braina CLAUDE.md

A project guide for Braina, a framework that analyzes relationships in brain signals such as EEG, MEG, and fMRI data. It explains the project, its commands, dependencies, and verification tests in simple terms.

In plain words
What is it for?
Use it to understand Braina's structure, check its environment, run library tests, launch its MCP server, and run example analyses.
Why use it?
It gives the coding agent the context needed to work safely in an unfamiliar computational-neuroscience project. It also helps verify that the environment and core libraries work before changes are recommended.

Instructions file

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/brainets/braina/claude-md
Clone the repo
git clone --depth 1 https://github.com/brainets/braina
Per session 1,080 This file is loaded in full into every session.
When invoked 1,080 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 $0.01080 $0.01080
Opus 5 $0.00540 $0.00540
Sonnet 5 $0.00216 $0.00216
Haiku 4.5 $0.00108 $0.00108

Measured yesterday against content hash e91c67a28fd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

braina 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 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

Braina is an AI-agent-assisted framework for analyzing complex neural interactions using information-theoretical measures on electrophysiological data (fMRI, MEG, EEG, LFP, MUA). Built at the Institut de Neurosciences de la Timone (BraiNets), Marseille.

The user may be a novice in computational neuroscience. Explain mathematical concepts (entropy, mutual information, O-information, Granger causality) simply and verify all proposed code before recommending it.

Commands

# Verify environment (all core dependencies)
uv run check_env.py

# Run the verification test suite for Frites + HOI
uv run mcp/verify_libs.py

# Launch the MCP server standalone
uv run mcp/braina_mcp.py

# Run any example script (all use uv inline dependencies)
uv run examples/frites/conn/plot_covgc.py
uv run examples/hoi/metrics/plot_oinfo.py

All scripts use uv with PEP 723 inline script metadata (# /// script blocks) for dependency management — no virtualenv setup needed.

Architecture

MCP Server (mcp/braina_mcp.py)

The central integration layer. A FastMCP server exposing 30+ tools that wrap Frites and HOI library functions with standardized file-based I/O. Each tool takes file paths as input (.npy or .nc), calls the underlying library function, and saves results. This is registered as a Claude Code MCP server (braina).

load_data/save_data are internal I/O helpers (not exposed as MCP tools) that handle the .npy vs .nc dispatch for every tool.

Tool categories:

  • Data I/O: inspect_data, read_pdf
  • Frites connectivity: frites_conn_covgc, frites_conn_dfc, frites_conn_pid, frites_conn_ii, frites_conn_te, frites_conn_fit, frites_conn_spec, frites_conn_ccf
  • Frites workflows: frites_wf_stats (WfStats), frites_wf_mi (WfMi), frites_wf_conn_comod (WfConnComod)
  • Frites simulation: frites_sim_ar (StimSpecAR)
  • HOI metrics: hoi_oinfo, hoi_gradient_oinfo, hoi_infotopo, hoi_redundancy_mmi, hoi_synergy_mmi, hoi_rsi, hoi_dtc, hoi_get_nbest_mult

Read the full file on GitHub · 67 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 · 67 lines · 1,080 tokens per session scan A e91c67a28fd8

Subscribe to this mod's changes

braina CLAUDE.md is an instructions file published in the GitHub repository brainets/braina (5 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 1,080 tokens to every session, about $0.0054 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.

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 · 5,182 tokens

buildNext

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

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

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

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 · 7,040 tokens

langchain 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 · 4,345 tokens