recalllisted

# recall Single-shot RAG lookup. Don't over-fetch. **Mount guard:** `[ -d "${DEV_ROOT}/rag-index" ] || echo WARNING: RAG degraded` - directory reachability, not `mount` output parsing (matches the canonical guard in `claude/skills/knowledge-loop/references/mount-guard.sh`: `mount` only lists actual mount points, never nested paths, so grepping its output false-positives as "unmounted" even when the drive is present; it also escapes spaces in mount-point paths on Linux, which a naive grep won't decode). The index lives on the external drive; an unmounted drive silently degrades recall. See `standards/knowledge-brain.md §1`. ## How Call the MCP tool directly: ``` rag_query(query="<natural-language question>", top=5) ``` **Done when:** top results answer your question in 1–2 chunks. If not, narrow the query or increase `top` (up to 8). Optional args: - `top` (1–20, default 5) — more isn't always better; reranker quality drops past 8. - `scope_types` — narrow to e.g. `["memory", "handoffs"]` for "what did I write down" queries, or `["commit"]` for "what did we ship lately on X". - `scope_repos` — pass `["all"]` to ignore cwd auto-scope; pass `["<project-a>"]` etc. to force a specific repo. ## Failure modes - **Unmounted external drive** — if the drive drops mid-session, the RAG index becomes stale or inaccessible. Mount guard (above) catches this; surface "WARNING: RAG degraded" and skip the query or fall back to grep. - **Stale index** — if memory or code changed recent