learnlisted

# Learn Teach the agent a new fact or behavioral preference. Writes immediately to memory/ — no batch processing. ## One-File-Per-Concept Rule If the user provides multiple facts in one /learn call, create separate files for each concept. Do not combine multiple facts into one file. **Why:** Memory files are the unit of deprecation. If fact A becomes outdated but B stays valid, a combined file forces you to either keep stale A or discard still-valid B. Separate files let each fact be independently deprecated or superseded. ## Active Projects Intent Detection Write to `MEMORY.md ## Active Projects` ONLY when the user message explicitly references a project lifecycle event. Triggers Active Projects update (write to MEMORY.md): - "starting project X", "project Y is done", "adding project Z", "updating status of project A" Does NOT trigger (write to memory/ file instead): - "in project X we use Y", "I worked on project X before" When unclear → AskUserQuestion: "Add to Active Projects in MEMORY.md, or create a memory file?" Options: `active-projects / memory-file` ## Contradiction Detection Before writing a new file, grep `memory/` for files with overlapping topics or similar content. Scan ONLY files with `status: active` or `status: needs-review` — skip deprecated files. **Why:** Deprecated files are intentionally retired. Re-surfacing them as conflicts would create ghost conversations about facts the user has already decided to discard. If a potential conflict is fo