codex

Note: If you want a more autonomous setup for agentic workflows, check out klaudworks/ralph-meets-rex.

Installation

This repository is structured as a Claude Code Plugin with a marketplace. You can install it as a plugin (recommended) or extract it as a standalone skill.

Option 1: Plugin Installation (Recommended)

Install via Claude Code's plugin system for automatic updates:

/plugin marketplace add skills-directory/skill-codex
/plugin install skill-codex@skill-codex

Option 2: Standalone Skill Installation

Extract the skill folder manually:

git clone --depth 1 git@github.com:skills-directory/skill-codex.git /tmp/skills-temp && \
mkdir -p ~/.claude/skills && \
cp -r /tmp/skills-temp/plugins/skill-codex/skills/codex ~/.claude/skills/codex && \
rm -rf /tmp/skills-temp

Usage

Running a Task

1. Ask the user (via AskUserQuestion) which model to run (gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.3-codex-spark, or gpt-5.3-codex) AND which reasoning effort to use (xhigh, high, medium, or low) in a single prompt with two questions.
2. Select the sandbox mode required for the task; default to --sandbox read-only unless edits or network access are necessary.
3. Assemble the command with the appropriate options:
4. -m, --model
5. --config model_reasoning_effort=" "
6. --sandbox
7. --full-auto
8. -C, --cd
9. --skip-git-repo-check
10. "your prompt here" (as final positional argument)
11. Always use --skip-git-repo-check.
12. When continuing a previous session, use codex exec --skip-git-repo-check resume --last via stdin. When resuming don't use any configuration flags unless explicitly requested by the user e.g. if he species the model or the reasoning effort when requesting to resume a session. Resume syntax: echo "your prompt here" | codex exec --skip-git-repo-check resume --last 2>/dev/null. All flags have to be inserted between exec and resume.
13. IMPORTANT: By default, append 2>/dev/null to all codex exec commands to suppress thinking tokens (stderr). Only show stderr if the user explicitly requests to see thinking tokens or if debugging is needed.
14. Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.
15. After Codex completes, inform the user: "You can resume this Codex session at any time by saying 'codex resume' or asking me to continue with additional analysis or changes."

Following Up

• After every codex command, immediately use AskUserQuestion to confirm next steps, collect clarifications, or decide whether to resume with codex exec resume --last.
• When resuming, pipe the new prompt via stdin: echo "new prompt" | codex exec resume --last 2>/dev/null. 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.

Critical Evaluation of Codex Output

Codex is powered by OpenAI models with their own knowledge cutoffs and limitations. Treat Codex as a colleague, not an authority.

Guidelines

• Trust your own knowledge when confident. If Codex claims something you know is incorrect, push back directly.
• Research disagreements using WebSearch or documentation before accepting Codex's claims. Share findings with Codex via resume if needed.
• Remember knowledge cutoffs - Codex may not know about recent releases, APIs, or changes that occurred after its training data.
• Don't defer blindly - Codex can be wrong. Evaluate its suggestions critically, especially regarding:
• Model names and capabilities
• Recent library versions or API changes
• Best practices that may have evolved

When Codex is Wrong

1. State your disagreement clearly to the user
2. Provide evidence (your own knowledge, web search, docs)
3. Optionally resume the Codex session to discuss the disagreement. Identify yourself as Claude so Codex knows it's a peer AI discussion. Use your actual model name (e.g., the model you are currently running as) instead of a hardcoded name:

   echo "This is Claude (<your current model name>) following up. I disagree with [X] because [evidence]. What's your take on this?" | codex exec --skip-git-repo-check resume --last 2>/dev/null

1. Frame disagreements as discussions, not corrections - either AI could be wrong
2. Let the user decide how to proceed if there's genuine ambiguity