Runs OpenAI Codex CLI for independent code review, adversarial challenge, and consult sessions.
npx skills add https://github.com/no-session/pstack --skill codex-no-session
Please help me install this Agent Skill. Skill: codex Source: https://github.com/no-session/pstack/tree/main/codex Command: npx skills add https://github.com/no-session/pstack --skill codex-no-session
codex review against your branch diff with a pass/fail gate based on [P1] critical findings, plus cross-model comparison against Claude's own /review results. - Challenge Mode: Adversarial analysis that tries to break your code, hunting edge cases, race conditions, security holes, and failure modes, with optional focus areas like security. - Consult Mode: Ask Codex anything with session continuity for follow-up questions, using medium reasoning effort for interactive speed. - Use Case: Before shipping a billing change, run /codex review to get an independent pass/fail verdict, then /codex challenge security to probe for injection and auth bypass paths. ## Quick Start Ask the assistant to run /codex review on the current branch to get an independent code review with a pass/fail gate.High-intent search queries and answers about installing and using this skill.
Run /codex review to have the OpenAI Codex CLI independently review your branch diff against the base branch. It returns a pass/fail gate based on critical [P1] findings and can compare results against Claude's own /review output.
Install it with npm install -g @openai/codex, or see the repository at github.com/openai/codex. The skill checks for the codex binary first and stops with install instructions if it is not found.
Review mode produces a standard code review with a pass/fail gate on critical findings. Challenge mode is adversarial: it tries to break your code by hunting edge cases, race conditions, security holes, and failure modes, with an optional focus like security.
Yes. The skill detects the platform from the git remote URL and uses glab to find the merge request target branch, falling back to git-native commands like symbolic-ref when CLI tools are unavailable.
Review runs with a 5-minute timeout, so very large diffs may exceed it. Failures also occur when the codex binary is missing, the directory is not a git repository, or the base branch cannot be detected.
Yes. Pass --xhigh anywhere in your command to override the per-mode defaults. Review and Challenge default to high effort, while Consult defaults to medium for faster interactive responses.
OlatisunkanmiGenerate concise pull request summaries from branch diffs and git history.
VirtoCommerceValidate merged commits and release verified fixes as controlled hotfix patches.
GCWingReviews implementation plans for architecture, code quality, test coverage, and performance issues.
eklyukinObtains independent second opinions from OpenAI Codex CLI for planning, code review, and implementation review.