What is claude-cortex CLAUDE.md?

A Claude Code instruction set for Claude Cortex, a tool that stores coding-agent memory in a local ledger and can search, sign, sync, and summarize it.

Use it to install Claude Cortex locally or from a marketplace, preserve work-in-progress state, search past information, and share or synchronize stored agent memory.

It gives Claude Code a persistent record of useful project context and unfinished work across sessions. Installation also sets up the package, hooks, settings, and ledger storage.

How aaronb305/claude-cortex configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to aaronb305/claude-cortex. 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/aaronb305/claude-cortex/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/aaronb305/claude-cortex

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/aaronb305/claude-cortex/claude-md/github.svg)](https://agentmods.dev/instructions/aaronb305/claude-cortex/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/aaronb305/claude-cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronb305/claude-cortex/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/aaronb305/claude-cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronb305/claude-cortex/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8,938 This file is loaded in full into every session.

When invoked 8,938 The same file — it is already loaded in full.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.08938	$0.08938
Opus 5.5	$0.03575	$0.03575
Sonnet 5.5	$0.01788	$0.01788
Haiku 4.5	$0.00894	$0.00894

Measured 2mo ago against content hash d976498f1016, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

claude-cortex CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

| uv | Package management | `pip install uv` or `curl -LsSf https://astral.sh/uv/install.sh \| sh` |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| uv | Package management | `pip install uv` or `curl -LsSf https://astral.sh/uv/install.sh \| sh` |

CLAUDE.md · 1,072 lines

How it starts

The opening of the file, as written. The whole thing — 1,072 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Cortex

Blockchain-style ledger memory with performance-based reinforcement for Claude Code.

Installation

# Install from local directory
cd ~/projects/claude-cortex
./install.sh

# Or install plugin from local marketplace
claude plugin install claude-cortex@claude-cortex --scope user

This will:

Install the Python package with uv
Set up hooks in ~/.claude/hooks/
Configure Claude Code settings
Initialize the global ledger at ~/.claude/ledger/

Dependencies

All features are included by default with uv sync:

Feature	Description	Dependencies
Ledger storage	Blockchain-style learning storage	pydantic, click
Full-text search	FTS5 keyword search	sqlite3 (Python stdlib)
Semantic search	Vector similarity search	fastembed, sqlite-vec
Cryptographic signing	Ed25519 block signatures	cryptography
Content-addressed storage	Deduplication via content hash	(included)
Distributed sync	Merkle-based ledger sync	(included)
Handoffs	Work-in-progress state capture	(included)
Summaries	Transcript summary storage	(included)
Confidence decay	Time-based confidence adjustment	(included)
Cross-project transfer	Learning suggestions & import	(included)
File locking	Race condition prevention	fcntl (Python stdlib)
Git/PR ingestion	Extract learnings from commits & PRs	gh CLI (for PRs)
Entity graph	Code structure tracking	tree-sitter-language-pack
MCP tools	Low-latency Claude Code integration	mcp

External Requirements

Requirement	Purpose	Install
Python 3.10+	Runtime	System package manager
uv	Package management	`pip install uv` or `curl -LsSf https://astral.sh/uv/install.sh \| sh`
gh CLI	GitHub PR ingestion	`brew install gh` or system package manager

Verify Installation

# Check all dependencies installed
uv sync

# Verify semantic search
uv run python -c "from claude_cortex.search.semantic import is_available; print(is_available())"

# Verify entity extraction
uv run python -c "from claude_cortex.entities.extractors import get_extractor_for_file; print(get_extractor_for_file('test.py'))"

Read the full file on GitHub · 1,072 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.

2mo ago First seen · 1,072 lines · 8,938 tokens per session scan C d976498f1016

Subscribe to this mod's changes

claude-cortex CLAUDE.md is an instructions file published in the GitHub repository aaronb305/claude-cortex (2 stars, last pushed 7mo ago), licensed MIT. It adds 8,938 tokens to every session, about $0.0358 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context

claude-cortex CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-cortex CLAUDE.mdaaronb305/claude-cortex	Instructions file	2	7mo ago	MIT	C	8,938	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-cortex: Instructions file for Claude Code