Wraps OpenAI Codex CLI for independent code review, adversarial challenge, and consult sessions.
npx skills add https://github.com/kitfunso/claude-config --skill codex-kitfunso
Please help me install this Agent Skill. Skill: codex Source: https://github.com/kitfunso/claude-config/tree/main/skills/codex Command: npx skills add https://github.com/kitfunso/claude-config --skill codex-kitfunso
codex review against your changes with a pass/fail gate, catching issues your primary model may have 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 context across questions in the same session. - Use Case: Before merging a branch, invoke a codex review to get a "200 IQ autistic developer" second opinion on the diff, then run challenge mode to stress-test the riskiest logic. ## Quick Start Ask the assistant to run a codex review of the current branch diff and report any blocking issues before shipping.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 gate with findings. It works on the current git branch and reports blocking issues before you ship.
Challenge mode instructs Codex to actively try to break your code by attacking assumptions, edge cases, and failure paths rather than approving it. Use it when you want stress-testing instead of a standard review.
Yes, consult mode maintains session continuity so follow-up questions build on earlier answers within the same session. This lets you iterate on a design or debugging thread without restating context.
Yes, the preamble detects headless sessions via gstack-session-kind and skips interactive prompts. In headless mode, unavailable AskUserQuestion calls result in a BLOCKED state rather than silent auto-decisions.
The review quality depends on the Codex CLI being installed and authenticated, and it reviews the diff it is given rather than running your test suite. Treat the pass/fail gate as a second opinion, not a replacement for CI.
fwojciecAutomate code reviews by querying Gemini on Git branch diffs.
Juhwa-Lee1023Orchestrate end-to-end PR workflows for GitHub Copilot CLI deployments.
testdoubleRefactor code iteratively with test-gated validation after each step.
eklyukinObtains independent second opinions from OpenAI Codex CLI for planning, code review, and implementation review.