Super Save

Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.

Token-effizientes persistent Memory-System für Claude Code, das ca. 67 % der Tokens beim Aufwärmen der Sitzung spart (verifiziert mit tiktoken). Schichtweise Architektur mit progressiver Ladung, kompakter Kodierung, Branch-fähigem Kontext, intelligenter Komprimierung, Sitzungsdifferenzierung, Konflikterkennung, Sitzungsfortsetzungsprotokoll und Wiederherstellungsmodus. Aktiviert beim Start der Sitzung (falls MEMORY.md existiert), bei "remember this", "pick up where we left off", "what were we doing", "wrap up", "save progress", "don't forget", "switch context", "hand off", "memory health", "save state", "continue where I left off", "context budget", "how much context left", oder jedem Sitzungsstart bei einem Projekt mit vorhandenen Speicherdateien. Diese Fähigkeit löst zwei Probleme gleichzeitig: Claude vergisst alles zwischen den Sitzungen UND Sitzungen erreichen zu schnell die Kontextgrenzen. Sie ersetzt Tausende von verschwendeten Erklärtokens durch eine kompakte, strukturierte Speicherladung, die Claude vollen Projektkontext in unter 2.000 Tokens gibt.

AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.

Store a global memory that is visible across all projects. Use when the user shares architecture rules, coding conventions, infrastructure facts, security policies, team agreements, or any knowledge that applies beyond a single project. Triggers on 'remember this everywhere', 'this applies to all projects', 'global rule', 'shared convention', 'infrastructure note', 'cross-project', or when the content is clearly universal (clean architecture, SOLID, deployment configs, server addresses).

Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.