docwilde

docwilde/LORE

Plugin Claude Code

Plugin marketplace listing 1 plugin: lore.

docwilde/LORE

Plugin Claude Code

Memory for Claude Code that reasons about you and improves itself: Honcho-pattern belief store with deriver, dreamer and dialectic (/lore:ask), automatic skillification with a closed judge/update/retire loop, on a Hermes-pattern core — hard-capped curated memory, FTS5 session search, staged review.

docwilde/LORE

Command

Approve staged lore proposals (ids or "all").

docwilde/LORE

Command

Ask the lore belief store a question (dialectic — synthesized, cited answer).

docwilde/LORE

Command

Full-transcript backfill — page every message of a session (or all sessions of a project) through the deriver, not just the newest window.

docwilde/LORE

Command

View and toggle LORE stages (inject, index, review, beliefs, skills, streaming).

docwilde/LORE

Command

Show exactly what lore holds in context right now — user + project memory as tables, interaction model, belief count.

docwilde/LORE

Command

Diagnose lore — environment checks, effective config, memory/index state. Read-only.

docwilde/LORE

Command

Project file map — where the load-bearing files live (show the table, or add an entry).

docwilde/LORE

Command

Belief graph — backfill the edges the store implies, then inspect or draw it.

docwilde/LORE

Command

One-screen reference card for all lore commands and the memory model.

docwilde/LORE

Command

Delta view — what changed in lore since you last looked (new beliefs, pending count).

docwilde/LORE

Command

List lore's staged memory/skill proposals from background review.

docwilde/LORE

Command

Reject staged lore proposals (ids or "all").

docwilde/LORE

Command

Store a fact in lore memory (decides user vs project scope).

docwilde/LORE

Command

Trigger lore background review of the current session now (TUI-visible task).

docwilde/LORE

Command

Get lore working — run doctor, then fix each finding behind its own gate.

docwilde/LORE

Command

Lore memory usage, session index and pending counts.

docwilde/LORE

Hook

Runs when a session starts on startup, resume, clear and compact, executing lore.py via python3. From docwilde/LORE.

docwilde/LORE

Hook

Runs when you submit a prompt, before the agent sees it, executing lore.py via python3 with --live (2 commands). From docwilde/LORE.

docwilde/LORE

Hook

Runs before the context is compacted, executing lore.py via python3. From docwilde/LORE.

docwilde/LORE

Hook

Runs when a session ends, executing lore.py via python3. From docwilde/LORE.

docwilde/LORE

Skill Claude CodeCodex

Maintain and recall persistent memory (Hermes-pattern). Use when the user says "remember this", asks what you know about them or the project, when you learn a durable preference/environment fact/workaround/correction worth keeping, or when a problem feels like it was solved in an earlier session and past transcripts…