rag-rat: Skill for Claude Code

init-rag-rat — configure a dormant rag-rat repo conversationally

rag-rat's MCP server boots dormant in a repo with no rag-rat.toml: ordinary tools return {"status":"no_index", "remedy":"Run rag-rat init … then restart"}. This skill turns that into a short guided setup. You own the conversation; rag-rat init owns the scan and validation — never hand-write a config blind, and let a real config load re-check it before indexing.

The common path

1. Detect state. You are here because a rag-rat tool returned status: "no_index", or the user asked to set up rag-rat. Confirm there is no rag-rat.toml at (or above) the repo root. If one already exists, this is a reconfigure — send the user to the interactive rag-rat init wizard and stop.

2. Resolve the CLI and use the same form throughout, from the target repo's root. It must match the version the rag-rat MCP server runs, so the index you create is one the server can read — do not use @latest, and don't blindly trust an on-PATH rag-rat:

   • If rag-rat is on PATH, check rag-rat --version and use it only if it matches the plugin/MCP version — a stale global install would build the index with the wrong binary. With the plugin, ~/.local/bin/rag-rat is its version-matched binary (the MCP server links it when it starts), so try that path too if rag-rat alone is not found.
   • Otherwise (or on a version mismatch) use npx -y @rag-rat/[email protected] … — the plugin pins @rag-rat/bin to its own version and caches the binary privately, so this is the version-matched CLI; npx runs it in the current directory.

3. Dry-run discovery. <rag-rat> init --yes --dry-run scans the repo and prints the auto-detected config (languages, path bindings, the default local FastEmbed backend) without writing. Read it; tell the user the material bits in a line or two (which languages and directories) — not every commented knob.