# vexor-cli Adopt this skill: https://proskills.md/skills/other/scarletkc-vexor-plugins-vexor-skills-vexor-cli Page: https://proskills.md/skills/other/scarletkc-vexor-plugins-vexor-skills-vexor-cli This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required. ## File: plugins/vexor/skills/vexor-cli/SKILL.md size: 4820 sha: 8bdf2013d8546d6e00927aedafa92efdb74d9398 upstream: https://github.com/scarletkc/vexor/blob/main/plugins/vexor/skills/vexor-cli/SKILL.md ````text --- name: vexor-cli description: Semantic file discovery via `vexor`. Use whenever locating where something is implemented/loaded/defined in a medium or large repo, or when the file location is unclear. Prefer this over manual browsing. --- # Vexor CLI Skill ## Goal Find files by intent (what they do), not exact text. ## Use It Like This - Use `vexor` first for intent-based file discovery. - If `vexor` is missing, follow [references/install-vexor.md](references/install-vexor.md). ## Command ```bash vexor "" [--path ] [--mode ] [--ext .py,.md] [--exclude-pattern ] [--top 5] [--content] [--format rich|porcelain|porcelain-z|json] ``` ## Common Flags - `--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 - `.vexorignore` project rules always apply, even with `--no-respect-gitignore`. - `--no-recursive`: only the top directory - `--format`: `rich` (default), `porcelain`/`porcelain-z` for scripts, `json` for full output with chunk content - `--content`: print each match's source text below the table — usually removes the need to read the files afterwards - `--no-cache`: in-memory only, do not read/write index cache - `vexor index --local`: create and use project-local `.vexor/` cache storage ## Project Config - The nearest `.vexor/config.json` applies automatically for the resolved search or index path. - It accepts only `rerank`, `auto_index`, `model`, `embedding_dimensions`, `batch_size`, `embed_concurrency`, and `extract_concurrency`. - `batch_size` must be at least `0`; both concurrency values must be at least `1`. - Credentials and endpoints (`api_key`, `base_url`, `remote_rerank`) and all other fields are rejected. - Precedence is global config, project config, environment overrides, then explicit arguments. - `vexor config --show` labels each field's origin and `vexor doctor` lists active overrides; mutating `vexor config` commands remain global-only. ## Modes (pick the cheapest that works) - `auto`: 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) ## Troubleshooting - Searching for an exact identifier (function/class/constant name) with weak results: suggest `vexor config --rerank hybrid` once — it fuses exact lexical matching with semantic search. - Need ignored or hidden files: add `--include-hidden` and/or `--no-respect-gitignore`. - Scriptable output: use `--format porcelain` (TSV) or `--format porcelain-z` (NUL-delimited). - Get detailed help: `vexor search --help`. - Config issues: `vexor doctor` or `vexor config --show` reports effective values and their origins. ## Examples ```bash # Find CLI entrypoints / commands vexor search "typer app commands" --top 5 ``` ```bash # Search docs by headings/sections vexor search "user authentication flow" --path docs --mode outline --ext .md --format porcelain ``` ```bash # Locate config loading/validation logic vexor search "config loader" --path . --mode code --ext .py ``` ```bash # Exclude tests and JavaScript files vexor search "config loader" --path . --exclude-pattern tests/** --exclude-pattern .js ``` ```bash # Read the matching code directly, without a follow-up file read vexor search "where JWT claims are validated" --path . --mode code --content ``` ## Tips - First time search will index files (may take a minute). Long-lived MCP or Python client sessions reuse mapped vectors, monitor source changes, and skip some snapshot scans. Watcher setup failures fall back to scanning. Separate CLI invocations still validate the filesystem. Use longer timeouts if needed. - Results return similarity ranking, exact file location, line numbers, and matching snippet preview. - Add `--content` (or `--format json`) to get the matching source text in the same call, and skip reading those files separately. The text sits at `content_start_line`..`content_end_line`, which can begin later than the result's `start_line` when a long symbol was indexed as several chunks. If a result shows `stale_line_range`, the file changed since indexing — re-run `vexor index`. Content is capped per response, so lower-ranked results may report `budget_exhausted`. - Combine `--ext` with `--exclude-pattern` to focus on a subset (exclude rules apply on top). ```` ## File: plugins/vexor/skills/vexor-cli/references/install-vexor.md size: 1245 sha: 410794c63fff8f3e02cb0ed136b8f142921ee34e upstream: https://github.com/scarletkc/vexor/blob/main/plugins/vexor/skills/vexor-cli/references/install-vexor.md ````text # Install Vexor Use this when the `vexor` command is missing. ## Steps 1. Verify if it is already installed: ```bash vexor --help ``` 2. Install with pip (recommended): ```bash python -m pip install -U vexor ``` 3. (Optional) Install with pipx for isolation: ```bash pipx install vexor ``` 4. Verify the install: ```bash vexor --help ``` ## If the command is still missing - Try running via module: ```bash python -m vexor --help ``` - Ensure the Python scripts directory is on PATH (e.g., `~/.local/bin` for user installs). ## After install: configure a provider Vexor needs a provider configuration before semantic search works. - **Remote providers (openai/gemini/custom)**: set an API key. ```bash vexor config --set-api-key "" ``` Optional: choose provider/model. ```bash vexor config --set-provider openai vexor config --set-model text-embedding-3-small ``` - **Local provider** (no API key, but requires local model setup): ```bash pip install "vexor[local]" or pip install "vexor[local-cuda]" vexor local --setup --model intfloat/multilingual-e5-small [--cuda] ``` If you cannot provide credentials or choose a local model, ask the user to assist. ```` ## File: README.md upstream: https://github.com/scarletkc/vexor/blob/main/README.md ````text
Vexor # Vexor [![Python](https://img.shields.io/badge/python-3.11%2B-blue)](https://www.python.org/downloads/) [![PyPI](https://img.shields.io/pypi/v/vexor.svg)](https://pypi.org/project/vexor/) [![CI](https://img.shields.io/github/actions/workflow/status/scarletkc/vexor/publish.yml?branch=main)](https://github.com/scarletkc/vexor/actions/workflows/publish.yml) [![Codecov](https://img.shields.io/codecov/c/github/scarletkc/vexor/main)](https://codecov.io/github/scarletkc/vexor) [![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/scarletkc/vexor?utm_source=oss&utm_medium=github&utm_campaign=scarletkc%2Fvexor&labelColor=171717&color=FF570A&link=https%3A%2F%2Fcoderabbit.ai&label=CodeRabbit+Reviews)](https://coderabbit.ai) [![License](https://img.shields.io/github/license/scarletkc/vexor.svg)](https://github.com/scarletkc/vexor/blob/main/LICENSE) [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/scarletkc/vexor)
--- **Vexor** is a semantic search engine that builds reusable indexes over files and code. It supports configurable embedding and reranking providers, and exposes the same core through a Python API, a CLI tool, and an MCP server. ## Featured In Vexor has been recognized and featured by the community: - **[Ruan Yifeng's Weekly (Issue #379)](https://github.com/ruanyf/weekly/blob/master/docs/issue-379.md#ai-%E7%9B%B8%E5%85%B3)** - A leading tech newsletter in the Chinese developer community. - **[Awesome Claude Skills](https://github.com/VoltAgent/awesome-claude-skills?tab=readme-ov-file#development-and-testing)** - Curated list of best-in-class skills for AI agents. - **[Awesome MCP Servers](https://github.com/punkpeye/awesome-mcp-servers#-developer-tools)** - Curated list of Model Context Protocol servers. - **[Awesome CLI Apps](https://github.com/agarrharr/awesome-cli-apps#search)** - Curated list of command-line apps. ## Why Vexor? When you remember what a file *does* but forget its name or location, Vexor finds it instantly—no grep patterns or directory traversal needed. Designed for both humans and AI coding assistants, enabling semantic file discovery in autonomous agent workflows. ## Install Download standalone binary from [releases](https://github.com/scarletkc/vexor/releases) (no Python required), or: ```bash pip install vexor # also works with pipx, uv ``` ## Quick Start ### 0. Guided Setup (Recommended) ```bash vexor init ``` The wizard also runs automatically before the first interactive operational command when no config exists. Configuration-management (`vexor config`), MCP, help, and version commands run directly. ### 1. Search ```bash vexor "api client config" # defaults to search current directory # or explicit path: vexor search "api client config" --path ~/projects/demo --top 5 # in-memory search only: vexor search "api client config" --no-cache ``` Vexor auto-indexes on first search. Example output: ``` Vexor semantic file search results ────────────────────────────────── # Similarity File path Lines Preview 1 0.923 ./src/config_loader.py - config loader entrypoint 2 0.871 ./src/utils/config_parse.py - parse config helpers 3 0.809 ./tests/test_config_loader.py - tests for config loader ``` ### 2. Explicit Index (Optional) ```bash vexor index # indexes current directory # or explicit path: vexor index --path ~/projects/demo --mode code ``` Useful for CI warmup or when `auto_index` is disabled. ## Python API Vexor can also be imported and used directly from Python: ```python from vexor import index, search index(path=".", mode="head") response = search("config loader", path=".", mode="name") for hit in response.results: print(hit.path, hit.score) ``` Configuration follows the same global and project-level resolution as the CLI. For runtime overrides, cache controls, and per-call options, see [`docs/api/python.md`](https://github.com/scarletkc/vexor/tree/main/docs/api/python.md). ## AI Agent Skill This repo includes a skill for AI agents to use Vexor effectively: ```bash vexor install --skills claude # Claude Code vexor install --skills codex # Codex ``` Skill source: [`plugins/vexor/skills/vexor-cli`](https://github.com/scarletkc/vexor/raw/refs/heads/main/plugins/vexor/skills/vexor-cli/SKILL.md) ## MCP Server [![vexor MCP server](https://glama.ai/mcp/servers/scarletkc/vexor/badges/score.svg)](https://glama.ai/mcp/servers/scarletkc/vexor) > [!NOTE] > The Agent Skill and the MCP server provide the same core capability — pick **one** per agent. > The skill teaches shell-capable agents (Claude Code, Codex) to drive the full CLI and assumes `vexor` is installed on PATH; the MCP server exposes search as native tools, works in any MCP client (Cursor, Windsurf, Zed, ...), and can bootstrap without prior setup via `uvx` and environment variables. Vexor ships a built-in [MCP](https://modelcontextprotocol.io) stdio server, so any MCP-capable agent can use semantic file search as a native tool: ```bash claude mcp add vexor -- vexor mcp # Claude Code codex mcp add vexor -- vexor mcp # Codex ``` Or configure manually in any MCP client, optionally supplying the API key and any config overrides via `env` (no `vexor init` needed): ```json { "mcpServers": { "vexor": { "command": "vexor", "args": ["mcp"], "env": { "VEXOR_API_KEY": "sk-...", "VEXOR_CONFIG_JSON": "{\"provider\": \"gemini\", \"rerank\": \"bm25\"}" } } } } ``` The server exposes two tools: `vexor_search` (semantic file search, returning the matching source text so an agent rarely needs a follow-up file read) and `vexor_index` (explicit index warm-up). No extra dependencies are required. Vexor is listed on the [official MCP registry](https://registry.modelcontextprotocol.io) as `io.github.scarletkc/vexor`. See [`docs/mcp.md`](https://github.com/scarletkc/vexor/tree/main/docs/mcp.md) for tool schemas, environment variables, and client setup details. ## Configuration ```bash vexor init # guided setup (recommended) vexor config --set-api-key "YOUR_KEY" # or env: VEXOR_API_KEY / OPENAI_API_KEY / ... vexor config --set-provider openai # default; also gemini/voyageai/custom/local vexor config --rerank hybrid # optional: fuse exact keyword + semantic ranking vexor config --show # view effective settings and origins ``` Global config lives in `~/.vexor/config.json`; the nearest `/.vexor/config.json` can override a restricted set of behavior fields for that project. Non-secret fields can also be injected via `VEXOR_CONFIG_JSON` (useful for MCP clients and CI), and fully offline use is supported through local embedding models. See [`docs/configuration.md`](https://github.com/scarletkc/vexor/blob/main/docs/configuration.md) for the complete reference: project config fields and precedence, all config commands, API keys and environment variables, rerank strategies (hybrid / BM25 / FlashRank / remote), remote vs local providers, embedding dimensions, and offline local model setup. ## CLI Reference Everyday usage fits in `vexor "query"`, `vexor search`, and `vexor index` (see Quick Start). The full command table, common flags, index modes (`--mode auto/name/head/brief/full/code/outline`), `.vexorignore` files, project-local indexes (`vexor index --local`), cache behavior, and porcelain output format are documented in [`docs/cli.md`](https://github.com/scarletkc/vexor/blob/main/docs/cli.md). ## Documentation - [Con ````