mcpField
C
codex-result-handling

codex-result-handling

github.com/openaiAgent workflows34.7k680 installsUpdated 16w ago
Repository

About codex-result-handling

A skill for handling output from a Codex helper, including reviews, edits, and failed runs. It preserves the helper’s structure and evidence boundaries, and requires review findings to be reported without applying fixes.

Key features

  1. 01Preserve verdicts and output sections
  2. 02Order review findings by severity
  3. 03Retain uncertainty and evidence boundaries
  4. 04Report edits and touched files
  5. 05Stop after review; request fix approval

Use cases

  1. 01Present Codex review results faithfully
  2. 02Summarize files changed by a Codex run
  3. 03Report failed or incomplete runs without guessing

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/openai/codex-plugin-cc --skill codex-result-handling

After installing, type/codex-result-handlingin Claude Code to confirm it loaded.

Details

From the project README

Codex Result Handling

When the helper returns Codex output:

  • Preserve the helper's verdict, summary, findings, and next steps structure.
  • For review output, present findings first and keep them ordered by severity.
  • Use the file paths and line numbers exactly as the helper reports them.
  • Preserve evidence boundaries. If Codex marked something as an inference, uncertainty, or follow-up question, keep that distinction.
  • Preserve output sections when the prompt asked for them, such as observed facts, inferences, open questions, touched files, or next steps.
  • If there are no findings, say that explicitly and keep the residual-risk note brief.
  • If Codex made edits, say so explicitly and list the touched files when the helper provides them.
  • For codex:codex-rescue, do not turn a failed or incomplete Codex run into a Claude-side implementation attempt. Report the failure and stop.
  • For codex:codex-rescue, if Codex was never successfully invoked, do not generate a substitute answer at all.
  • CRITICAL: After presenting review findings, STOP. Do not make any code changes. Do not fix any issues. You MUST explicitly ask the user which issues, if any, they want fixed before touching a single file. Auto-applying fixes from a review is strictly forbidden, even if the fix is obvious.
  • If the helper reports malformed output or a failed Codex run, include the most actionable stderr lines and stop there instead of guessing.
  • If the helper reports that setup or authentication is required, direct the user to /codex:setup and do not improvise alternate auth flows.

Comments

Markdown supported