--- title: "#aicoding articles | Hashnode" description: "Explore 29 articles tagged #aicoding on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/aicoding" --- Tag # #aicoding 29 posts · 0 followers [techpotions](https://hashnode.com/@techpotions) · [Oct 21](https://hashnode.com/posts/claude-code-in-vs-code-setup-without-the-terminal-tax/6ad8edad282574a01e057d46) ### [Claude Code in VS Code: Setup Without the Terminal Tax](https://techpotions.hashnode.dev/claude-code-in-vs-code-setup-without-the-terminal-tax?utm_source=hashnode&utm_medium=feed) Stop typing claude in the terminal. The VS Code extension gives you inline diffs, plan review, and permission controls that keep you in the loop, without the terminal tax. Here’s how to set it up the right way. 7 min read · [techpotions.hashnode.dev](https://techpotions.hashnode.dev/claude-code-in-vs-code-setup-without-the-terminal-tax?utm_source=hashnode&utm_medium=feed) [ZyVOP](https://hashnode.com/@zyvop) · [Oct 21](https://hashnode.com/posts/how-to-use-gemini-4-argon-in-antigravity-on-google-ai-pro-no-99-99-ultra-plan-needed-69t0k/6ad86e8f395319ae4d54df06) ### [How to Use Gemini 4 Argon in Antigravity on Google AI Pro (No $99.99 Ultra Plan Needed)](https://blog.zyvop.com/how-to-use-gemini-4-argon-in-antigravity-on-google-ai-pro-no-99-99-ultra-plan-needed-69t0k?utm_source=hashnode&utm_medium=feed) How to use Gemini 4 Argon in Antigravity with Google AI Pro, check eligibility and usage limits, and avoid paying for Ultra unnecessarily. 5 min read · [blog.zyvop.com](https://blog.zyvop.com/how-to-use-gemini-4-argon-in-antigravity-on-google-ai-pro-no-99-99-ultra-plan-needed-69t0k?utm_source=hashnode&utm_medium=feed) [Khasky](https://hashnode.com/@khasky) · [Oct 18](https://hashnode.com/posts/practical-ai-coding-workflows-with-awesome-agent-skills/6ad51564ceb820a098a70662) ### [Practical AI Coding Workflows with Awesome Agent Skills](https://khasky.hashnode.dev/practical-ai-coding-workflows-with-awesome-agent-skills?utm_source=hashnode&utm_medium=feed) An AI agent can finish a feature, pass the tests, and still leave behind unnecessary abstractions, misleading comments, or a README that no longer matches the product. Asking it to "check everything" 8 min read · [khasky.hashnode.dev](https://khasky.hashnode.dev/practical-ai-coding-workflows-with-awesome-agent-skills?utm_source=hashnode&utm_medium=feed) [Mihai\_LeanZero](https://hashnode.com/@mihaileanzero) · [Oct 14](https://hashnode.com/posts/llm-regression-testing-for-jira-with-cognirunner/6acf0ca00426e3a85f480c54) ### [LLM Regression Testing for Jira with CogniRunner](https://leanzero.hashnode.dev/llm-regression-testing-for-jira-with-cognirunner?utm_source=hashnode&utm_medium=feed) LLM regression testing for a Jira workflow validator: 8 labelled issues, a Node script and CogniRunner's Rules API, run before you change the model or prompt. 32 min read · [leanzero.hashnode.dev](https://leanzero.hashnode.dev/llm-regression-testing-for-jira-with-cognirunner?utm_source=hashnode&utm_medium=feed) [Powerduck](https://hashnode.com/@powerduck) · [Oct 10](https://hashnode.com/posts/agent-breaks-dockerfile-because-never-seen-ci/6aca9165e131cce18c8d0535) ### [Your Agent Breaks the Dockerfile Because It Has Never Seen CI Run](https://blogs.powerduck.com/agent-breaks-dockerfile-because-never-seen-ci?utm_source=hashnode&utm_medium=feed) Agents edit Dockerfiles and CI YAML like application code. They miss layer cache order, build-arg scoping, and the gap between your laptop and the runner. 3 min read · [blogs.powerduck.com](https://blogs.powerduck.com/agent-breaks-dockerfile-because-never-seen-ci?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/agent-breaks-dockerfile-because-never-seen-ci/6aca9165e131cce18c8d0535) [Powerduck](https://hashnode.com/@powerduck) · [Oct 9](https://hashnode.com/posts/ai-tests-that-pass-but-dont-verify/6ac9fdc0cf0296b8c9d8ff3a) ### [Your AI Wrote a Test That Only It Can Pass](https://blogs.powerduck.com/ai-tests-that-pass-but-dont-verify?utm_source=hashnode&utm_medium=feed) When the model writes both the handler and the test, green CI proves almost nothing. Here's the cheap structural fix that catches the failure mode. 4 min read · [blogs.powerduck.com](https://blogs.powerduck.com/ai-tests-that-pass-but-dont-verify?utm_source=hashnode&utm_medium=feed) [Khasky](https://hashnode.com/@khasky) · [Oct 3](https://hashnode.com/posts/fable-becomes-the-advisor-to-opus-5-5-in-claude-code/6ac056a397a6376f24f88546) ### [Fable Becomes the Advisor to Opus 5.5 in Claude Code](https://khasky.hashnode.dev/fable-becomes-the-advisor-to-opus-5-5-in-claude-code?utm_source=hashnode&utm_medium=feed) With Opus 5.5 as the main model in a Claude Code session, a Fable quota can still go to work without Fable taking over the session. The /advisor fable command connects Fable as an advisor that Opus co 3 min read · [khasky.hashnode.dev](https://khasky.hashnode.dev/fable-becomes-the-advisor-to-opus-5-5-in-claude-code?utm_source=hashnode&utm_medium=feed) [ZyVOP](https://hashnode.com/@zyvop) · [Oct 2](https://hashnode.com/posts/ai-wrote-the-code-now-nobody-understands-it/6abf57b0e7d686025a84831f) ### [AI Wrote the Code. Now Nobody Understands It.](https://blog.zyvop.com/ai-wrote-the-code-now-nobody-understands-it?utm_source=hashnode&utm_medium=feed) Naur said in 1985 that the real product is the theory in the team's heads. AI can write the code, but it can't hold that theory for you. 6 min read · [blog.zyvop.com](https://blog.zyvop.com/ai-wrote-the-code-now-nobody-understands-it?utm_source=hashnode&utm_medium=feed) [Khasky](https://hashnode.com/@khasky) · [Sep 27](https://hashnode.com/posts/awesome-agents-md-for-any-agent-and-any-stack/6ab8a3fa0e4c49b2aac3edcf) ### [Awesome AGENTS.md for Any Agent and Any Stack](https://khasky.hashnode.dev/awesome-agents-md-for-any-agent-and-any-stack?utm_source=hashnode&utm_medium=feed) I reverse-engineered popular coding-agent instruction repos and distilled their best ideas into a stack-agnostic AGENTS.md. 📦 The core rules cover small, focused changes, security boundaries, debuggi 5 min read · [khasky.hashnode.dev](https://khasky.hashnode.dev/awesome-agents-md-for-any-agent-and-any-stack?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/awesome-agents-md-for-any-agent-and-any-stack/6ab8a3fa0e4c49b2aac3edcf) [Tw93](https://hashnode.com/@hitw93) · [Sep 8](https://hashnode.com/posts/from-mole-cli-to-mole-for-mac-what-i-learned/6aa02d4f9951c229edf5e9df) ### [From Mole CLI to Mole for Mac: What I Learned](https://hitw93.hashnode.dev/from-mole-cli-to-mole-for-mac-what-i-learned?utm_source=hashnode&utm_medium=feed) What I learned building a native Mac app alongside an open-source CLI: safer cleanup, accessible design, user feedback, and indie development. 18 min read · [hitw93.hashnode.dev](https://hitw93.hashnode.dev/from-mole-cli-to-mole-for-mac-what-i-learned?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/from-mole-cli-to-mole-for-mac-what-i-learned/6aa02d4f9951c229edf5e9df)