refactor-agents-md

# Refactor AGENTS.md Refactor an `AGENTS.md` toward progressive disclosure. Every retained line enters each Codex session in its scope, so it must earn that attention. Move narrower guidance to the closest applicable scope or a reusable skill, and remove instructions that do not change behavior. ## Instructions 1. **Pick the target.** Use a target named by the invocation. Otherwise ask the user to choose among the files that exist: - The user-level file at `$CODEX_HOME/AGENTS.md`, defaulting to `~/.codex/AGENTS.md` when `CODEX_HOME` is unset. - The current project's root `AGENTS.md`. - Any nested `AGENTS.md` on the path from the project root to the current working directory. 2. **Fetch the yardsticks.** Fetch these pages to calibrate the audit: - https://developers.openai.com/api/docs/guides/latest-model?model=gpt-5.6 - https://developers.openai.com/api/docs/guides/prompt-guidance-gpt-5p6 - https://www.aihero.dev/a-complete-guide-to-agents-md 3. **Audit.** Read the target and applicable broader `AGENTS.md` files. Give every instruction in the target exactly one verdict against the target's bar below. Finish only when every instruction has a verdict. - **contradiction**: conflicts with another applicable instruction. Record both instructions and their source files. - **delete**: fails the no-op test because Codex would behave the same without it. This includes default behavior, vague directions, and platitudes such as "write clean code." - **dem...