Claude Code – Everything you can configure that the docs don't tell you (buildingbetter.tech)

What’s up with scrolling on that page?! I was locked into a page region several times until I finally gave up. Safari/Orion iOS current

That example classifier is horrendous. A simple substring search for ls/cat/echo/etc?

  echo blah blah >> ~/.ssh/authorized_keys

Related from then:

The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

https://news.ycombinator.com/item?id=47586778

claude package has ten new versions published per week, and one new model every few months, one should definitely not rely on some undocumented tricks around it: it'll change, it'll break deep ultra-specific configurations

Some of these things are documented. For example the model in frontmatter in skills is documented here: https://code.claude.com/docs/en/skills#frontmatter-reference

(It's not easy to find though, and lots of other docs doesn't mention it or link to this)

[dead]

[flagged]

most of these are in fact documented, the rest either no longer exists, is still gated by feature flags (i checked), or has little use to most users.

you can however convince claude to create a local command with the extracted prompts for stuff like autodream

Claude Code’s feature cardinality is breathtaking. At this rate, the next pope will be from Anthropic

I'm curious about that "magic doc" feature. Is that meant to go in CLAUDE.md or a project file? Does the file need to be mentioned during the session or does Claude automatically search for all mentions of the "magic doc" header in the project?

> Honest status

> Not at 100% - and I want to be straight about why that's a longer road...

https://github.com/user-attachments/assets/961eff6c-0060-45d...

I just want Claude Code to stop giving up on achieving tasks. It's so annoying. Even with `/goal` or the new `ultracode` it gives up constantly.

My project is very complex (https://github.com/mohsen1/tsz) but Codex has no problem keep grinding without stopping like that

[dead]

Have fun finding out that the undocumented feature you rely on suddenly stops working.

Is there an AI Coding Agent application structure emerging that is more or less universal across llm models? Is anyone collecting and writing on how to understand this architectural style?

[flagged]

Anyone else pick up on the fact that the article was released on Apr 01, 2026?

Clearly AI-generated writing (confirmed with Pangram). Amazed this has so many upvotes—are people even reading the article?

@dang I know you have so far resisted a rule for AI-generated content (as we now have for comments), but I personally would prefer a flag for articles so that I don't waste my time on slop.

[flagged]

This article is 2 month old and partly outdated, Some features have been documented, for example the auto mode: https://code.claude.com/docs/en/auto-mode-config#define-trus...

yup, it's super old

can i ask claude to generate its own config? "you're me, create your perfect set of config files."

Wow, not one mention of the env vars that have a far greater influence on how the models actually work under the hood - https://code.claude.com/docs/en/env-vars

Very important for bedrock deployments and other not-as-standard deployments

Key for how I've deployed it - disable adaptive thinking, max thinking tokens, disable telemetry, etc

[flagged]

It's a great guide that is necessary because the documentation of Claude code is so lacking. It's a shame really, trillions of dollars, but not one man hour to make an agent on the ci to write the doc and a pr. It frustrates me, it has been like that for months, it's like nobody cares or find this normal.

i'm pretty sure that the hook behavior (at least) is documented, ad i was already aware