/wrap — Session Wrap

Close out a working session by writing what was decided, shipped, and learned into the right file, so the next session doesn't start cold.

An agent's output is cheap; its amnesia is expensive. Every session that ends without a wrap is a session your setup partly forgets — the workaround gets rediscovered next week, the decision gets relitigated next month. Memory discipline compounds; generation does not.

The Four Layers

Memory is layered. /wrap updates all four:

WORKBENCH.md (volatile) — current state, blockers, recent decisions, next steps. One per project, at the project root. Create it if a project deserves one and doesn't have it.
CLAUDE.md (evergreen) — who/what/why, where things live. Updated only when a decision changes a durable fact (tech stack, file location, people, rules).
Skills (.claude/skills/<skill>/) — capabilities the agent reuses across sessions. Bug fixes, new patterns, scope clarifications, and reusable scripts surfaced this session belong here.
Persistent memory (your agent's cross-session memory directory) — learnings that apply beyond one project AND don't fit cleanly inside any single skill. Keep an index file with one line per memory.

Don't write duplicates across layers. The routing decision tree: