Brain and memory

The capabilities that feed the loop and act on it. Most run rarely and matter most: sync once a day, self-review once a month when sync offers it, seed export when a teammate needs an agent.

Capability	What it does	Skills and tools
Capture	Feed the brain anything: a thought, a file, a URL, the clipboard, a correction.	tools: capture
Compile	Raw sessions and captures become a structured wiki that loads next session.	knowledge-compile tools: compile_next, compile_write, knowledge_lint
Self-review	Monthly upkeep: stale tasks, memory and articles pruned with you, then feedback turned into changes to the agent’s own prompts.	self-review
Sync	One pass through every maintenance operation, ending in a status, any decisions due, and a next move.	sync tools: memory_prune, links_rewrite
Dashboard	The mission-control page regenerated from the home: today, tasks, projects, sessions, brain, reports.	dashboard tools: dashboard, report_write
Seed bundles	An agent’s persona and setup exported as a zip; a teammate’s fresh home imports it.	seed tools: seed_scan, seed_export, seed_import
Diagrams and prose	Mermaid validated before it ships; AI tells stripped from any text.	mermaid humanizer
Onboarding	A guided first run, a rename across the home, packs and custom skills configured.	init rename-agent configure-skills tools: codex_setup

The loop, as skills

1. Hooks capture every session; capture takes anything else: a thought, a file, a URL, a correction.
2. knowledge-compile distils raw capture into the wiki; sync runs it with every other maintenance pass.
3. self-review prunes what has gone stale in the brain with you, then turns the accumulated feedback into changes to the agent's own prompts.
4. dashboard renders the result as one page.