second-opinionlisted

# /second-opinion ## Preconditions - `.forge/settings.yaml` exists and `agents.review_host_cli` is set to `codex` or `gemini` (not `null`, not `claude`). - The configured reviewer CLI is installed (`which codex` / `which gemini`). - **Working tree is rebased onto current `main`.** The reviewer reads files from disk; if the worktree is stale, the reviewer reasons about old code and may miss recently-merged dependencies (sibling adapters, new abstractions, refactored APIs). Always `git fetch origin main && git rebase origin/main` in the worktree before invoking. - For framework projects using gitignored project meta (e.g., `spec/`, `plans/`, `docs/learnings/`): re-hydrate them in the worktree after rebase so the reviewer sees the canonical source-of-truth, not just the tracked source files. ## Why a second opinion (not just an in-CC agent) The reviewer runs in a separate process with its own context, its own model, and its own training cutoff. It has no memory of this conversation. That makes it an honest second opinion: it can't be primed by what you've already concluded, and it'll catch type errors / mirror-faithfulness bugs that an agent inheriting context will rationalize away. Two things to leverage: - **Codebase reasoning.** The reviewer reads the working tree on demand (`rg`, `sed`, file reads). It can trace a tracker's dependency on a sibling adapter, check a refactor against recently-merged PRs, verify a plan's pseudocode against the actual type signatures it cla