mcpField
V
vexor

vexor

github.com/sickn33Development48.7k83 installsUpdated today
Repository

About vexor

Vexor is a skill for using a vector-powered CLI to search project files semantically. It is intended for developers using Claude or Codex, and emphasizes checking the installed tool and validating matched source locations.

Key features

  1. 01Semantic file search
  2. 02Vector-powered CLI workflow
  3. 03Claude and Codex skill guidance
  4. 04Query and exclusion planning
  5. 05Match verification guidance

Use cases

  1. 01Finding code by concept
  2. 02Searching a large project
  3. 03Locating relevant files without exact terms

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sickn33/agentic-awesome-skills --skill vexor

After installing, type/vexorin Claude Code to confirm it loaded.

Details

From the project README

Vexor

Overview

Vector-powered CLI for semantic file search with a Claude/Codex skill

When to Use This Skill

Use this skill when you need to work with vector-powered cli for semantic file search with a claude/codex skill.

Procedure

This is a guide to an external semantic file-search tool, not a bundled executable. Identify the authorized project root, search question and file exclusions. Inspect an already installed, reviewed Vexor version and its actual help before constructing a query. Confirm whether indexing or embedding sends file content to a provider and obtain the required data/cost scope before doing so. Exclude credentials and unrelated private files. Read returned source locations to verify relevance; a semantic match is not proof. Report missing runtime or index explicitly, and use an available local text search when appropriate.

See the source repository for version-specific setup.

Example

User request:

Use @vexor for this task: Vector-powered CLI for semantic file search with a Claude/Codex skill.

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Comments

Markdown supported