---
title: "Discussion on \"I grew my agent instruction file from 90KB to 147KB. Violations did not drop. The 8 rules I moved into code did.\" | Hashnode"
description: "Discussion on \"I grew my agent instruction file from 90KB to 147KB. Violations did not drop. The 8 rules I moved into code did.\". You have a rule you want your AI agent to follow. You write it in AGENTS.md. It gets broken. You write it in more detail. Still broken. You add another clause.\nAfter 48 days of doing that, my resident"
url: "https://hashnode.com/posts/i-grew-my-agent-instruction-file-from-90kb-to-147kb-violations-did-not-drop-the-8-rules-i-moved-into-code-did/6ab2cf53e07effab49016b76"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [I grew my agent instruction file from 90KB to 147KB. Violations did not drop. The 8 rules I moved into code did.](https://untactit.hashnode.dev/i-grew-my-agent-instruction-file-from-90kb-to-147kb-violations-did-not-drop-the-8-rules-i-moved-into-code-did?utm_source=hashnode&utm_medium=feed)

You have a rule you want your AI agent to follow. You write it in AGENTS.md. It gets broken. You write it in more detail. Still broken. You add another clause. After 48 days of doing that, my resident

Sep 22 · 5 min read · untactit.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#claude](https://hashnode.com/tag/claude)
-   [#programming-ciovqvfcb008mb253jrczo9ye](https://hashnode.com/tag/programming-ciovqvfcb008mb253jrczo9ye)
-   [#developer-tools](https://hashnode.com/tag/developer-tools)
-   [#productivity](https://hashnode.com/tag/productivity)

## Written by

[untactit](https://hashnode.com/@untactit)

@untactit

  
[View profile](https://hashnode.com/@untactit)

One control plane for the skills, rules and memory AI agents run on

Building untactit — one control plane for the skills, rules and memory your AI agents run on. Approve once, deploy everywhere. https://untactit.com

## Responses 1

Markdown supported · ⌘↵ to post

[Mihai\_LeanZero](https://hashnode.com/@mihaileanzero)

[Sep 22](https://hashnode.com/posts/i-grew-my-agent-instruction-file-from-90kb-to-147kb-violations-did-not-drop-the-8-rules-i-moved-into-code-did/6ab2cf53e07effab49016b76/comment/6ab2de072b0da52d7af599a8)

This is one of the more honest measurement posts I've read on this topic - the selection-bias and reverse-causation objections you raise against your own result are exactly the ones that needed raising, and most people wouldn't have bothered. One thing I'm curious about in the tier-2 design: since the injected top-3 set is chosen dynamically by recent violation count, a newly-written clause for a brand-new rule has to compete for one of those three slots against whatever is currently violating the most. If it doesn't win a slot early, does it get less reinforcement than an established high-violator, and does that change how fast it accumulates the three violations needed to earn a code gate in the first place? That would be a form of selection bias in which rules ever make it into Group A - gated because they violated often enough, fast enough, to win a top-3 slot, not necessarily because they mattered most. Tracking how long a rule waits before first cracking the top 3, separate from the recurrence count you're already logging, might surface that.
