ccc-memorylisted

# /ccc-memory — Two-Tier Persistent Memory Claude Code sessions forget everything at the end. Memory makes the important bits stick. ## When to use - After resolving a tricky bug — save the root cause so next time the same class of issue is faster - After making an architectural decision — record the reasoning so future-you doesn't re-argue with past-you - When a project grows beyond one CLAUDE.md section — split into a memory/ tree - Before a big /clear when you want to carry forward a specific insight ## Not for - Session-scoped state that ends with this session — use /ccc-save-session for that - Searchable cross-project knowledge — use /ccc-recall for that - Per-skill notes — put those inline in the skill's body ## How it works Two layers, different load patterns: ### Layer 1 — CLAUDE.md (always-loaded) Every file Claude reads in a session is relative to CLAUDE.md. Put here: - Project type + tech stack (once) - Key paths + conventions - Commands Kevin runs daily - Cross-cutting style rules Keep it tight — everything here costs context on every turn. ### Layer 2 — memory/ directory (on-demand) Dated markdown files for things that don't belong in the always-loaded layer: - `memory/YYYY-MM-DD-{slug}.md` — daily learnings, decisions, corrections - `memory/decisions/` — one file per big call (why we picked Postgres over Mongo) - `memory/gotchas/` — known footguns (tailwind v4 syntax, framer-motion v11 rename) - `memory/preferences.md` — curated long-term prefs that