---
title: "Comment by Mihai_LeanZero on \"Good Agentic Workflows Are Born From Pain, Not Principles\" | Hashnode"
description: "The \"audit the rules as well as the code\" section is the part I'd push on hardest, because in my experience that's exactly where these efforts stall -- by the t"
url: "https://hashnode.com/posts/good-agentic-workflows-are-born-from-pain-not-principles/6aaee98131b8b540d787fd9b/comment/6ab00715325ee698b4811a7c"
---

[Discussion](https://hashnode.com/posts/good-agentic-workflows-are-born-from-pain-not-principles/6aaee98131b8b540d787fd9b)

Comment [Good Agentic Workflows Are Born From Pain, Not Principles](https://hashnode.com/posts/good-agentic-workflows-are-born-from-pain-not-principles/6aaee98131b8b540d787fd9b)

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

[Sep 20](https://hashnode.com/posts/good-agentic-workflows-are-born-from-pain-not-principles/6aaee98131b8b540d787fd9b/comment/6ab00715325ee698b4811a7c)

The "audit the rules as well as the code" section is the part I'd push on hardest, because in my experience that's exactly where these efforts stall -- by the time AGENTS.md is forty rules deep, nobody remembers which incident produced rule seventeen, so nobody dares remove it. What's worked for me is tagging each rule with a one-line trailer naming the incident and date it came from ("added after an agent reimplemented locking in the in-memory adapter, 2026-03"), so an audit becomes a question you can actually answer -- has this situation recurred, or is the underlying code now structurally incapable of it -- instead of a vague fear of regressing something you can't name anymore. Costs almost nothing to write and turns rule pruning from a judgment call into something closer to a changelog review.

[Thomas Portelange](https://hashnode.com/@lekoala)

[Sep 20](https://hashnode.com/posts/good-agentic-workflows-are-born-from-pain-not-principles/6aaee98131b8b540d787fd9b/comment/6ab00715325ee698b4811a7c#reply-6ab056e2b17a533f034c4541)

Ah yes, six months later, nobody remembers the pain :-) but adding a timestamp is not a real solution either: a rule should have a recoverable reason for existing. And that's the point, because once your agents.md grows too big, then you might need to refactor it. What stays is a simple rule, and a good reason for it. This rule might move to another document, or be merged with another one.

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

[Sep 29](https://hashnode.com/posts/good-agentic-workflows-are-born-from-pain-not-principles/6aaee98131b8b540d787fd9b/comment/6ab00715325ee698b4811a7c#reply-6abbffbc6647e2d39e23e8aa)

The date's doing less work than the incident description sitting next to it -- that's the part meant to carry the recoverable reason. The timestamp is just there so you can tell whether the thing that produced the rule could still happen today or got patched out since. Agreed the whole file needs to stay refactorable rather than just prunable line by line, the trailer's only useful up to the point you're merging or moving rules around, not as an argument against ever restructuring the document.

[Vlad Zoff](https://hashnode.com/@vladzoff)

[Oct 13](https://hashnode.com/posts/good-agentic-workflows-are-born-from-pain-not-principles/6aaee98131b8b540d787fd9b/comment/6ab00715325ee698b4811a7c#reply-6ace2cd6eafb63db6852c70e)

The incident link is valuable, but I'd be careful not to let the timestamp do too much work. It tells you when a rule was added, not whether the failure is still reachable. I'd want each rule to point to a reproducible regression test or the specific structural condition it prevents, so pruning can be based on evidence rather than the age of the incident.

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

[Oct 15](https://hashnode.com/posts/good-agentic-workflows-are-born-from-pain-not-principles/6aaee98131b8b540d787fd9b/comment/6ab00715325ee698b4811a7c#reply-6ad0698b479de991a5dd79eb)

Fair, a test that reproduces the failure is the stronger version and the trailer is the cheap fallback for rules that can't be tested. If a rule can be pinned by a regression test or a structural check (a lint, a type that makes the bad state unrepresentable), the trailer should just name that test and the date becomes noise. The rules I'd still keep a dated incident note for are the behavioral ones, where there's no test to point at, and there the date at least tells you whether the underlying cause could have been patched out since. Pruning a rule whose test still fails without it is easy, pruning one with no test is where the guessing starts.
