What is claude-cortex CLAUDE.md?

Project instructions for Claude Cortex, a system with Python tools for a semantic knowledge graph and analysis services, plus TypeScript tools for hooks and an MCP dashboard. An MCP server is a program that lets an AI agent use external tools.

Installing and testing the Brainiac, Cortex, and ContextScore components, checking knowledge-graph data, and building the TypeScript dashboard.

They explain the project structure, development commands, and testing requirements across its separate components.

How Peaky8linders/claude-cortex configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Peaky8linders/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/Peaky8linders/claude-cortex/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Peaky8linders/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/peaky8linders/claude-cortex/claude-md/github.svg)](https://agentmods.dev/instructions/peaky8linders/claude-cortex/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/peaky8linders/claude-cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/peaky8linders/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/peaky8linders/claude-cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/peaky8linders/claude-cortex/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,122 This file is loaded in full into every session.

When invoked 1,122 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.

Model	Per session	Once invoked
Fable 5.1	$0.01122	$0.01122
Opus 5.5	$0.00449	$0.00449
Sonnet 5.5	$0.00224	$0.00224
Haiku 4.5	$0.00112	$0.00112

Measured 2mo ago against content hash a2e62f465da0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-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 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Commands

# Brainiac (Python — semantic graph engine)
pip install -e .                                    # Install in dev mode
cd ~/.claude/knowledge && python -m brainiac stats  # Graph overview
cd ~/.claude/knowledge && python -m brainiac search "query"

# Cortex (TypeScript — hook processor + MCP dashboard)
cd cortex && npm install && npm run build
cd cortex && npm test

# ContextScore (Python — analyzers + snapshot + HTTP API)
cd contextscore && pip install -e .
cd contextscore && pytest tests/ -v

Architecture

Product	Language	Purpose
`brainiac/`	Python	Semantic embedding engine, graph persistence, CLI
`cortex/`	TypeScript	Hook processor, knowledge graph engine, MCP dashboard server
`contextscore/`	Python	7 analyzers, snapshot/recovery, HTTP API

Plugin Structure

.claude-plugin/plugin.json       — Plugin manifest
.claude/settings.json            — Team permissions (committed)
.claude/rules/                   — Path-scoped instruction modules
.claude/commands/                — 14 slash commands (learn, hypothesis, cortex-*, ralph-*, etc.)
.claude/skills/cortex/           — Auto-invoked cortex advisor + support docs (SKILL.md, GRAPH_SCHEMA.md, QUALITY_DIMENSIONS.md)
.claude/agents/                  — cortex-advisor, graph-maintainer (haiku), work-evaluator (sonnet)
.mcp.json                        — MCP server registration (cortex-dashboard)
hooks/hooks.json                 — Hook wiring (5 events: SessionStart, PostToolUse, PreCompact, PostCompact, Stop)
hooks/scripts/                   — Shell hook handlers

MCP Dashboard Tools

cortex_token_timeline — Token consumption time-series with spike detection
cortex_activity_map — Gantt-like skill/hook/tool activation timeline
cortex_quality_heatmap — 7-dimension context quality radar
cortex_graph_explorer — Interactive knowledge graph
cortex_dashboard — Unified session dashboard with KPIs, charts, cost breakdown, and cross-session trends

Read the full file on GitHub · 106 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 · 106 lines · 1,122 tokens per session scan A a2e62f465da0

Subscribe to this mod's changes

claude-cortex CLAUDE.md is an instructions file published in the GitHub repository Peaky8linders/claude-cortex (11 stars, last pushed 4mo ago), licensed MIT. It adds 1,122 tokens to every session, about $0.0045 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.

claude-cortex CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-cortex CLAUDE.mdPeaky8linders/claude-cortex	Instructions file	11	4mo ago	MIT	A	1,122	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