cursor-interrogate
Codex runtime mapping
This published workflow is explicit-only through agents/openai.yaml. Use the native Codex subagent capability for independent read-only reviewers only when delegation is authorized. Require one immutable scope and rubric, at least two distinct model requests accepted by native spawn, separate read-only outputs, and a coordinator lead judgment before claiming a bounded review. If a configured reviewer is missing or fails, mark the aggregate PARTIAL and name the slot; never fabricate multi-model consensus or a complete configured run. Follow the standing model-capability-router and the operator-selected model/effort; do not force the Cursor default model table. Record requested reviewer profiles and unavailable slots, and mark effective model/effort readback unavailable unless the native surface supplies it. Keep the source rubric, lead judgment, and no-auto-apply contract.
Interrogate
Spawn one reviewer per configured model to adversarially review code changes. The adversarial signal comes from model diversity, not assigned personas. The deliverable is a synthesized verdict. Do NOT auto-apply changes.
Step 1, Scope
Identify what to review from context:
- If the user points at specific files or a diff, use that.
- If on a feature branch, run
git diff main...HEAD(or the appropriate base branch) for the full changeset. - If the user's message references recent work, gather the relevant files.
Package the diff or file contents with any surrounding context files the reviewers need to understand the code.