codex-result-handling

$npx mdskill add openai/codex-plugin-cc/codex-result-handling

Formats and presents Codex helper output to users while preserving structure and preventing unauthorized changes.

  • Helps developers receive clear, structured feedback from Codex without automatic code modifications.
  • Integrates with Codex helper services to process review outputs and rescue operations.
  • Decides recommendations by following strict rules for ordering findings and preserving evidence boundaries.
  • Delivers results by presenting findings first, explicitly stating edits, and requiring user approval for fixes.
SKILL.md
.github/skills/codex-result-handlingView on GitHub ↗
---
name: codex-result-handling
description: Internal guidance for presenting Codex helper output back to the user
user-invocable: false
---

# 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.
More from openai/codex-plugin-cc