Lightweight search across the project or neuroflow memory. Use a tag to scope the search — `memory` searches inside .neuroflow/ only, `project` searches the codebase outside .neuroflow/. Returns a fast summary of what was found.
From neuroflownpx claudepluginhub stanislavjiricek/neuroflow --plugin neuroflow/searchSearches issues by text query across title, description, and ID. Supports filters (--status, --label, --assignee, --type, etc.), sorting, limits, and JSON output.
/searchSearches Redpanda Connect components (inputs, outputs, processors, caches, rate-limits, buffers, metrics, tracers) matching the provided description.
/searchSearch AI experiments by query, tool, tag, rating, or date filters with sorting options and display formatted terminal results including stats.
/searchSearches pro-workflow learnings database using BM25 full-text search, returning top 10 ranked matches with category, mistake details, and application counts. Supports category and project filters.
/searchSearches your Notion workspace for pages, databases, and content matching the natural-language query, returning a scannable list with titles, types, descriptions, and clickable links.
/searchSearch Claude's persistent memories for content, patterns, or keywords via <query> [limit]. Returns matches with relevance scores, human-readable timestamps, and highlighted keywords.
Read the neuroflow:phase-search skill first. Then follow the neuroflow-core lifecycle: read project_config.md and flow.md if they exist.
Performs a lightweight, scoped search across either the project's neuroflow memory (.neuroflow/) or the broader project codebase. Uses flow.md files as a fast index to avoid reading every file. Returns a brief summary.
/search <tag>:<query>
Tags:
| Tag | Scope |
|---|---|
memory | Search inside .neuroflow/ only — plans, summaries, session logs, reasoning |
project | Search the project codebase outside .neuroflow/ — scripts, notebooks, results, config |
Examples:
/search memory:ICA artifact rejection
/search project:bandpass filter
/search memory:analysis plan
/search project:preprocessing pipeline
If no tag is supplied, default to memory and inform the user.
Extract the tag and query from the user's input:
<tag>:<query>, use the tag to determine scope and the rest as the search term.memory and tell the user: "No tag specified — searching memory. Use project: to search the codebase."If .neuroflow/ does not exist and the scope is memory, stop and tell the user to run /neuroflow first.
For project scope, .neuroflow/ is optional — proceed if the working directory contains any project files.
Follow the neuroflow:phase-search skill instructions exactly:
flow.md as the index firstPresent the compact result format defined in the phase-search skill:
🔍 Search: "<query>" [scope: memory | project]
Found in:
• <file-path> — <one-line reason why it matches>
Summary: <2–4 sentences>
Do not write anything to .neuroflow/ or anywhere else — this command is read-only.