local-brain CLAUDE.md

local-brain CLAUDE.md is an instructions file for coding agents from SanderMoon/local-brain. It costs 1,901 tokens per session, scanned A, original, MIT.

Project instructions for Local Brain, a local-first command-line project manager that stores workspaces, notes, and tasks in plain Markdown files.

In plain words
What is it for?
Use them when changing Local Brain to understand brains, projects, the task inbox, repository links, build commands, and test commands.
Why use it?
They give coding agents the project’s structure and the commands needed to build and test it consistently.

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/sandermoon/local-brain/claude-md
Clone the repo
git clone --depth 1 https://github.com/SanderMoon/local-brain

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.

agentmods badge for local-brain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandermoon/local-brain/claude-md.svg)](https://agentmods.dev/instructions/sandermoon/local-brain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sandermoon/local-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/sandermoon/local-brain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,901 This file is loaded in full into every session.
When invoked 1,901 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 $0.01901 $0.01901
Opus 5 $0.00950 $0.00950
Sonnet 5 $0.00380 $0.00380
Haiku 4.5 $0.00190 $0.00190

Measured 3d ago against content hash b0676e998780, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

local-brain 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 3d 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 · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 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

Local Brain is a minimalist, local-first project management CLI tool for developers. It manages Brains (high-level workspaces) and Projects (specific focus areas within a Brain), providing context management for notes, tasks, and code repositories.

Key Concepts:

  • Brains: Top-level workspaces (e.g., "Work", "Personal"). Only one brain is active at a time, symlinked to ~/brain
  • Projects: Focus areas within a brain. Each has notes.md, todo.md, and optional git repo links
  • Dump: Quick capture inbox (00_dump.md) for tasks/notes that get refiled to projects
  • Local-first: Plain text Markdown files, grep-able, version-controllable

Build & Test Commands

Building

make build              # Build binary to ./brain
make dev-install        # Install to ~/.local/bin
make install            # Install to /usr/local/bin (system-wide)

Testing

make test               # Fast unit tests only (default)
make test-all           # All tests including integration
make test-unit          # Unit tests only
make test-integration   # Integration tests only
make test-cover         # Generate coverage report (coverage.html)
make test-race          # Run with race detection

# Run single test
go test -v ./pkg/api -run TestGenerateItemID
go test -v ./pkg/config -run TestLoadConfig

Code Quality

make fmt                # Format code
make vet                # Run go vet
make lint               # Run golangci-lint (if installed)
make check              # Run all checks (fmt, vet, test)

Release

make snapshot           # Test release build without tags (artifacts in dist/)
make release            # Create production release (requires git tag)

Architecture

Package Structure

cmd/ - Cobra CLI commands (19 commands)

  • Each command in separate file (e.g., add.go, project.go, todo.go)
  • All register with rootCmd in their init() functions
  • root.go defines base command and version handling

Read the full file on GitHub · 201 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. 3d ago First seen · 201 lines · 1,901 tokens per session scan A b0676e998780

Subscribe to this mod's changes

local-brain CLAUDE.md is an instructions file published in the GitHub repository SanderMoon/local-brain (9 stars, last pushed 5mo ago), licensed MIT. It adds 1,901 tokens to every session, about $0.0095 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