nano-brain

Persistent memory + code intelligence for AI coding agents. Hybrid search (BM25 + vector + RRF + recency), cross-session recall, symbol analysis, impact checks, knowledge graph, OpenCode/Claude Code session harvesting. Use this skill when you need to recall prior decisions across sessions, search across multiple codebases, trace symbol callers/callees, analyze code impact (what breaks if X changes), persist long-term context, or query the knowledge graph. Triggers — "remember what we did about X", "search across sessions", "find references to X", "what breaks if I change Y", "save this decision", "wake-up briefing".

Persistent memory + code intelligence for AI coding agents. Hybrid search (BM25 + vector + RRF), cross-session recall, symbol graph analysis, impact checks, OpenCode/Claude Code session harvesting. Use when you need to recall prior decisions, search across sessions/codebase, trace symbol callers/callees, or persist long-term context.

MANDATORY for any non-trivial feature planning. Multi-agent pipeline: Metis (scope/risk) + Oracle (architecture) in parallel → cross-critique → confidence-scored synthesis → early Momus sanity check → OpenSpec proposal → full Momus review. MUST USE when: user describes a feature that touches multiple services or modules, user wants to plan/design/architect before coding, user says 'plan this', 'design this', 'think this through', 'spec this out', 'deep design', 'let me get this right', 'before we start coding', 'rethink how X works', 'migrate from X to Y', 'add multi-tenancy/billing/auth/permissions/real-time/encryption/caching', user describes any system that needs architectural decisions, user mentions wanting a proposal or spec, user wants to avoid mistakes on a complex feature. Also triggers on: 'plan out the migration', 'design a system for', 'I want to add [complex feature]... need to think through', 'this is a big change', 'let me get the design reviewed', 'before anyone writes code'. When in doubt abo