Runs OpenAI Codex CLI for independent code review, adversarial challenge, and consult sessions.
npx skills add https://github.com/aicodepro/ai-agent-nexi --skill codex-aicodepro
Please help me install this Agent Skill. Skill: codex Source: https://github.com/aicodepro/ai-agent-nexi/tree/main/agent/skills/gstack/codex Command: npx skills add https://github.com/aicodepro/ai-agent-nexi --skill codex-aicodepro
codex review as a pass/fail gate on your diff, catching issues your own review missed. - Adversarial Challenge Mode: Tries to break your code by attacking assumptions, edge cases, and failure paths. - Consult with Session Continuity: Ask Codex anything and keep follow-up questions in the same session context. - Use Case: Before merging a risky refactor, invoke the review mode to get a pass/fail verdict, then run challenge mode to probe the weakest part of the change. ## Quick Start Ask the assistant to run a codex review of the current diff and report whether it passes or fails.High-intent search queries and answers about installing and using this skill.
Invoke the codex review mode, which runs the OpenAI Codex CLI against your current diff and returns a pass/fail verdict. It acts as an independent reviewer so issues your own review missed are surfaced before merge.
Challenge mode instructs Codex to actively try to break your code by attacking assumptions, edge cases, and failure paths. It is useful after a review passes, to probe the weakest parts of an implementation.
Yes, consult mode keeps session continuity so follow-up questions retain prior context. You can ask Codex anything and refine the discussion across multiple turns without restating the problem.
Yes, the preamble detects session kind (interactive, headless, or spawned) and adapts. In spawned sessions it auto-chooses recommended options and skips interactive prompts; in headless mode it blocks when a question cannot be answered.
CLI-based review depends on the underlying model's context window and the quality of the diff provided. Very large changes may need to be split, and the pass/fail gate should complement rather than replace human review for critical code.
apocohqRebase a feature branch into logical commits for PR review.
TioSavichMerge base branch, run tests, bump version, update changelog, commit, push, and create a pull request.
TruCol270Automate Spring Boot project verification with builds, tests, coverage, and security scans.
eklyukinObtains independent second opinions from OpenAI Codex CLI for planning, code review, and implementation review.