Awesome-omni-skill plan-refine-codex

Refine a Claude Code plan using OpenAI Codex. Use when you have a plan file and want a second opinion or to improve robustness.

install

source · Clone the upstream repo

git clone https://github.com/diegosouzapw/awesome-omni-skill

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/diegosouzapw/awesome-omni-skill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/ai-agents/plan-refine-codex" ~/.claude/skills/diegosouzapw-awesome-omni-skill-plan-refine-codex && rm -rf "$T"

manifest: skills/ai-agents/plan-refine-codex/SKILL.md

source content

Plan Refinement with Codex

Use OpenAI Codex to review and refine implementation plans, adding robustness and catching edge cases.

Prerequisites

```
codex
```
CLI installed and authenticated (
```
codex login
```
)
A plan file exists (typically at
```
~/.claude/plans/<name>.md
```
)

Usage

Invocation	Behavior
`/plan-refine-codex`	Refine the current plan file (if in plan mode)
`/plan-refine-codex /path/to/plan.md`	Refine the specified plan file

How to Refine a Plan

Run codex exec with

--full-auto

and ask it to read and refine the plan file:

codex exec --full-auto "Please read the file $PLAN_FILE and refine the plan. Make it more robust, handle edge cases, and simplify where possible. Return only the improved plan in markdown format."

Important: Have codex read the file itself rather than piping content via stdin. Stdin piping has reliability issues.

Example

codex exec --full-auto "Please read the file /Users/me/.claude/plans/my-plan.md and refine the plan. Look for edge cases like: error handling, input validation, permission issues. Return only the improved plan in markdown format."

Known Issues & Workarounds

Issue: Model not available

ERROR: The 'o3' model is not supported when using Codex with a ChatGPT account.

Workaround: Don't specify

-m o3

. Use the default model (

gpt-5.2-codex

Issue: Stdin content not received

When piping content via stdin, codex may not receive it:

# This may fail - codex doesn't see the piped content
cat plan.md | codex exec "Refine this plan..."

Workaround: Ask codex to read the file directly in the prompt.

Issue: Heredoc with embedded bash fails

# This fails due to nested $() and backticks
codex exec "$(cat <<'EOF'
...plan with bash code...
EOF
)"

Workaround: Reference the file path instead of embedding content.

Iterating on Refinement

You can pass the plan to codex multiple times for progressive improvement:

First pass: Focus on edge cases and error handling
Second pass: Focus on simplification and clarity
Final pass: Focus on production-readiness

After each refinement, update your plan file with the improved version.

Related Skills

```
/roborev-review
```
- Get AI code review on your implementation
```
/roborev-refine
```
- Automated review-fix loop