retrolisted

# Retro — LLM-driven Session Retrospection One efficient LLM pass over a session (or the stored memory backlog) detects **friction and reusable learnings**, classifies each into one of six destinations, and materializes approved ones. **Core principle:** No silent writes — every materialization needs explicit per-proposal approval. ## Modes Detail per mode, and the shared pipeline, in `references/workflow.md`. - **`/retro`** — Sweep: the whole current session. - **`/retro "<problem>"`** — Spotlight: one described issue. - **`/retro outcome [session-id|--since N]`** — replay a past session by what happened to its output afterward. - **`/retro audit [--scope project|repo|skill]`** — cross-session architectural drift. - **`/retro promote`** — inventory already-written local memory and re-home each note upward (never project-local memory); drain the source only after the upward write is verified. See `references/promote-mode.md`. - **Auto** — optional SessionEnd hook (`hooks/session-end.json`), off by default. ## Pipeline (all modes) 1. Mechanical pre-pass — `scripts/detect-mechanical.py` (Promote substitutes `scripts/scan-memory-inventory.py`). 2. LLM enrichment — inferential signals, both classes (friction + learnings B16–B18); filter false positives. 3. Cross-session enrichment (optional) — JSONL scan via `scripts/scan-cross-session.py`. 4. Discover skills — `scripts/find-org-skills.py` (installed + org catalogue). 5. Classify (`classification-heuristic.md