This is a problem that people mostly have to solve themselves. Like, I've been working with Claude for almost a year now and I have never once seen it write "Arrow Anti-Pattern" code. That, and much of the rest, would be fluff in my projects. Agent instructions are best learned from experience project-by-project.
Yes, the interesting part about seeing other people's agent.md files, is getting to see what issues they have with working with agents. Seems different people run into very different issues, which probably is caused by how differently we work. So a the file probably should be personalised.
A bunch of these should be enforce with linting, that way people who still hand-craft code get the same kind of feedback, e.g. Always use {}, even on a one-line "if" statement. & Keep function names short. Less than 30 characters.
Then this one really is a pattern that creates a lot of churn:
- Add a small, to the point, comment to explain what the block does and why. Use examples when possible. Propose ASCII drawings to explain complete systems.
I would rather bet that people don’t know that their problem has been solved for ages. Either they don’t know about the tools or can’t make the leap to think of using something like awk or sed to quickly script out their use cases. Or even quickly draft up a quick function/plugin in something like vim, emacs, sublime,…
In “The Pragmatic Programmer”, the power of unix tools and editor fluency is well argued. There are plenty of other books like “Unix Power Tools”, “Small, Sharp Software Tools”,…
I'm not always forced for time. And the time is slightly less when you know how to use man (with apropos and whatis, a few unix conventions (null vs newline when piping text) and the quirks/feature of your shell.
Yeah, I've actually found in my own testing and usage of LLMs that this is where I get a lot of benefit. I already have fd, ripgrep, etc. installed and know how to use them, but it's not hard to tell the LLM to do it and it often finds things just as well. Or even better.
It's especially handy on modern style code where things get broken up across a multitude of files based on convention.
Right. I've really struggling to get AI to stop explaining the what. It seems to add it to the commits, PRs, code, wherever it feels like. I've put in multiple places to not write the "what", but the "why", and in multiple ways, but it still does it in one or other place.
The best way I've found to solve this is using LLM as CI - use a small cheap model to inspect the diff and look for those kinds of comments. Prompt left to the observer but using `claude -p` / `codex exec` gets you a lot cleaner output usually, and makes robots fight robots instead of you constantly having to reprompt and it ignoring you.
One thing I don’t get with a lot of these agents.md and other skills are… why not throw as much mechanical checks and other stuff at the repo to constrain as you want instead of asking a non-deterministic agent (squishy or non-squishy) to maintain it.
With the mechanical routes, we get checks, failures, and so much more. A bit wild to me.
Make an agent operate within defined constraints and yell at it when it doesn’t.
I forbid my agents from adding any comments. I review the code and add comments manually. If I can't understand something despite having the context then I throw away the code instead of having an LLM generate comments to explain what it did. This way the code stays readable/debuggable by humans.
If you don’t trust the code to write a decent comment, why trust it write good code?
Of course, ensuring compilation or other checks can verify some code, which it can’t do for comments. But comments still serve the same purpose as human comments.
If I understand correctly, it’s not that the LLM can’t write a good comment, it’s that you want to be able to interpret and understand the generated code without comments - and in that process end up writing comments yourself.
I don’t get that argument. Most of the time by the end of the session the comments from the agent encode tricky details that I told the agent to write down so it stops making “simplifying” assumptions. Thus comments at the end of a couple days of agent-only coding, when I start to actually read and edit the prose, contain the details which aren’t possible to know from reading the local code. It may help that my last couple sessions before I start reading the code myself are variations on telling the agent to self-review and improve the comments in specific ways, so the comments left are only those the agent thought remain meaningful at clarifying unexpected interactions between the local code and other code that needs to be referenced to understand it.
The actual code output has improved a lot over the past year. I’ve found it matches existing patterns better, and the code is succinct so I can easily tweak it if I don’t like the way the agent wrote it.
The problem with comments is that LLMs tend to copy their verbose chat output format and insert session/prompt specific details. It makes me think that LLMs aren’t constrained in their comment output the same way they are with their code output
Add "Don't add any code comments anywhere" to your system prompt.
If the model doesn't follow this, you want to start using a better model ASAP, because SOTA models for the last year or so, been able to following this without an issue.
> This way the code stays readable/debuggable by humans.
Please take the following as expressed with genuine curiosity: Do you not use an editor with syntax highlighting and collapsible comments?
At least on JetBrains you can configure the editor to collapse all comments on open and to have the comments displayed in a low-contrast color. This way, LLMs add a bunch of comments, but it doesn't affect your actual experience in trying to read the code. If you encounter code that seems inexplicable, then and only then would you expand the comment to see if that helps you understand.
Sometimes I try to add comments in a new session and the agent just don't have enough context for it to give a comprehensive sentence with full context on the why, then the agent will just describe what it does.
Human comment is in another level to answer the questions mainly like "why do it like this" for the later collaborators or the forget-ed self, so the important blocks live when it is needed and can be eliminated when it does not.
Also, the language model might not fully understand the code then add a comment, then the next iteration will treat assumptions in the comment as the truth.
> If the human can read/understand it well enough to comment it, then it is readable by humans.
No, because the one who is writing the comment has context later reader dont. The writer knows what the requirements are, what he was trying to achieve and what he struggled to comprehend. Writer also presumably spent more time trying to understand it then the person coming later should.
It is not perfect, but the delta between 'cannot understand what agent wrote' and 'it makes sense to me right now' is already an improvement. That it may not be sufficient, doesn't mean it isn't a necessary condition.
Besides, it has always been like this. I sometimes can't even understand some of the things I wrote myself a couple of months ago, because I forgot the context. Good comments and documentation will help you re-acquire the context you need, not completely eliminate it.
Comments should be written only when there is (hidden) complexity or external context strictly required. Otherwise it is just easier to read the code. Comments then signal one of two things: a) the following code is really complex and I need to tread carefully, or b) this code is complicated, and could benefit from a refactor.
In regards to agentic coding, all these comments are extra contents, driving down quality while increasing cost. Agents also tend to be inconsistent about updating comments, I've had cases repeatedly where a comment did not match the code, at which point it is just a documentation liability.
I'm not convinced, yet, that eliminating LLM-generated comments is the right path for me. I do review everything written by an LLM and some comments are actually pretty good, but sometimes I'm just too tired to try to figure out how to reword an oddly worded one.
I just added Sanglard's rules to my ~/.claude/CLAUDE.md file, did another code review, and found some LLM-generated comments were really hard to understand. I think they're due to invented metaphors and flowery language instead of using standard terms, so I've added this:
- Comments must be literal. Don't invent figurative language for what a plain technical term already says — write "rows still reference it," not "rows still wear it."
Improving LLM code generation is an iterative process. I'm glad people share their efforts to improve it.
Labs have now long understood that ASCII drawing is a core skill needed for coding agents. However, I would not trust them understanding what an existing drawing means, unless it has generated itself.
Incidentally, I'm from the opposite school and consider every “if” followed by a braced block a smell.
If a conditional body needs a block, it's doing enough to deserve a name, so I promote it to a single named call, à la "Extract till you drop".
Another phrase for this is "functional decomposition", which usually is a good thing.
Better yet is to identify conditional execution paths as early as possible in order to obviate conditionals in the call tree. For example, identifying a "create a new something" verses an "update an existing something" based on the workflow initially invoked greatly simplifies service and/or persistent store logic.
Linters and static analysis -> setup as hooks in your harness. Don’t rely on CLAUDE.md because it’ll ignore it a lot.
> ASCII drawings in code
Please don’t this is super obnoxious. Make proper diagrams and kee them in knowledge base. Link out to them if you need to and let the agent fetch them via MCP or API or whatever if it wants them.
Even the why sometimes shouldn’t be a comment, unless it’s very immediate to the code itself. What’s often more necessary is a high level overview of the design of the solution, because that’s what drives the design of the code and link disparate section. Especially the glossary , which you let you understand the name of the symbols (variables, struct. functions,…) used in the code.
It’s like learning the culture associated to a foreign language instead of trying to translate each single word with a dictionary.
The cost of custom linters has like any other code dropped through the floor. I'm sprinkling all kinds of linters over my latest projects. It seems some people are still sleeping on this, expecting great code from the agents.
They're fast and deterministic and I run them in git pre-commit.
This! I also saw lot of potential work that could be done by linting tools. Remember to always prefer mechanical guards than agent instructions, as they cannot ignore them.
> Then this one really is a pattern that creates a lot of churn:
> - Add a small, to the point, comment...
As if you even need to tell Claude to add comments. Over the past few weeks I've noticed Claude over-commenting everything. Massive PRs where you realise that fully half or more of the lines that have changed are comments.
It's no good at all: it just pollutes the context, causes token churn, ablates quality, and makes getting to a high quality outcome considerably slower and more expensive.
I get that sometimes knowing why a thing is the way it is can be useful and valuable, but this is what commit comments are for in my mind.
I've had to tell Claude to stop commenting code because the behaviour has become so problematic.
> The what _is_ the code.
Exactly.
If I don't know what the code does because it's arcane and not commented I can simply ask the LLM to explain it to me. I don't need an essay in comment form.
We've been using agents heavily for all code for a long time now in my company - everyone has comprehensive & opinionated AGENTS.md customisations & they're widely shared & discussed. Almost everything in this post seems incredibly naive day-one LLM user mistakes - especially everything related to coding style at line level granularity.
We've had non-LLM tooling for these kinds of standards for many years now & the great thing about agents is they're already versed in said tooling. If you haven't got a decent lint setup, ask your agent to set one up. It'll give you much better guarantees than this slop which is just going to drift from model to model & is completely unverifiable.
A comment is just a summary of the code in an abstraction that's easier to follow. Let's say you have a simple function which would produce an almost as large comment, yes obviously useless. If the function is large enough, yeah summarizing it as a comment is a good idea.
Now you might say, don't write huge functions. Sure I agree, but most codebase or teams are not super disciplined enough. So comments are a compromise.
>> A comment is just a summary of the code in an abstraction that's easier to follow.
I disagree. The code already tells you what it does. A summary has low value.
Comments should be for explaining the why: the reason the function uses a particular algorithm even if it's a bit slower, or why the return format is an unconventional shape or contains redundant bits. This is so that someone coming in later (either a human or agent) doesn't get confused or think that the function needs refactoring.
Summary comments have ended up as the bane of my existence everywhere I've worked, for one simple reason: they go stale and there's no way to prevent it from happening.
That's your experience and it's valid. For me documentation AND comments have been useful on occasion.
The core thing that I agree with is that comments (or docs) can get stale and not follow what is actually being executed. The way I work with it is by being structured, consistent and follow standards. Unfortunately for me, not all developers follow the same guidelines.
At my work we have basically banned "what" comments for blocks of code. JSDoc comments can still document what a function does at a high level but it should not go into implementation details unless they are important to anyone using the function. And any comments inside the function should always be for explaining why, not what. The "what" of a piece of code should be self explanatory by just reading the code. If it's not, then you likely should rewrite it to be more clear (sometimes hard-to-read code is necessary and then a "what" comment would be appropriate, but this is rare).
"What" comments almost always end up falling out of date or even sometimes being slightly incorrect from day one. Incorrect comments lead to confusion and bugs. If a comment says some code does X but the code actually does Y, then you don't know whether the comment is just out of date or if Y is actually a bug. But if a comment explains the intention of the code and the code contradicts that intention, then you know it's likely a bug.
No, why should I have to remember to @ in every prompt? Or ask contributors to remember. It just makes it easier to make human mistakes. I have better things to do than micromanagement. There is huge value in auto-included context.
The GP wrote @ it from the agents.md file, not from the prompt. Their point was that instead of writing "how to contribute" instructions for agents, you could explain that in the CONTRIBUTING.md and link it from your agents file, so both humans and agents read it from one place.
These days that sounds like a really good idea. 6 months ago, AGENTS.md would have contained a lot of instructions that would have been embarrassing to write out for a human audience.
This has not been my experience at all. I have been using this skill[0] for several weeks and when I ask it to rewrite existing AI slop docstrings to use this convention they are nearly always 10-20% smaller, plus easier to read and mostly free from the traditional "tells" of AI writing.
Do you give the model access to the ASD-STE100 spec for reference/review or are you just assuming that enough of it is baked into the model for it to mostly adhere to it?
I have been using it for a few weeks, and it significantly improves the quality of the docstrings and code comments, as well as the readability of spec docs.
I have also added a few key bullet points to my AGENTS.md and have found the results to be very effective and generating plans and code that looks like something I would have written:
-----------
## planning, design and spec docs
- the highest design goal is simplicity -- in our systems and our mental model -- even if if means edge cases are unaddressed and could potentially fail
- please practice "ya ain't gunna need it" (YAGNI) do not add unnecessary guardrails
- do not plan to add caching, many layers of unnecessary abstraction or other premature optimizations
- look for places where adding or clarifying an invariant would simplify the code or the overall system
please specifically try to avoid:
- redundant calculations or duplicated work
- duplicated conditionals or state-machine logic
- storing state that can be derived from other state, which could drift and become out of sync over time
- leaky abstractions across layers of the application
- multi-line comments explaining a variable name or a single statement. well chosen names and design should makes these unnecessary, as the code is self-documenting
Anything that goes into the context window has that going for it. That's a huge part of why Claude's gone absolutely bonkers with genuine, brutal honesty. The system prompt's absolutely stuffed full of those keywords, so now every single output is tainted with that right from the start.
Since we are sharing our AGENTS.md, I thought I'd share my own, because most of the time, this is pretty much all you need for LLMs to write good code, everything else can be added per project:
----
*Convergence rule*
Every substantial task must end in exactly one of three states:
A. Success
The intended capability works in the real path and the real motivating case materially improves.
B. Meaningful progression
The capability is not complete, but one genuine blocker is removed and the next blocker is isolated with evidence.
C. Honest stop
Further work would require overbroad scope expansion, excessive debt, brittle patching, or tangled logic. Stop and report the reason with concrete evidence.
Do not continue producing patches once the work stops converging.
Do not confuse activity with progress. A failed attempt is only acceptable if it leaves behind a narrower problem, stronger evidence, or a justified stop.
Any partial work must leave the codebase in a cleaner, more legible, and more diagnosable state than before.
----
A lot of the article's AGENTS.md just feel like telling the LLM agents either something they already know (for example, most of the time they know to use exhaustive switch/match statements instead of "arrow anti-pattern") or seems actively harmful ("keep function names short" seems arbitrary and may cause the LLMs to write weird abbreviations for functions that are harder to read and review.
Not very often, but when it happens, usually it's time to sit down and brainstorm architecture with the LLM to figure out how to proceed next instead of looping blindly.
The problem is that linting the AGENTS.md is risky work. Everything added there was in response to mistakes. If I remove some instruction I run the risk of repeating the mistake.
"- Don't touch blocks of code unrelated to the feature you implement. e.g. Don't add comments to a block of code if you did not create it or modify it. As much as possible try to minimize the number of changed lines when implementing a feature."
The feature where you ask the LLM to fix one thing and it fixes three things.
> As much as possible try to minimize the number of changed lines when implementing a feature
Great way to get LLMs to start making an endless profusion of methods instead of adding parameters to or switching to a richer return type from an existing method, in my experience.
I’m tired of seeing “get_total_rounded_up” + “get_total_float” bloat when a few changes to unrelated code to round floats to ints would keep the method API surface small.
An earlier version of Gemini used to do this a lot to me back when I used it for some light tinkering around on my projects. "Oh by the way, I fixed a misspelling in a comment file completely unrelated to the feature you asked for, so I fixed that as well, shall I commit everything now?" GAHHH. NO.
These days I have an instruction in my default AGENTS.md to bring issues unrelated to the prompt to my attention when found, but never to just automatically fix them.
I find too often that models do the opposite - they'll pile small targeted band-aids on code blocks based on new requirements, etc, when having them analyze whether a changed (broader) design would result in a far better overall design?
this was what i was doing 3-4 months ago. i just have AI write/update my agents.md file now as i find problems. i also have ai keep a set of design documentation that it can update as it goes too. oh and he should try omp+codex/xhigh, he will probably be less annoyed.
From FAB's AGENT.MD:
> - Avoid magic numbers and strings by extracting recurring or meaningful values into descriptive constants (const) or enums.
---
I've been seeing the same thing with models like GPT5.6 and Opus4.8 in GH Cop CLI. They still introduce magic numbers, and in Scala they often put an entire 10-line Spark expression inside an if condition instead of extracting it into a meaningfully named value to keep "if" readable. I wonder when common sense instructions will be baked into the models.
What's the point of agents.md if you just use an LLM on a codebase?
Just say, complete this bit like how the rest is...
Even then they aren't great at it. Idk, the best case use for LLMs are extremely specific requests, for example "write an evaluator for this byte code and if you can't ask for clarification"
The ultimate specification language is code anyways so you might as well stick a to-do, a comment describing the semantics of the function and say "okay codex fill the to-do"
But in summary: the more bloated your AGENTS.md is, the worse the context consumption gets. The best approach I use is telling the agent to first think about what it needs to do, then choose which rules apply. I got 100% consistency across every area of my projects.
My most impactful section has been on voice. It's impact is that I don't go insane, which is pretty high value. (Not putting quote blocks so people can copypasta):
## Voice
Rule #1: No AIisms
Avoid the stock phrases and rhetorical tics that mark AI prose. Say the thing
plainly instead. Be concise and direct.
*Banned phrases* — never use these, or close variants:
- "Honest" or "honestly"
- "Exactly" or "exact, unless referencing a specific quantity or measurement
- "You're absolutely right" / "You're right to push back" / "Great question"
I would describe this as 13 code writing rules (interpreted to be at least 16 - Starting with reduce code indentation) plus a commit message instruction set which I chose to ignore - because it's style-specific and not interesting to me.
8 or 9 of these rules are not necessary. Basic CS is not something I have needed to ask agents, I use, to follow. eg Explaining that you need explicit interfaces is not a necessary instruction, nor is leveraging early return. Unclear instructions are of limited utility. What "Let the reader of the code breathe" or "reduce code indentation" means is subjective and will rarely be effective. If you want to measure, ask it to output a string when it applies a rule. You'll figure out what works, what doesn't and how often, quickly.
There's 3 or 4 style choices.
The rest are not something I would use, but we all get burned by different things so I get it.
One thing I've figured out of that qwen3.6 35b refuses to use 2 space indentation for python code, although it claims to be doing it. I know for a fact it is an easy thing to do.
> Explicitly ask the harness to reload agent.md. "Reload agent.md" is enough when I see code quality dropping.
Having the LLM re-read the file is really silly and a common bug in harnesses. Even sillier is when the harness allows a file to be compressed away during summarisation. The harness should compose the context so this doesn't happen. Files should be "added" (by LLM or human) and then always be injected into context the same way forever. "Reload this file" is not something you should ever have to type.
170 comments
[ 0.20 ms ] story [ 42.0 ms ] threadThen this one really is a pattern that creates a lot of churn:
- Add a small, to the point, comment to explain what the block does and why. Use examples when possible. Propose ASCII drawings to explain complete systems.
The what _is_ the code.
Which is kind of cool if you’re unaware enough to know to do it yourself.
Oh, and find. Agents use find a lot.
If you've ever used an LLM to deal with ffmpeg you'll know exactly what I mean.
You think of what you need, and you type it. No need to even ask “what options should I use?”
In “The Pragmatic Programmer”, the power of unix tools and editor fluency is well argued. There are plenty of other books like “Unix Power Tools”, “Small, Sharp Software Tools”,…
It's especially handy on modern style code where things get broken up across a multitude of files based on convention.
With the mechanical routes, we get checks, failures, and so much more. A bit wild to me.
Make an agent operate within defined constraints and yell at it when it doesn’t.
> Make an agent operate within defined constraints and yell at it when it doesn’t.
And tell it what the constraints are.
I wish my coworkers would adopt this.
I’m sick of reading a fucking Charles dickens novel for every fucking tiny function
Use that script as a super linter.
That’s the only way I found to strictly enforce some rules, like the no comments rule, without enforcing them against my own changes or old code.
Of course, ensuring compilation or other checks can verify some code, which it can’t do for comments. But comments still serve the same purpose as human comments.
The problem with comments is that LLMs tend to copy their verbose chat output format and insert session/prompt specific details. It makes me think that LLMs aren’t constrained in their comment output the same way they are with their code output
If the model doesn't follow this, you want to start using a better model ASAP, because SOTA models for the last year or so, been able to following this without an issue.
which claims "do" rules persist much better then "don't" rules.
Please take the following as expressed with genuine curiosity: Do you not use an editor with syntax highlighting and collapsible comments?
At least on JetBrains you can configure the editor to collapse all comments on open and to have the comments displayed in a low-contrast color. This way, LLMs add a bunch of comments, but it doesn't affect your actual experience in trying to read the code. If you encounter code that seems inexplicable, then and only then would you expand the comment to see if that helps you understand.
Human comment is in another level to answer the questions mainly like "why do it like this" for the later collaborators or the forget-ed self, so the important blocks live when it is needed and can be eliminated when it does not.
If the human can read/understand it well enough to comment it, then it is readable by humans.
No, because the one who is writing the comment has context later reader dont. The writer knows what the requirements are, what he was trying to achieve and what he struggled to comprehend. Writer also presumably spent more time trying to understand it then the person coming later should.
Besides, it has always been like this. I sometimes can't even understand some of the things I wrote myself a couple of months ago, because I forgot the context. Good comments and documentation will help you re-acquire the context you need, not completely eliminate it.
>> This way, LLMs add a bunch of comments, but it doesn't affect your actual experience in trying to read the code
by saying that at least reading the code and generating comments is forcing some understanding. Is there a disagreement in that?
You're saying that it's not (necessarily) enough understanding, which may be true but beside the point.
The next developer doing a review will see it. The next agent iteration will see it.
If the comment is wrong (even slightly) or redundant, that will help noone.
Comments should be written only when there is (hidden) complexity or external context strictly required. Otherwise it is just easier to read the code. Comments then signal one of two things: a) the following code is really complex and I need to tread carefully, or b) this code is complicated, and could benefit from a refactor.
In regards to agentic coding, all these comments are extra contents, driving down quality while increasing cost. Agents also tend to be inconsistent about updating comments, I've had cases repeatedly where a comment did not match the code, at which point it is just a documentation liability.
I just added Sanglard's rules to my ~/.claude/CLAUDE.md file, did another code review, and found some LLM-generated comments were really hard to understand. I think they're due to invented metaphors and flowery language instead of using standard terms, so I've added this:
- Comments must be literal. Don't invent figurative language for what a plain technical term already says — write "rows still reference it," not "rows still wear it."
Improving LLM code generation is an iterative process. I'm glad people share their efforts to improve it.
LLMs are very bad at ASCII drawings.
https://medium.com/data-science/why-llms-suck-at-ascii-art-a...
Labs have now long understood that ASCII drawing is a core skill needed for coding agents. However, I would not trust them understanding what an existing drawing means, unless it has generated itself.
Better yet is to identify conditional execution paths as early as possible in order to obviate conditionals in the call tree. For example, identifying a "create a new something" verses an "update an existing something" based on the workflow initially invoked greatly simplifies service and/or persistent store logic.
https://github.com/unclebob/fitnesse
> Write in-code comments that describe _why_ code or a class does what it does, but not _what_ it does. The "what" should be self-evident.
> ASCII drawings in code
Please don’t this is super obnoxious. Make proper diagrams and kee them in knowledge base. Link out to them if you need to and let the agent fetch them via MCP or API or whatever if it wants them.
Even the why sometimes shouldn’t be a comment, unless it’s very immediate to the code itself. What’s often more necessary is a high level overview of the design of the solution, because that’s what drives the design of the code and link disparate section. Especially the glossary , which you let you understand the name of the symbols (variables, struct. functions,…) used in the code.
It’s like learning the culture associated to a foreign language instead of trying to translate each single word with a dictionary.
Agreed. One of the first rules I toss into Biome is `noNestedTernary` - LLMs seem to adore completely unreadable nested expressions.
They're fast and deterministic and I run them in git pre-commit.
Isnt that too late? I would want the agent to stumble into this as early as possible in the agentic loop, eg at the same time as compiler.
But that's a pretty good idea, wonder if there is a way...
> - Add a small, to the point, comment...
As if you even need to tell Claude to add comments. Over the past few weeks I've noticed Claude over-commenting everything. Massive PRs where you realise that fully half or more of the lines that have changed are comments.
It's no good at all: it just pollutes the context, causes token churn, ablates quality, and makes getting to a high quality outcome considerably slower and more expensive.
I get that sometimes knowing why a thing is the way it is can be useful and valuable, but this is what commit comments are for in my mind.
I've had to tell Claude to stop commenting code because the behaviour has become so problematic.
> The what _is_ the code.
Exactly.
If I don't know what the code does because it's arcane and not commented I can simply ask the LLM to explain it to me. I don't need an essay in comment form.
We've been using agents heavily for all code for a long time now in my company - everyone has comprehensive & opinionated AGENTS.md customisations & they're widely shared & discussed. Almost everything in this post seems incredibly naive day-one LLM user mistakes - especially everything related to coding style at line level granularity.
We've had non-LLM tooling for these kinds of standards for many years now & the great thing about agents is they're already versed in said tooling. If you haven't got a decent lint setup, ask your agent to set one up. It'll give you much better guarantees than this slop which is just going to drift from model to model & is completely unverifiable.
Now you might say, don't write huge functions. Sure I agree, but most codebase or teams are not super disciplined enough. So comments are a compromise.
I disagree. The code already tells you what it does. A summary has low value.
Comments should be for explaining the why: the reason the function uses a particular algorithm even if it's a bit slower, or why the return format is an unconventional shape or contains redundant bits. This is so that someone coming in later (either a human or agent) doesn't get confused or think that the function needs refactoring.
Summary comments have ended up as the bane of my existence everywhere I've worked, for one simple reason: they go stale and there's no way to prevent it from happening.
The core thing that I agree with is that comments (or docs) can get stale and not follow what is actually being executed. The way I work with it is by being structured, consistent and follow standards. Unfortunately for me, not all developers follow the same guidelines.
"What" comments almost always end up falling out of date or even sometimes being slightly incorrect from day one. Incorrect comments lead to confusion and bugs. If a comment says some code does X but the code actually does Y, then you don't know whether the comment is just out of date or if Y is actually a bug. But if a comment explains the intention of the code and the code contradicts that intention, then you know it's likely a bug.
That way everyone benefits.
Then the model will go discover what it needs to.
**Always use ASD-STE100 Simplified Technical English
Disclaimer: I saw this listed in some other HN post that I can' locate right away.
[0]: https://github.com/AminBlg/SimpleEnglish
I have been using it for a few weeks, and it significantly improves the quality of the docstrings and code comments, as well as the readability of spec docs.
I have also added a few key bullet points to my AGENTS.md and have found the results to be very effective and generating plans and code that looks like something I would have written:
-----------
AI users are overwhelmingly addicts who are lying to themselves and the people around them. I've lost patience for their kind.
A. Success The intended capability works in the real path and the real motivating case materially improves.
B. Meaningful progression The capability is not complete, but one genuine blocker is removed and the next blocker is isolated with evidence.
C. Honest stop Further work would require overbroad scope expansion, excessive debt, brittle patching, or tangled logic. Stop and report the reason with concrete evidence.
Do not continue producing patches once the work stops converging.
Do not confuse activity with progress. A failed attempt is only acceptable if it leaves behind a narrower problem, stronger evidence, or a justified stop.
Any partial work must leave the codebase in a cleaner, more legible, and more diagnosable state than before. ----
A lot of the article's AGENTS.md just feel like telling the LLM agents either something they already know (for example, most of the time they know to use exhaustive switch/match statements instead of "arrow anti-pattern") or seems actively harmful ("keep function names short" seems arbitrary and may cause the LLMs to write weird abbreviations for functions that are harder to read and review.
What's the difference between a "genuine blocker" and a "blocker"? Why is the next blocker not genuine? Does it become genuine only after isolation?
local llm remain more in line like that.
I esp liked:
"- Don't touch blocks of code unrelated to the feature you implement. e.g. Don't add comments to a block of code if you did not create it or modify it. As much as possible try to minimize the number of changed lines when implementing a feature."
The feature where you ask the LLM to fix one thing and it fixes three things.
I kept noticing this in diffs.
Great way to get LLMs to start making an endless profusion of methods instead of adding parameters to or switching to a richer return type from an existing method, in my experience.
I’m tired of seeing “get_total_rounded_up” + “get_total_float” bloat when a few changes to unrelated code to round floats to ints would keep the method API surface small.
These days I have an instruction in my default AGENTS.md to bring issues unrelated to the prompt to my attention when found, but never to just automatically fix them.
I've been seeing the same thing with models like GPT5.6 and Opus4.8 in GH Cop CLI. They still introduce magic numbers, and in Scala they often put an entire 10-line Spark expression inside an if condition instead of extracting it into a meaningfully named value to keep "if" readable. I wonder when common sense instructions will be baked into the models.
- new model comes out and a bunch of it becomes obsolete
- they get flat out ignored, esp. with larger context windows. The ai just responsds with, "your'e right I shouldn't have done that"
- they sometimes end up poisoning the reasoning because the rule gets interpreted in an unintended way.
Just say, complete this bit like how the rest is...
Even then they aren't great at it. Idk, the best case use for LLMs are extremely specific requests, for example "write an evaluator for this byte code and if you can't ask for clarification"
The ultimate specification language is code anyways so you might as well stick a to-do, a comment describing the semantics of the function and say "okay codex fill the to-do"
- https://www.minid.net/2026/7/14/how-to-automatise-with-ai
But in summary: the more bloated your AGENTS.md is, the worse the context consumption gets. The best approach I use is telling the agent to first think about what it needs to do, then choose which rules apply. I got 100% consistency across every area of my projects.
In the post there's also a replica of one of projects rules I use, feel free to provide feedback: https://github.com/meerita/monorepo-nextjs-golang-rust-pytho...
Conditional logic .agents/rules/16-conditional-logic.md
Identifiers and UUIDv7 .agents/rules/18-identifiers-and-uuidv7.md
Thanks for sharing this approach, I'll give it a shot in my mono repo project.
## Voice
Rule #1: No AIisms
Avoid the stock phrases and rhetorical tics that mark AI prose. Say the thing plainly instead. Be concise and direct.
*Banned phrases* — never use these, or close variants:
- "Honest" or "honestly"
- "Exactly" or "exact, unless referencing a specific quantity or measurement
- "You're absolutely right" / "You're right to push back" / "Great question"
- "load-bearing", "full stop", "worth stating plainly", "worth noting"
- "the honest answer", "to be clear", "let me be direct"
- "it's not just X, it's Y" — and every cousin: "not X but Y", "X is not Y; it is Z", "this isn't X — it's Y"
- "this matters because", "that reduction is useful, because", "here's the thing", "and that's the trap"
- "in other words", "put differently", "better posed:", "the deeper point is"
- "delve", "leverage", "harness", "unlock", "tapestry", "realm", "seamless", "robust", "holistic", "paradigm", "cutting-edge", "game-changer", "transformative", "elevate", "empower", "streamline", "landscape", "ecosystem" (unless literally software packaging)
- "genuinely", "structurally", "fundamentally", "quietly", "meaningfully" as depth-manufacturing adverbs
- "Ultimately," / "At the end of the day," as a closing summary
- "serves as", "stands as", "represents", "marks a" where "is" works
- "say the word"
*Banned moves:*
- The aphoristic closer. Don't end on a line engineered to sound quotable.
- The suspense hook — "the cleanest way to think about this is this:"
- Anticipate-and-rebut — raising an objection only to knock it down.
- Meta-signposting — "Three caveats belong up front", "below I'll explain".
- Reflexive hedging stacks: "almost", "tends to", "roughly", "largely", "with few exceptions".
- Litotes as confidence: "not difficult", "not optional", "no small thing".
- AI-humility asides about being a language model.
- Self-ranking your own points: "most importantly", "the key insight here".
- Em dash overuse. One per paragraph at most; a comma usually works.
- Colon-reveals and dramatic mid-sentence pauses where "and" or "but" is the real conjunction.
- Fragment rhythm. Not every third sentence. Like this.
- Uniform structure — every paragraph three sentences, every sentence the same length. Vary it.
- Mirrored clauses: "X does A; Y does B" balanced for symmetry alone.
- Validate-then-precise: "That's correct, and we can make it precise."
Vary the openers. Don't answer three messages in a row with the same shape.
I would describe this as 13 code writing rules (interpreted to be at least 16 - Starting with reduce code indentation) plus a commit message instruction set which I chose to ignore - because it's style-specific and not interesting to me.
8 or 9 of these rules are not necessary. Basic CS is not something I have needed to ask agents, I use, to follow. eg Explaining that you need explicit interfaces is not a necessary instruction, nor is leveraging early return. Unclear instructions are of limited utility. What "Let the reader of the code breathe" or "reduce code indentation" means is subjective and will rarely be effective. If you want to measure, ask it to output a string when it applies a rule. You'll figure out what works, what doesn't and how often, quickly.
There's 3 or 4 style choices.
The rest are not something I would use, but we all get burned by different things so I get it.
Having the LLM re-read the file is really silly and a common bug in harnesses. Even sillier is when the harness allows a file to be compressed away during summarisation. The harness should compose the context so this doesn't happen. Files should be "added" (by LLM or human) and then always be injected into context the same way forever. "Reload this file" is not something you should ever have to type.