From mnemonic
Searches mnemonic memory files by namespace, tag, type, date, title, confidence, or full-text using ripgrep and find, with progressive disclosure and optional semantic search via qmd.
npx claudepluginhub zircote/mnemonicThis skill is limited to using the following tools:
<!-- BEGIN MNEMONIC PROTOCOL -->
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Analyzes BMad project state from catalog CSV, configs, artifacts, and query to recommend next skills or answer questions. Useful for help requests, 'what next', or starting BMad.
Search first: /mnemonic:search {relevant_keywords}
Capture after: /mnemonic:capture {namespace} "{title}"
Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.
Search and filtering for mnemonic memories.
rg "^namespace: _semantic/decisions" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
# Single tag
rg -l "^ - architecture" ${MNEMONIC_ROOT}/ --glob "*.memory.md"
# Multiple tags (AND)
rg -l "^ - architecture" ${MNEMONIC_ROOT}/ --glob "*.memory.md" | xargs rg -l "^ - database"
rg "^type: semantic" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
rg "^type: episodic" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
rg "^type: procedural" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
rg "^created: 2026-01" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
rg -i '^title: ".*auth.*"' ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
rg "confidence: 0\.9" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
rg -i "search term" ${MNEMONIC_ROOT}/ --glob "*.memory.md"
rg "database" ${MNEMONIC_ROOT} --path "*/_semantic/decisions/" --glob "*.memory.md"
find ${MNEMONIC_ROOT} -name "*.memory.md" -mtime -7
Always start at Level 1. Expand only if needed.
| Level | What | How |
|---|---|---|
| 1 (start here) | Titles only | rg -l "pattern" ${MNEMONIC_ROOT}/ --glob "*.memory.md" then extract ^title: |
| 2 | Frontmatter + summary | Read first ~50 lines of matched files |
| 3 | Full detail | Read entire memory file |
If @tobilu/qmd is installed (see /mnemonic:qmd-setup):
# BM25 keyword search (ranked)
qmd search "authentication middleware" -n 10
# Semantic vector search (meaning-based)
qmd vsearch "how do we handle user sessions" -n 10
# Hybrid search (BM25 + vector combined)
qmd query "authentication patterns" -n 10
# Scope to collection
qmd search "auth" -c mnemonic-zircote
| Tool | Best For | Requires |
|---|---|---|
rg | Exact strings, regex, frontmatter fields | Nothing |
qmd search | Ranked keyword search, typo-tolerant | qmd update |
qmd vsearch | Conceptual/meaning-based queries | qmd embed |
qmd query | Best overall recall, combines both | Both |
After adding memories, run /mnemonic:qmd-reindex to update indexes.
For complex or multi-faceted queries:
mnemonic-search-subcall agent)Use when queries span multiple namespaces or need comprehensive coverage.
## Synthesized Answer
{Answer drawing from all found memories}
### Sources
| Memory | Namespace | Relevance |
|--------|-----------|-----------|
| [[memory-id]] title | namespace | High/Medium |
### Gaps
- {Topics where no memories were found}