentmods
npx agentmods add instructions/remskill/cortex/claude-md
Clone the repo
git clone --depth 1 https://github.com/Remskill/Cortex
Per session 1,401 This file is loaded in full into every session.
When invoked 1,401 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01401 $0.01401
Opus 5 $0.00700 $0.00700
Sonnet 5 $0.00280 $0.00280
Haiku 4.5 $0.00140 $0.00140

Measured yesterday against content hash 402959388bc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Cortex 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 yesterday.

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 · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 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

Cortex is a free, open-source AI memory system that provides semantic search over codebases via Model Context Protocol (MCP). It uses local PostgreSQL + pgvector for vector storage and Ollama for embeddings.

Development Commands

# Setup & Database
npm run setup          # Create schema + sync all files (full setup)
npm run db:setup       # Create database schema only
npm run db:sync        # Re-sync all files to database
npm run db:wipe        # Delete all embeddings (destructive)

# Docker
npm run docker:up      # Start PostgreSQL + Ollama containers
npm run docker:down    # Stop containers (keeps data)
npm run docker:logs    # View container logs
docker-compose down -v # Stop and remove volumes (destructive!)

# Development
npm run mcp:server     # Start MCP server manually (Claude Code auto-starts via .mcp.json)
npm run hook:install   # Install git pre-commit hook for auto-sync
npx tsc --noEmit       # Type check without emitting

Core Architecture

Module System

  • ESM: Uses ES modules ("type": "module" in package.json)
  • Imports: .js extensions optional - tsx resolves both (codebase is inconsistent, some use .js)
  • Runtime: Uses tsx for TypeScript execution without compilation

MCP Server (src/server.ts)

  • Transport: STDIO (NOT HTTP/SSE) - receives stdin, returns stdout
  • Tools: 6 MCP tools: cortex_init, cortex_query, cortex_sync, cortex_stats, cortex_list_files, cortex_delete
  • Entry point: Launched by Claude Code via .mcp.json configuration

Database Layer (src/db.ts)

  • Package: Uses postgres (NOT pg) for better performance
  • Connection: Single global sql connection for all operations (max: 1)
  • Memory: Single connection reduces memory (~50MB/connection saved)
  • Isolated connections: createConnection()/closeIsolatedConnection() available but currently unused

Read the full file on GitHub · 142 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. yesterday First seen · 142 lines · 1,401 tokens per session scan A 402959388bc3

Subscribe to this mod's changes

Cortex CLAUDE.md is an instructions file published in the GitHub repository Remskill/Cortex (6 stars, last pushed 7mo ago), licensed MIT. It adds 1,401 tokens to every session, about $0.0070 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.

DatabasesDevOps and cloudMemory and contextai-memoryclaude-aiclaude-cliclaude-codemcpollama
Related

Other instructions, from other repositories

timps AGENTS.md

Instructions for Sandeeprdy1729/timps, covering agents.md — timps codebase guide, repo layout, typescript config drift, agent entrypoints (timps-code) and auto-capture & context-anywhere (timps setup / recall).

Sandeeprdy1729/timps · 24,407 tokens

Nemp-memory CLAUDE.md

Instructions for SukinShetty/Nemp-memory, covering project context (via nemp memory), project info, technical details and other.

SukinShetty/Nemp-memory · 222 tokens

weighted-compact CLAUDE.md

Instructions for zzallirog/weighted-compact, covering claude.md — weighted-compact root, substrate framing, tl;dr in 30 seconds, repo map and architectural invariants (locked).

zzallirog/weighted-compact · 3,490 tokens

memory CLAUDE.md

Instructions for RLabs-Inc/memory, covering memory system - claude.md, project overview, core philosophy, architecture overview and development setup.

RLabs-Inc/memory · 1,848 tokens

SeekMoney-ai CLAUDE.md

Instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.

zykooooooooo/SeekMoney-ai · 2,178 tokens

ai-workflow AGENTS.md

Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.

cunhaax/ai-workflow · 2,602 tokens