recalllisted
Install: claude install-skill Smart-AI-Memory/attune-ai
# Recall
**IMPORTANT: Start your response by telling the user:**
> **Recall** — Searching cross-session memory for findings related to
> your query.
## What It Does
`/recall` is the on-demand companion to the automatic SessionStart
recall. It searches TWO stores and labels results by source:
1. **Session findings** — stashed by the Stop hook across past
sessions (file backend by default; Redis AMS when connected).
2. **The lessons corpus** — the repo's accumulated engineering
lessons, retrieved via `attune.lessons.LessonsIndex` (query mode
only; lessons have no recency, so the no-query mode skips them).
- **With a query** (`/recall AMS event loop`): both stores; session
findings keyword + recency ranked, lessons by retrieval score.
- **No query** (`/recall`): the most recent session findings for
this project.
## Pick Your Transport First
Route by what YOUR client can actually do — never assume the
universal Python recipe works everywhere (in a sandboxed provider
it selects an unwritable file tier or a blocked socket):
1. **MCP available** — the `session_memory_*` tools appear in your
tool list (Codex, Claude Code with the attune MCP server, any
MCP client): use them. They execute host-side, outside your
sandbox, and carry the full contract (sanitization, cwd scoping,
TTL). **Never run in-process Python for memory from a sandboxed
client, and never substitute raw `redis_memory_store` for
finding capture — capture goes through `session_me