Help us improve
Share bugs, ideas, or general feedback.
From vexor
Locates files semantically via vexor CLI in medium/large repos to find implementations, loaders, or definitions when locations are unclear.
npx claudepluginhub scarletkc/vexor --plugin vexorHow this skill is triggered — by the user, by Claude, or both
Slash command
/vexor:vexor-cliThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Find files by intent (what they do), not exact text.
Discovers files semantically via vexor CLI in medium/large repos. Locates implementations, loaders, definitions, or docs by intent, faster than grep or manual browsing.
Semantic codebase search — use for exploring code, finding implementations, and answering questions about any project. Searches using natural language queries, identifier names, or file paths. Returns ranked results using embedding-based similarity, BM25 keyword matching, symbol matching, import graph analysis, and git recency. Use this as the default exploration tool instead of grep when you don't know the exact text to search for.
Searches codebases semantically with natural language queries to find implementations by concept (e.g., 'where is X', 'how does Y work'). Returns file paths, lines, and snippets.
Share bugs, ideas, or general feedback.
Find files by intent (what they do), not exact text.
vexor first for intent-based file discovery.vexor is missing, follow references/install-vexor.md.vexor "<QUERY>" [--path <ROOT>] [--mode <MODE>] [--ext .py,.md] [--exclude-pattern <PATTERN>] [--top 5] [--format rich|porcelain|porcelain-z]
--path/-p: root directory (default: current dir)--mode/-m: indexing/search strategy--ext/-e: limit file extensions (e.g., .py,.md)--exclude-pattern: exclude paths by gitignore-style pattern (repeatable; .js → **/*.js)--top/-k: number of results--include-hidden: include dotfiles--no-respect-gitignore: include ignored files--no-recursive: only the top directory--format: rich (default) or porcelain/porcelain-z for scripts--no-cache: in-memory only, do not read/write index cacheauto: routes by file type (default)name: filename-only (fastest)head: first lines only (fast)brief: keyword summary (good for PRDs)code: code-aware chunking for .py/.js/.ts (best default for codebases)outline: Markdown headings/sections (best for docs)full: chunk full file contents (slowest, highest recall)--include-hidden and/or --no-respect-gitignore.--format porcelain (TSV) or --format porcelain-z (NUL-delimited).vexor search --help.vexor doctor or vexor config --show diagnoses API, cache, and connectivity (tell the user to set up).# Find CLI entrypoints / commands
vexor search "typer app commands" --top 5
# Search docs by headings/sections
vexor search "user authentication flow" --path docs --mode outline --ext .md --format porcelain
# Locate config loading/validation logic
vexor search "config loader" --path . --mode code --ext .py
# Exclude tests and JavaScript files
vexor search "config loader" --path . --exclude-pattern tests/** --exclude-pattern .js
--ext with --exclude-pattern to focus on a subset (exclude rules apply on top).