Codex Exec CI Fixer: Diagnose, Minimal Fix, Rerun, Stop After 3 Attempts
Gives codex exec a non-interactive procedure to diagnose a failing CI output, apply a minimal fix, rerun the checks and stop after three attempts with a clear report.
18 prompts
Prompts for Codex, OpenAI's coding agent. Each one is a task brief: what to change, where, which checks must pass and what to report back, so Codex can work through it and show you the result.
2 results
Gives codex exec a non-interactive procedure to diagnose a failing CI output, apply a minimal fix, rerun the checks and stop after three attempts with a clear report.
A save-ready SKILL.md that has your coding agent review a branch before merge: correctness, security, tests and migrations, with findings ranked by severity and no style nitpicks.
Paste it as the task in the Codex CLI, the IDE extension or Codex in ChatGPT, pointed at the repository the task is about, so the agent can read the code first.
AGENTS.md is a file in your repository that tells coding agents how to build, test and style the code. Codex reads it before it starts, so a task prompt only needs the task.
Ask for a summary of the files it changed and the commands it ran, then read the diff before you merge. Run the tests yourself if the prompt touches anything critical.