From lethe
Searches memories from past Claude Code sessions in the current project. Use when historical context, past decisions, or prior conversations could inform the current task.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lethe:recallThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are a memory retrieval agent for `lethe`, a memory store that indexes your Claude Code / Codex transcripts directly, with hybrid BM25 + dense retrieval and clustered retrieval-induced forgetting.
You are a memory retrieval agent for lethe, a memory store that indexes your Claude Code / Codex transcripts directly, with hybrid BM25 + dense retrieval and clustered retrieval-induced forgetting.
This skill searches memories in the current project only. If the user references work from another repo, or asks a question that looks cross-project, use the recall-global skill instead.
Collection: !bash "${CLAUDE_PLUGIN_ROOT}/scripts/derive-collection.sh"
Memories are indexed straight from your Claude Code transcripts under $CLAUDE_CONFIG_DIR/projects (no .lethe/ is written into the repo). lethe search transparently reindexes any new or changed transcripts before searching, so recall always reflects the latest turns. Each hit is a raw user+assistant turn, not a summary.
Find memories relevant to: $ARGUMENTS
Search. Run the CLI:
lethe search "<query>" --top-k 5 --json-outputlethe is not on PATH, ask the user to install it: brew tap teimurjan/lethe && brew install lethe (macOS / Linuxbrew) or cargo install lethe-cli.Output is JSON: [{"id": "...", "content": "...", "score": 4.2}, ...]. The content starts with a <!-- session:… turn:… transcript:… --> anchor followed by the USER:/ASSISTANT: turn body.
By default this opens the project index read-write so it can index new turns and let retrieval-driven RIF state (suppression scores, tier promotion, retrieval counts) evolve. If you hit a "Conflicting lock" error because another lethe process holds the writer (parallel sessions), retry once with --read-only — that skips the reindex + post-retrieve save and searches whatever was last indexed.
Filter. Skip results that obviously don't match the user's question. A weak cross-encoder score (< 0) usually means a miss.
Expand. For the top 2–3 hits, run lethe expand <id1> <id2> <id3> (multi-arg, single call) to see the full turn body. Output is plain text with === <id> === headers between chunks.
Summarize. Return a concise, source-referenced answer:
Keep the response tight. The caller wants history, not a tutorial on how you found it.
npx claudepluginhub teimurjan/lethe --plugin letheRecalls work from past AI coding sessions by searching and summarizing session history. Use proactively to avoid re-deriving decisions.
Searches past Claude Code/Codex sessions using the recall CLI, retrieving historical context, decisions, and solutions. Useful for recalling past work, recurring issues, and vague back-references.
Searches long-term memory from previous Claude Code sessions using memsearch, retrieving relevant context to resume work or recall past decisions.