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.
npx claudepluginhub kevin-hs-sohn/hipocampus --plugin hipocampusThis skill uses the workspace's default tool permissions.
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.
Searches Hipocampus memory using qmd (BM25 + optional vector) hybrid search and compaction tree traversal. Checks ROOT.md Topics Index before external lookups.
Queries memory files (decisions.md, preferences.md, lessons.md, etc.) via routing table with keyword, attribution/date/file filters, deep traversal, and context-first recall before agent dispatch.
PROACTIVELY query Forgetful MCP (mcp__forgetful__* tools) when starting work on any project, when user references past decisions or patterns, when implementing features that may have been solved before, or when needing context about preferences. Save important decisions, patterns, and architectural insights to memory.
Share bugs, ideas, or general feedback.
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).