Run Codex CLI code reviews with pass/fail gates on git diffs.
npx skills add https://github.com/mattothomas/sp26_hackpsu --skill codex-mattothomas
Please help me install this Agent Skill. Skill: codex Source: https://github.com/mattothomas/sp26_hackpsu/tree/main/.claude/skills/gstack/codex Command: npx skills add https://github.com/mattothomas/sp26_hackpsu --skill codex-mattothomas
Provides an independent Codex-based assessment of code changes via a CLI wrapper that exposes multiple working modes.
Install the Codex CLI and run codex review on the current git diff to get a second opinion.
High-intent search queries and answers about installing and using this skill.
To get an independent code review, run a CLI wrapper against your current git diff to perform a diff-based assessment with a pass/fail gate. This provides a brutally honest second opinion on your code changes before merging.
Yes, you can run adversarial prompts to try to break your code using a dedicated challenge mode. This mode executes adversarial challenges against your code changes to actively probe for weaknesses and potential failures.
Yes, you need the codex CLI installed to use this code assessment wrapper. The tool requires the codex CLI to be present in your environment and also supports the Bash, Read, Write, Glob, Grep, and AskUserQuestion tools.
Session continuity improves AI-assisted code consult feedback by maintaining context across multiple interactions. This retained context allows the AI-assistant to provide higher quality follow-up answers during consult-style prompts.
The best way to challenge AI-generated code suggestions is to use an adversarial CLI wrapper to run challenge prompts. This provides an independent, brutally honest second opinion that actively tries to break the code changes before approval.
ManzuetiWrap OpenAI Codex CLI for code review, challenge, and consultation modes.
DeL-TaiseiOzakiConsult Codex CLI for design, debugging, and code review decisions.
daffy0208Automate code review with OpenAI Codex CLI in Git workflows.
TimHL5Orchestrate Codex CLI evaluations for code review, challenge, and consult flows.
