---
title: "Comment by Ethan Frost on \"AI Hygiene for APEX Developers\" | Hashnode"
description: "this pattern transfers way beyond apex — i hit the same fork on nuxt 3 / go-zero work. the move from \"one-off prompts\" → \"structured skills + repo-level instruc"
url: "https://hashnode.com/posts/ai-hygiene-for-apex-developers/69eea0e33d6a492cdd64269d/comment/69f0ab2510a70b3335afde32"
---

[Discussion](https://hashnode.com/posts/ai-hygiene-for-apex-developers/69eea0e33d6a492cdd64269d)

Comment [AI Hygiene for APEX Developers](https://hashnode.com/posts/ai-hygiene-for-apex-developers/69eea0e33d6a492cdd64269d)

[Ethan Frost](https://hashnode.com/@ethanfrost)

[Apr 28](https://hashnode.com/posts/ai-hygiene-for-apex-developers/69eea0e33d6a492cdd64269d/comment/69f0ab2510a70b3335afde32)

this pattern transfers way beyond apex — i hit the same fork on nuxt 3 / go-zero work. the move from "one-off prompts" → "structured skills + repo-level instruction files" is the right framing.

one thing i underestimated for months: **versioned skill files, not just a single AGENTS.md**. one big AGENTS.md mutates every week and you lose the audit trail of "what exactly was the agent told when it shipped that bad PR". splitting into `.skills/<feature>.md` per subsystem + actual git commits per change bought me back blame-able context — same hygiene principle as schema migrations.

+1 on "verify, don't autopilot." what worked for me: keep a `replay.md` alongside skill files containing the actual prompts that produced each skill. when a skill drifts, re-derive instead of patch — kills the "where did this rule come from?" archaeology.

been collecting community-shared versions of these patterns (skill files / AGENTS.md / MEMORY shards / MCP configs) on [https://tokrepo.com/en](https://tokrepo.com/en) — public registry where you can grep how others structure their AI hygiene before reinventing. apex tag is sparse there atm but cross-stack patterns transfer well.
