Execute and manage Codex CLI sessions for code analysis, refactoring, and automated editing.
npx skills add https://github.com/jdrhyne/agent-skills --skill codex-jdrhyne
Please help me install this Agent Skill. Skill: codex Source: https://github.com/jdrhyne/agent-skills/tree/main/codex/codex Command: npx skills add https://github.com/jdrhyne/agent-skills --skill codex-jdrhyne
This skill enables users to run and manage the Codex CLI (codex exec, codex resume) for code analysis, automated editing, and refactoring tasks, consolidating workflow into a single conversational interface.
Start a new Codex session to analyze a repository: codex exec -m gpt-5.2 --sandbox read-only --full-auto --skip-git-repo-check 'Analyze this repository comprehensively...' 2>/dev/null
High-intent search queries and answers about installing and using this skill.
You can automate code analysis and refactoring with the Codex CLI by running the codex exec command with your prompt, which processes automated edits using GPT-5.2 by default while enforcing safety practices like skipping git repo checks.
The best way to resume a Codex CLI session across projects is to use the codex resume command, which safely restores your previous session context and state for continued code analysis and automated editing.
Yes, you need the codex CLI installed and accessible on your system PATH to execute code edits. This environment setup allows the skill to assemble and run commands with flags like -m/--model and --config.
Sandbox mode controls file system access during Codex CLI task execution by offering read-only, workspace-write, and danger-full-access options, ensuring safe code analysis and automated editing by restricting permissions as needed.
Thinking tokens are redirected during codex exec repository analysis to enforce safety practices and prevent output clutter, ensuring cleaner command results unless you explicitly request to view them.
Yes, you can select a different model instead of GPT-5.2 for Codex CLI session management by using the -m or --model flag during command assembly, allowing you to tailor the model and reasoning level to your code analysis needs.
stephanjIntegrate Codex CLI with Claude Code for automated code analysis and editing.
nvimcraftGenerate Angular Conventional Commit messages from staged Git changes.
Neneka448Manage tmux sessions and automate keyboard/mouse input.
Snowflake-LabsA concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略
