Codex Planning Prompt Skill for ChatGPT: Frame Key Decisions From Repository Evidence
Draft a copy-ready planning prompt for a supplied change. Ask for repository evidence and a few consequential choices before file-level implementation and verification planning.
中文Install in ChatGPT
Requires a ChatGPT workspace where you can create skills. This is a text adaptation of the pinned GitHub source.
- Review the inputs and outputs in the pinned .agents/skills/codenote-plan-mode-prompt/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide the feature goal, known repository structure, release constraints, and open choices.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional browser notes extension needs export. Image inclusion and original format are undecided. Draft a planning prompt using existing permission and version evidence.What to check
Ask for the export call path, data, and user flow. Frame format and image choices with consequences and request regression, release, and rollback conditions.
Original SKILL.md on GitHub · Updated
Frequently asked question
When should permission review appear in the plan?
When browser permission, remote requests, or declared scope changes, include current evidence and expected review effects as decision inputs.