run-codex-adversarial-loop
Use if fanning out parallel Codex adversarial reviews, verifying findings, fixing in worktrees.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use if fanning out parallel Codex adversarial reviews, verifying findings, fixing in worktrees.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use if driving agent-browser for webpage interaction, screenshots, @ref snapshots, tabs, UI verification, CDP attach, Steel Browser, or cloud providers (Browser Use, Browserbase, Browserless, Kernel).
Use if verifying claimed-done work or auditing session/plan/branch completion with evidence.
Use if creating, redesigning, or merging a Claude skill, with research before writing SKILL.md.
Use skill if you are running repeatable Codex reviews across lenses or branches, optionally verifying and fixing confirmed findings in isolated worktrees.
Use if running deep multi-file research over 5+ entities or a market — wave-dispatched corpus.
Use if finishing a project — review and merge every branch/worktree into main, retire dead branches.
Use if fanning out parallel Codex adversarial reviews, verifying findings, fixing in worktrees.
# Copy this command into Claude Code to install this skill
/plugin add https://github.com/yigitkonur/skills-by-yigitkonur/tree/main/plugins/run-codex-adversarial-loop/skills/run-codex-adversarial-loop
For more information, visit the GitHub repository.