What is cortex CLAUDE.md?

Project instructions for Cortex, a Claude Code plugin that stores useful context from past sessions and retrieves it later. The document also describes its commands, build process, tests, and internal data flow.

Use it when developing Cortex, including installing dependencies, building its entry points, checking types, testing sample input, and understanding its architecture.

It gives a coding agent the repository context needed to build, check, and understand Cortex without rediscovering the project structure.

cortex CLAUDE.md — Instructions file by hjertefolger

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/hjertefolger/cortex/claude-md

Clone the repo

git clone --depth 1 https://github.com/hjertefolger/cortex

Per session 2,192 This file is loaded in full into every session.

When invoked 2,192 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.02192	$0.02192
Opus 5	$0.01096	$0.01096
Sonnet 5	$0.00438	$0.00438
Haiku 4.5	$0.00219	$0.00219

Measured 2d ago against content hash d0c161394484, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

cortex CLAUDE.md scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

4. Configures statusline in `~/.claude/settings.json`

CLAUDE.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 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 when working with this repository.

Project Overview

Cortex is a Claude Code plugin that provides persistent local memory with cross-session recall. It uses vector embeddings and hybrid search to store and retrieve meaningful context from past sessions.

Key Features:

Automated context management with configurable thresholds
Smart compaction: save, clear, and restore continuity
MCP server exposing memory tools to Claude
Session analytics and insights
Colored statusline with progress bar
Granular memory saving with cortex_remember

Build Commands

npm install            # Install dependencies
npm run build          # Build both index.js and mcp-server.js
npm run build:index    # Build main entry point only
npm run build:mcp      # Build MCP server only
npm run typecheck      # Type check without emitting

# Test with sample stdin data
echo '{"cwd":"/home/user/project","context_window":{"used_percentage":45}}' | node dist/index.js stats

Architecture

Data Flow

Claude Code → stdin JSON → parse → command router → handler → stdout
                                        ↓
                               SQLite + Embeddings
                                        ↓
                              ~/.cortex/memory.db

MCP Client → JSON-RPC → mcp-server.js → tools → database

Core Components

File	Purpose
`src/index.ts`	Command router and handlers
`src/mcp-server.ts`	MCP server exposing tools
`src/stdin.ts`	Parse Claude Code's JSON input
`src/types.ts`	TypeScript interfaces
`src/database.ts`	SQLite schema, queries, FTS5
`src/embeddings.ts`	BGE model loading, vector generation
`src/search.ts`	Hybrid search (vector + keyword + RRF)
`src/archive.ts`	Transcript parsing, content extraction, restoration context
`src/config.ts`	Configuration management
`src/analytics.ts`	Session tracking and insights

Read the full file on GitHub · 266 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.

2d ago First seen · 266 lines · 2,192 tokens per session scan B d0c161394484

Subscribe to this mod's changes

cortex CLAUDE.md is an instructions file published in the GitHub repository hjertefolger/cortex (174 stars, last pushed 5mo ago), licensed MIT. It adds 2,192 tokens to every session, about $0.0110 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Documents Planning Testing

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

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

cortex CLAUDE.md