brain.md
NewA persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.
Summary
md provides a persistent, file-based memory layer for coding agents like Claude Code and Codex, enabling them to store and recall durable decisions, requirements, and constraints across sessions.
- It uses a zero-dependency CLI to manage a project brain, ensuring context is never lost and agents stay aligned with project goals.
Install & Usage
mkdir -p .claude/skillsAdd the configuration to .claude/skills/brain-md.md
/brain-mdUse Cases
Usage Examples
/brain-md add 'Use React hooks for all state management' to record a design decision.
/brain-md read to load the current project brain before starting a new task.
Update the brain with the constraint 'Database queries must use parameterized inputs' and ask Claude Code to review existing code.
Security Audits
Frequently Asked Questions
What is brain.md?
brain.md provides a persistent, file-based memory layer for coding agents like Claude Code and Codex, enabling them to store and recall durable decisions, requirements, and constraints across sessions. It uses a zero-dependency CLI to manage a project brain, ensuring context is never lost and agents stay aligned with project goals.
How to install brain.md?
To install brain.md: create the skills directory (mkdir -p .claude/skills), then add the config to .claude/skills/brain-md.md. Finally, /brain-md in Claude Code.
What is brain.md best for?
brain.md is a other categorized under General. It is designed for: agent. Created by mindmuxai.
What can I use brain.md for?
brain.md is useful for: Store and retrieve project-wide design decisions so coding agents consistently apply the same architecture choices.; Maintain a living document of requirements and constraints that agents reference before generating code.; Track resolved bugs and their fixes to prevent agents from repeating the same mistakes.; Record API contracts and integration rules for agents to follow when building new features.; Document coding standards and style preferences that agents enforce automatically.; Capture user feedback and change requests as a persistent backlog for agents to prioritize..