gh-gemini-review-loop

Deep Discovery adds a Codex skill that interrogates a topic with 100 questions before you commit to a design, plan, or strategy. Each question builds on the previous answer, helping surface hidden assumptions, missing constraints, and weak decisions. It routes the process through focused patterns for architecture, code review, plugin and skill audits, product strategy, trading systems, or general analysis, making it useful as a deliberate pre-execution review step.

Point the skill at a NetIQ or OpenText Identity Manager Designer workspace to document drivers, policies, filters, entitlements, packages, vault schema, and RBPM provisioning. It can compare two exports in terms of actual behavior instead of noisy IDs, ordering, and timestamps. The workflow is intentionally read-only and does not edit Designer files.

The Council sends project context and a focused prompt to Codex and Gemini in parallel, then has Claude synthesize their agreement, disagreements, and a final recommendation. It supports code review, architecture decisions, debugging, and general second opinions, with single-advisor fallback when one CLI is unavailable. Versions 1.2.0 and 1.2.1 did not reliably enforce Gemini read-only access, so version 1.3.0 or later should be used.

Leave requested changes directly beside the relevant source code using @feedback annotations in common comment styles. The plugin finds unaddressed notes, implements each request, and adds an @agent-response for review; once approved, a resolve command removes both annotation types and leaves clean code ready to commit.