From claude-rag
Browses past Claude sessions, projects, and events in RAG database via curl API. Lists recent sessions, details by ID with agent/event stats, or project searches.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-rag:browseThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Browse past sessions and events: "$ARGUMENTS"
Browse past sessions and events: "$ARGUMENTS"
Read the plugin config:
cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}'
Determine what the user wants to browse:
curl -s <endpoint>/api/v1/sessions?limit=10
Display as a table: | # | Session | Project | Events | Started | Show session IDs so the user can drill down.
curl -s <endpoint>/api/v1/sessions/<id>
Show:
Then:
curl -s "<endpoint>/api/v1/sessions/<id>/events?limit=20"
Show timeline of events with content previews.
curl -s <endpoint>/api/v1/projects
Find matching project, then list its sessions.
/claude-rag:browse <session-id> to see session details"/claude-rag:search <query> to search within results"npx claudepluginhub thisisyoyodev/claude-plugins --plugin claude-ragFetches recent session history from agentmemory and formats it as a reverse-chronological timeline with IDs, projects, times, status, highlights, observation counts, titles, and decisions. Useful for 'what did we do last time' or past work overviews.
Revives previous sessions from YAML squirrel logs and transcripts to reconstruct context. Browses recent activity across walnuts, filters by topic/person/timeframe, flags unsaved sessions.
Searches persistent cross-session memory database (claude-mem) to retrieve past work, decisions, and context. Use when user asks about prior sessions or solutions.