Codex
- 28 installs
- 902 repo stars
- Updated June 22, 2026
- bear2u/my-skills
Codex is a Claude skill that instructs an agent to run the OpenAI Codex CLI (codex exec, resume) for code analysis, refactoring, and automated editing.
About
This skill guides an agent to run the OpenAI Codex CLI for code analysis, refactoring, and automated editing. It prompts for the model and reasoning effort, picks an appropriate sandbox mode, assembles the codex exec command, and can resume prior sessions via stdin. A developer uses it to delegate coding tasks to Codex with controlled permissions.
- Drives the OpenAI Codex CLI (codex exec, resume) with model and reasoning-effort prompts
- Selects sandbox mode (read-only, workspace-write, danger-full-access) per task
- Confirms high-impact flags with the user before running
Codex by the numbers
- 28 all-time installs (skills.sh)
- Ranked #9,505 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
codex capabilities & compatibility
- Capabilities
- refactoring · code review
- Works with
- openai
- Use cases
- refactoring · code review · orchestration
- Runs
- Runs locally
- Pricing
- Bring your own API key
What codex says it does
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
Select the sandbox mode required for the task; default to `--sandbox read-only` unless edits or network access are necessary.
npx skills add https://github.com/bear2u/my-skills --skill codexAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 28 |
|---|---|
| repo stars | ★ 902 |
| Last updated | June 22, 2026 |
| Repository | bear2u/my-skills ↗ |
What it does
Run the OpenAI Codex CLI for code analysis, refactoring, or automated editing with controlled sandbox and model settings.
Who is it for?
Delegating code analysis, refactoring, or edits to the OpenAI Codex CLI with the right sandbox.
Skip if: Tasks that do not involve the Codex CLI.
When should I use this skill?
When the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code work.
What you get
A correctly assembled and executed codex exec command with the chosen model, effort, and sandbox, plus a summarized result.
By the numbers
- 3 sandbox modes: read-only, workspace-write, danger-full-access
Files
Codex Skill Guide
Running a Task
1. Ask the user (via AskUserQuestion) which model to run: gpt-5 or gpt-5-codex. 2. Ask the user (via AskUserQuestion) which reasoning effort to use: low, medium, or high. 3. Select the sandbox mode required for the task; default to --sandbox read-only unless edits or network access are necessary. 4. Assemble the command with the appropriate options:
-m, --model <MODEL>--config model_reasoning_effort="<low|medium|high>"--sandbox <read-only|workspace-write|danger-full-access>--full-auto-C, --cd <DIR>--skip-git-repo-check
5. When continuing a previous session, use codex exec resume --last via stdin. IMPORTANT: When resuming, you CANNOT specify model, reasoning effort, or other flags—the session retains all settings from the original run. Resume syntax: echo "your prompt here" | codex exec resume --last 6. Run the command, capture stdout/stderr, and summarize the outcome for the user.
Quick Reference
| Use case | Sandbox mode | Key flags |
|---|---|---|
| Read-only review or analysis | read-only | --sandbox read-only |
| Apply local edits | workspace-write | --sandbox workspace-write --full-auto |
| Permit network or broad access | danger-full-access | --sandbox danger-full-access --full-auto |
| Resume recent session | Inherited from original | `echo "prompt" \ |
| Run from another directory | Match task needs | -C <DIR> plus other flags |
Following Up
- After every
codexcommand, immediately useAskUserQuestionto confirm next steps, collect clarifications, or decide whether to resume withcodex exec resume --last. - When resuming, pipe the new prompt via stdin:
echo "new prompt" | codex exec resume --last. The resumed session automatically uses the same model, reasoning effort, and sandbox mode from the original session. - Restate the chosen model, reasoning effort, and sandbox mode when proposing follow-up actions.
Error Handling
- Stop and report failures whenever
codex --versionor acodex execcommand exits non-zero; request direction before retrying. - Before you use high-impact flags (
--full-auto,--sandbox danger-full-access,--skip-git-repo-check) ask the user for permission using AskUserQuestion unless it was already given. - When output includes warnings or partial results, summarize them and ask how to adjust using
AskUserQuestion.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10