brain:export

Generate a structured CLAUDE.local context from a brain SQLite database.

264|11|Updated Apr 25, 2026
One-click install
npx skills add https://github.com/rkz91/coco --skill brain-export
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: brain:export
Source: https://github.com/rkz91/coco/tree/main/systems/brain/skills/brain-export
Command: npx skills add https://github.com/rkz91/coco --skill brain-export

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Auto-generates and refreshes the CLAUDE.local.md auto-generated context from the brain SQLite DB, while preserving manual behavior rules above and below the sentinels.

Core Features & Use Cases

  • Auto-generate the auto-generated context block from brain DB including key people, systems, decisions, and project status.
  • Preserve manually written content around the auto-generated section to maintain intentional edits.
  • Write changes atomically to CLAUDE.local.md to avoid partial updates and ensure consistency.

Quick Start

Run the brain export command to refresh CLAUDE.local.md for your project.

Frequently Asked Questions about brain:export

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I auto-generate a CLAUDE.local.md file from a SQLite database?

To auto-generate CLAUDE.local.md from a SQLite database, this workflow reads your brain DB, regenerates the auto-generated context block into a compact ~1,200-token narrative, and writes the output atomically to the file.

How do I refresh project context in markdown without overwriting my manual edits?

Refreshing project context without losing manual edits works by preserving content above and below sentinel markers, regenerating only the auto-generated block to keep your intentional edits safe during file updates.

Does generating context for Claude require a specific database format?

Generating context for Claude requires a project brain SQLite database, reading key people, systems, decisions, and project status from the DB to synthesize the structured markdown narrative.

What is the best way to keep a markdown context file synced with a brain database?

The best way to keep markdown context synced with a brain database is running an automated export workflow that reads the DB and atomically writes changes to CLAUDE.local.md, ensuring consistency and avoiding partial updates.

Are there limitations to the token size when exporting context to a markdown file?

Exporting context to a markdown file has a limitation of approximately 1,200 tokens for the auto-generated narrative section, requiring your brain database content to fit within this compact output constraint.