From hipocampus
Retrieves project memory for user queries via three-step fallback: ROOT.md topics triage, frontmatter manifest LLM selection from weekly/monthly notes, qmd search. Use when past knowledge may apply.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hipocampus:recallThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this when the user's question may relate to past memory. Three-step fallback: ROOT.md O(1) lookup → manifest LLM selection → qmd search.
Use this when the user's question may relate to past memory. Three-step fallback: ROOT.md O(1) lookup → manifest LLM selection → qmd search.
Check ROOT.md Topics Index for the query topic.
Decision rule: If Topics Index contains a keyword within 1 semantic hop of the query, it's a match. "배포" matches "deployment". "CI/CD" matches "github-actions".
Use this ONLY when ROOT.md Topics Index has no relevant match but you suspect memory may exist (e.g., the user references something that sounds familiar, or the topic is cross-domain).
Build manifest from compaction node frontmatter (NOT full content):
memory/weekly/*.md frontmatter only (type, period, topics)memory/monthly/*.md frontmatter only (type, period, topics)knowledge/*.md first 3 lines onlymemory/daily/ (already rolled up into weekly)Self-evaluate: Given the manifest and the user's query, select up to 5 most relevant files.
Load selected files in full and extract the answer.
Token budget: Manifest should be <500 tokens. If too large, use monthly nodes only.
If Step 1-2 don't find the answer and qmd is installed:
qmd query "keyword1 keyword2" # hybrid (BM25 + vector)
qmd search "keyword1 keyword2" # BM25 only
qmd vsearch "semantic query" # vector only
Use 2-4 specific keywords. Try variations if first query misses.
When recalling memory, check the source age:
project type + >30 days old: append warning — "이 정보는 {N}일 전 기록입니다. 현재 상태를 확인하세요."reference type + [?] marker: append warning — "이 참조는 검증되지 않았습니다. 접근 가능 여부를 확인하세요."user/feedback type: no age warning (these are durable).npx claudepluginhub kevin-hs-sohn/hipocampus --plugin hipocampusSearches Hipocampus memory using qmd (BM25 + optional vector) hybrid search and compaction tree traversal. Checks ROOT.md Topics Index before external lookups.
Recall facts from past sessions via memoir. STORE PATH: ALWAYS compute first via `STORE=$(bash "$CLAUDE_PLUGIN_ROOT/scripts/derive-store-path.sh")` (or `$MEMOIR_STORE`). Pass `-s "$STORE"` on every call — never rely on memoir's connected default (frequently stale). PROCEDURE (single-shot default): ONE `summarize --depth 3 -n default` → pick at most 5–7 keys → batch `get`. Only escalate to drill (batched `--keys`) if the depth-3 response shows `total_memories > 1000` AND the query is broad. Never call `summarize --depth 1` separately — `--depth 3` already returns count + full key listing. EXCLUDE `metrics.*` unless args contain `--include-metrics`. NEVER shell out to `memoir recall` (legacy LLM-bundled, slow, requires OPENAI_API_KEY). First reply line MUST be a mode marker `[mode=get|fast|drill|flat|blame|diff]`. DEFAULT ON: invoke for any question or task that may depend on past preferences, decisions, conventions, or knowledge — questions touching prior state, meta/overview asks, design/implementation prompts where output may reflect prior style, SessionStart hints, or any moment you'd otherwise silently apply remembered facts. SKIP only for mechanical single-symbol lookups, throwaway scratch work, or explicit user opt-out. Defer to memoir-onboard for repo-structure questions (it owns `codebase:onboard`). Cost of an unused recall is low; cost of missing a remembered preference is high.
Searches and retrieves memories from Cortex persistent memory using WRRF retrieval. Use for past decisions, patterns, bugs, or architecture context.