anthropics/claude-code

yeah, I actually just re-use claude-code .devcontainer: https://github.com/anthropics/claude-code/tree/main/.devcontainer I especially like the firewall it has.

Anthropic ships an official plugin to create linters for you based on your Claude Code history or instructions, it’s great. You can vibe code your lint rules per repo. https://github.com/anthropics/claude-code/tree/main/plugins/hookify

…al caveats, and I'm only running them on my own phone. I ask Claude (not code) to help me with the spec, I give it some bullet points and it asks a bunch of clarifying questions then gives me a spec. I put that in a new directory, fire up Claude and use the ralph-loop plugin ( https://github.com/anthropics/claude-code/tree/main/plugins/ralph-wiggum ): > /ralph-loop:ralph-loop "Implement the iOS app described in app-spec.md. You have access to xcode CLI tools. You should write tests and use them to verify your work. The task will be complete when the app is fully implemented, with all tests passing. Output <promise>COMPLETE</promise> when finished." --max-iterations 50 --completion-promise "…

When you say Claude Code, what model do you refer to? CC with Opus still outperforms Codex (gpt-5-codex) for me for anything I do (Rust, computer graphics-related). However, Anthropic restricted Opus use for Max plan users 10 days or so ago severly (12-fold from 40h/week down to 5h week) [1]. Sonnet is a vastly inferioir model for my use cases (but still frequently writes better Rust code than Codex). So now I use Codex for planning and Sonnet for writing the code. However, I usually need about 3--5 loops with Codex reviewing, Sonnet fixing, rinse & repeat. Before I could use one-shot Opus and review myself directly, and do one polish run following my review (also via Opus). That was poss…

It was something that was used for token efficiency. Most of the settings and use cases are quite poorly communicated but asking Claude to review the latest release changelog ( https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md ) is quite useful. Combined with @"claude-code-guide (agent)" to read it's own docs for settings/configs is super helpful. The quite useful tool is to use /opusplan along with /codex:rescue ( https://github.com/openai/codex-plugin-cc ) means you get quite a strongly reviewed plan using native claude + codex without having to implement the mostly useless trust-me-bro plugins and other bs.

You really have to a) use Opus and b) use the frontend-design skill for decent results. https://github.com/anthropics/claude-code/blob/main/plugins/frontend-design/skills/frontend-design/SKILL.md

Anthropic's own frontend-design skill attempts to do that. You can install it in Claude Code, or you can tweak it to be closer to your own style: https://github.com/anthropics/claude-code/blob/main/plugins/frontend-design/skills/frontend-design/SKILL.md But what I find works best is to point Claude at a design system documentation website (your own company's or another public source) and tell it to use that design style. It usually does OK, and the results are usually much more in line with that style and not as Claude-y.

The main Claude Code GitHub repo even has a Devcontainer config: https://github.com/anthropics/claude-code It's a great starting point, and can be customized as needed. With the devcontainer CLI, you can even use it from a terminal, no GUI/IDE required.

The Ralph Wiggum Plugin, so you don't need the bash while loop: https://github.com/anthropics/claude-code/blob/main/plugins/ralph-wiggum/README.md The README.md has prompt examples.

The most accessible way to start experimenting would be the Ralph loop: https://github.com/anthropics/claude-code/tree/main/plugins/ralph-wiggum You could also work backwards from this paper: https://arxiv.org/abs/2512.18470

[BUG] Claude Code repeatedly creates backdoors and noops critical security code #59018 https://github.com/anthropics/claude-code/issues/59018

…auto-closed by a bot when they've had no activity for a while and are missing information needed to reproduce (usually a version and steps, or a /feedback ID). Nothing is triaged solely by counting" In reality all issues in this repo are subject to time-based auto-closing, unless they collect a number of upvotes. See details at https://github.com/anthropics/claude-code/issues/87647 . Therefore, I wonder whether the internal review process described in the Anthropic's blog for internal repos also results in such issues, and whether Anthropic has a internal way to measure and mitigate that. The blog post says: > "When someone wants to understand a part of the codebase, they ask Claude to wr…

I am not trying to get into a flame war, but I have seen a lot of complaints about Claude Code, not to mention their huge backlog of bug reports ( https://github.com/anthropics/claude-code/issues ) on GitHub. Just because they have lowered the bar for software quality and people have accepted it, does not mean that they are delivering quality software. I know at the very least we agree that these ideas are being re-explored in 2026, but I don't see evidence that it's a positive improvement for software development/quality. How many sites or services does one use on a daily basis that are just broken? Is that really the best our industry can aspire to? EDIT: also, from the software engineer …

And here is the issue raised in github: https://github.com/anthropics/claude-code/issues/14980 TLDR: They don't care.

Claude Code has 13.4k open bugs: https://github.com/anthropics/claude-code/issues Show me a popular open source project that doesn't have a large number of open issues and I'll show you one that has a triage bot auto-close them.