I find writing a good CLAUDE.md is done by running /init, and having the LLM write it. If you need more controls on how it should work, I would highly recommend you implement it in an unavoidable way via hooks and not in a handwritten note to your LLM.
Had me in the first half. But from the "The Microsecond Window" chapter and on...;
> No warning. No error. Just different methods that make no sense.
> This is why write barriers exist. They're not optional extras for C extension authors. They're how you tell the garbage collector: "I'm holding a reference. Don't free this
It's all ChatGPT LinkedIn and Instagram spam type slop. An unfortunate end to an otherwise interesting writeup.
This is the first time I see "steering rules" mentioned. I do something similar with Claude, curious how it looks for them and how they integrate it with Q/Kiro.
Those rules are often ignored by agents. Codex is known to be quite adhering, but it falls back to its own ideas, which run counter to rules I‘ve given it. The longer a session goes on, the more it goes off the rails.
I'm aware of the issues around rules as in a default prompt. I had hoped the author of the blog meant a different mechanism when they mentioned "steering rules". I do mean something different, where an agent will self-correct when it is seen going against rules in the initial prompt. I have a different setup myself for Claude Code, and would call parts of that "steering"; adjusting the trajectory of the agent as it goes.
With Claude Code, you can intercept its prompts if you start it in a wrapper and mock fetch (someone with github user handle „badlogic“ did this, but I can’t find the repo now). For all other things (and codex, Cursor) you‘d need to proxy/isolate all comms with the system heavily.
Yes they do, most of the time. Then they don’t. Yesterday, I told codex that it must always run tests by invoking a make target. That target is even configurable w/ parameters, eg to filter by test name. But always, at some point in the session, codex started disregarding that rule and fell back to using the platform native test tool directly. I used strong language to steer it back, but 20% or so of context later, it did that again.
"steering rules" is a core feature baked into Kiro. It's similar to the spec files use in most agentic workflows but you can use exclusion and inclusion rules to avoid wasting context.
There's currently not an official workflow on how to manage these steering files across repos if you want to have organisation-wide standards, which is probably my main criticism.
> The reported half-life of glyphosate in soil varies from two to 197 days with a typical field half-life of 47 days being suggested.[56] Soil and climate conditions affect glyphosate's persistence in soil. The median half-life of glyphosate in water varies from a few days to 91 days.[56] At a site in Texas, half-life was as little as three days. A site in Iowa had a half-life of 141.9 days.[94] The glyphosate metabolite AMPA has been found in Swedish forest soils up to two years after a glyphosate application.
It has a lower half-life in water, and a lower half-life when it's warmer.
I store my oats both dry and cold.
As for cancer, I don't know - but it certainly is giving everyone parkinsons.
But you see - this is the whole problem. Every time I tried looking into it myself all I could find was that "dessicating crops with glyphosate is safe because it breaks down before it makes it into your food". If that is just simply not true or at the very least "true but only in ideal conditions that happen 5% of the time" then we're all screwed and no one seems to care.
> Do you hear that noise in the distance? It’s me sigh-ing. (...) Yes, maintaining good documents for specific tasks is a good idea. I keep a big list of useful docs in a docs folder as markdown.
I'm not that familiar with Claude Code Plugins, but it looks like it allows integrations with Hooks, which is a lot more powerful than just giving more context. Context is one thing, but Hooks let you codify guardrails. For example where I work we have a setup for Claude Code that guides it through common processes, like how to work with Terraform, Git or manage dependencies and the whitelisting or recommendation towards dependencies. You can't guarantee this just by slapping on more context. With Hooks you can both auto-approve or auto-deny _and_ give back guidance when doing so, for me this is a killer feature of Claude Code that lets it act more intelligently without having to rely on it following context or polluting the context window.
Cursor recently added a feature much like Claude Code's hooks, I hope to see it in Codex too.
