Codex CLI Skill

Trust Score 81/100

Guides safe, sandboxed use of the Codex CLI for code analysis, refactoring, and automated edits, with recommended flags and safety boundaries.

triggers:codex execrun codexcodex resumeuse codexcodex cliautomated editscode refactor

GitHub SKILL.md

What it does

Provides operational guidance for using the Codex CLI in agent workflows. The skill documents recommended sandbox modes, flag usage, model defaults (gpt-5.2), and safe practices for running codex exec and resuming sessions. It includes step-by-step instructions for assembling commands, handling reasoning effort levels, and summarizing outcomes for users.

When to use it

Use this skill when a user requests that the agent run Codex CLI commands, perform automated code edits, or resume prior Codex sessions. It is applicable to tasks like refactoring, code review, applying local edits, or running agentic coding workflows that need explicit sandbox and safety controls.

What's included

Scripts: none bundled (has_scripts=false) — procedural CLI guidance is embedded in the SKILL.md.
References: none bundled (has_references=false).
Instructions: defaults to gpt-5.2, safe sandbox recommendations (read-only by default), append 2>/dev/null to suppress thinking tokens, and explicit error-handling and follow-up guidance.

Compatible agents

Targeted at systems that can execute CLI tools or orchestrate Codex (Codex CLI, Claude Code wrappers, or other agent runners).

Audit Summary

Instruction-only skill (no scripts) that guides safe use of the OpenAI Codex CLI for code analysis and refactoring. Well-structured SKILL.md with clear safety boundaries, sandbox mode defaults, and model options. No executable code to test.

Watch Out

No scripts — pure instruction skill, so code quality reflects SKILL.md writing only
--skip-git-repo-check is always recommended which skips a safety guardrail
Requires Codex CLI v0.57.0+

Notes

Clean skill with no security concerns. Emphasizes user confirmation before destructive operations. The always-use --skip-git-repo-check is a minor concern but specific to Codex CLI workflow.

Information

Repository: agent-skills
Stars: 231

Trust Score

Overall81

Security92

Code Quality72

Architecture65

Usefulness62

More from agent-skills

Gemini CLI — Code & Large-Context Analysis

Run the Gemini CLI for large-context code reviews, plan reviews, and multi-file analysis; includes safety guidance for background and interactive modes.

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

Back to Skills