Reflect Memory

Compounding has a failure mode: unbounded growth. Rules pile up, duplicate each other, go stale, and start contradicting — and every one of them is loaded into context on every session. This skill is the garbage collector and compactor for the memory reflect builds.

Surfaces

Work over, in order of impact:

1. The project's AGENTS.md / CLAUDE.md (agent-rule sections).
2. .reflect/observations.md and .reflect/applied.md.
3. Skill descriptions and command files reflect maintains (per the ledger).
4. ~/.reflect/ when run outside a project or when asked.

Only restructure freely inside .reflect/. For instruction files, apply safe mechanical fixes directly (exact duplicates, dead references) and propose everything judgment-shaped.