Gemma Runner

Execute prompts as the Gemma seat through the shared pi-runner implementation. This replaces the previous Cline-backed shim — --provider openrouter --model google/gemma-4-31b-it is pinned on every invocation, so the seat no longer depends on whichever provider Cline's mutable state happens to point at; the model that answers is always the forwarded Gemma model, served via OpenRouter.

Default Model

• google/gemma-4-31b-it, pinned as --provider openrouter --model google/gemma-4-31b-it on every run. Override with --model to point the Gemma seat at a different OpenRouter model id.

Prerequisites

• pi CLI installed and in PATH (npm install -g @mariozechner/pi-coding-agent)
• OPENROUTER_API_KEY in the environment (or an OpenRouter credential in Pi's auth store)

Security Model

This skill delegates to pi-runner, so it has the same execution and data sharing model as the Pi wrapper — see ../pi-runner/SKILL.md. Runs are hermetic (no extensions, skills, or AGENTS.md/CLAUDE.md discovery). Analysis roles (every role except implementer) default to read-only mode (only Pi's file-reading tool enabled). Pass --allow-write to opt out, or --no-tools to block tools entirely.

Shared Wrapper Reference