approve
01Command
Approve staged lore proposals (ids or "all").
Trustworthy memory for Claude Code — everything that steers the agent is either human-approved or outcome-calibrated. Beliefs, calibration ledger, learned skills, act-time consult.
Command
Approve staged lore proposals (ids or "all").
Command
Ask the lore belief store a question (dialectic — synthesized, cited answer).
Command
Full-transcript backfill — page every message of a session (or all sessions of a project) through the deriver, not just the newest window.
Command
View and toggle LORE stages (inject, index, review, beliefs, skills, streaming).
Command
Show exactly what lore holds in context right now — user + project memory as tables, interaction model, belief count.
Command
Diagnose lore — environment checks, effective config, memory/index state. Read-only.
Command
Project file map — where the load-bearing files live (show the table, or add an entry).
Command
Belief graph — backfill the edges the store implies, then inspect or draw it.
Command
One-screen reference card for all lore commands and the memory model.
Command
Delta view — what changed in lore since you last looked (new beliefs, pending count).
Command
List lore's staged memory/skill proposals from background review.
Command
Reject staged lore proposals (ids or "all").
Command
Store a fact in lore memory (decides user vs project scope).
Command
Trigger lore background review of the current session now (TUI-visible task).
Command
Get lore working — run doctor, then fix each finding behind its own gate.
Command
Lore memory usage, session index and pending counts.