claudecodex

varro

Data analysis scaffold for Claude Code: SQL, persistent Jupyter, and markdown dashboards. Skills and code are intentionally minimal so users grow the plugin to fit their setup.

1 on GitHubby josca42v0.1.1updated 5 months ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin varro in josca42/varro_plugin. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (4)

  • dashboards

    Use when creating, editing, or viewing markdown-based dashboards. Dashboards live in dashboards/<name>/ as a dashboard.md (markdown with `:::` containers and `<fig />` `<table />` `<metric />` tags) plus an outputs.py with `@output` Python functions. The dashboard URL is a canonical state descriptor

  • jupyter

    Use when running Python in a stateful IPython kernel via `mcp__varro__jupyter`.

  • sql

    Use when querying the project's SQL database via `mcp__varro__sql`.

  • workflow

    Default Varro workflow. Always read, when loading Varro plugin

MCP servers (1)

  • varro

    runs: bash -lc set -euo pipefail plugin_root="${VARRO_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}}" if [[ -z "$plugin_root" ]]; then for candidate in "$HOME"/.codex/plugins/cache/*/varro/*

View source on GitHub

Maintain varro?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted