onurkanbkrc
Awesome Codex Automations
Show HN: AgentLint – ESLint for your coding agents
https://github.com/samilozturk/agentlint
I’ve been spending a lot of time with coding agents lately. Across Claude Code, Cursor, OpenCode, Codex, and different models, I kept noticing that some people were getting much better results from the same tools. It became clear that this was not just about prompting.A big part of it was context drift. AGENTS.md, skills, rules, and workflows looked fine, but were no longer aligned with the...
The Anatomy of an Agent Harness
Show HN: SFT to convert a base language model into a conversational chat model
Show HN: Minisft – from base model to chat model
Re:ai;dr
on Friday February 13, 2026 @04:16AM (#47000693)
LLMs are trained on vast portions of the internet.
In that sense, they are essentially systems that mimic online content.
Therefore, what an AI generates often reflects the perspectives of the people who originally created the training data, rather than the true thoughts of the person prompting it.
Explanation of Microgpt Line by Line
Opus: Towards Efficient and Principled Data Selection in LLM Pre-Training
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
GLM-5: From Vibe Coding to Agentic Engineering
Last year, all my non-programmer friends built apps
Architecture of SQLite
Ask HN: How to Use `npx skills add` with On-Prem / Private Repos?
As you know, we can install the desired skill using the following command:npx skills add https://github.com/anthropics/skills --skill frontend-designIs there a way to achieve the same setup in an on-premise environment without exposing the repository publicly?