How this command is triggered — by the user, by Claude, or both
Slash command
/context-memory:recall <query> [--project] [--detailed] [--limit N] [--format json|markdown]The summary Claude sees in its command listing — used to decide when to auto-load this command
# /recall Command Search past sessions stored in context memory. ## Usage **Arguments:** - `query` (required): Search terms to find relevant sessions **Options:** - `--project`: Limit search to current project only - `--detailed`: Include full message content and code snippets - `--limit N`: Maximum number of results (default: 10) - `--format`: Output format: `json` or `markdown` (default: markdown) ## Examples ## Workflow When the user runs `/recall`: 1. **Parse Query and Options** Extract the search query and any flags: - `--project` -> filter by current project path ...
Search past sessions stored in context memory.
/recall <query> [options]
Arguments:
query (required): Search terms to find relevant sessionsOptions:
--project: Limit search to current project only--detailed: Include full message content and code snippets--limit N: Maximum number of results (default: 10)--format: Output format: json or markdown (default: markdown)/recall authentication
/recall "database migration" --project
/recall jwt --detailed --limit 5
/recall "error handling" --project --detailed
When the user runs /recall:
Parse Query and Options
Extract the search query and any flags:
--project -> filter by current project path--detailed -> include tier 2 content--limit N -> cap resultsExecute Search
Run the search script:
python "~/.claude/skills/context-memory/scripts/db_search.py" "<query>" [--project "$(pwd)"] [--detailed] [--limit N] --format markdown
Present Results
Display results in a clear, scannable format:
# Context Memory Results
**Query**: "authentication"
**Results**: 3 sessions
---
## 1. 2026-01-15 | my-app (Match #1)
**Summary**: Implemented JWT auth with refresh token rotation
**Topics**: authentication, JWT, security, Node.js
**Decisions**:
- Use RS256 for token signing
- 15-minute access token expiry
<details><summary>Full Context</summary>
[Detailed content when --detailed flag is used]
</details>
Offer Follow-up Actions
If results are helpful, offer to:
If results are insufficient:
--project filterThe search uses FTS5 full-text search with Porter stemming:
Good search queries:
authentication - Find auth-related sessionsreact hooks - Find React or hooks sessionsdatabase migration - Find database or migration sessionsbug fix error - Find debugging sessionsShows brief summaries, topics, and key decisions. Fast overview of matching sessions.
--detailed)Includes:
Use --detailed when you need to deeply understand a past session or reference specific code.
If no sessions match the query:
# Context Memory Results
**Query**: "quantum computing"
**Results**: 0 sessions
No matching sessions found.
Try:
- Using broader search terms
- Removing the --project filter
- Checking related topics
~/.claude/context-memory/context.dbnpx claudepluginhub elishakay/context-memory2plugins reuse this command
First indexed Mar 9, 2026
/search-sessionsSearches past Claude Code and OpenClaw sessions by metadata or full message content, returning session UUIDs for resuming.
/recallSearches session history logs by concept keyword, returning matching sessions with relevant bullets and decisions. Results sorted newest-first with deduplication.
/search-historianSearches past Claude Code conversations for relevant context, returning up to 5 matching sessions.
/search-conversationsSearches past conversations using semantic or text search, synthesizes findings from top results, and returns a concise summary with source pointers.
/searchSearches context-mem observations using BM25 full-text search, returning type-badged snippets of matching entries.
/recallRecovers context from recent conversation history — browse sessions, search exchanges, manage tags, export or prune logs, and view usage stats.