AI

This article will introduce how to use Codex Subagents to develop a product from scratch. You will see how multiple agents collaborate to build a space shooter game that runs directly in the browser, covering the entire process from design documents, visual assets, to testing and validation.

This article introduces an efficient approach for repetitive programming tasks at scale: organize tasks into a CSV, have Codex launch independent subagents for each row to process in parallel, then write the consolidated results back to an output CSV. Whether it's batch-generating unit tests, checking compatibility for React Query upgrades, or translating comments across an entire project, this pattern turns what would normally be done one-by-one into a process that finishes in minutes.

Treat Codex Subagents as dedicated parallel teammates that handle the most time-consuming and easily overlooked exploration and verification tasks in daily coding, boosting your efficiency.

Superpowers uses a variety of skills to train AI from a 'coding intern' into a 'professional engineer'.

Over the past year, AI has rapidly transformed from a 'tool' into a 'collaborator'. But many engineers, as they use it, gradually fall into a dangerous illusion: that AI can replace decision-making, even replace responsibility. The reality is quite the opposite. The more capable the AI, the greater the demand for humans to possess stronger constraint, judgment, and information-expression skills.

A Skill (or Skills) is a reusable skills package for AI agents—typically a folder containing task instructions, scripts, templates, and reference materials. The AI loads these resources on demand when handling relevant tasks, enabling more reliable and repeatable execution of specific work.

OpenCode Go is a low-cost coding model subscription plan launched by OpenCode. Its purpose is not to create a new model, but to provide heavy-duty developers with a unified model pool and billing method.

What is a Tool in the Vercel AI SDK? Think of it as a "function with instructions": the instructions are for the model, while the function body is for your own code.

Hermes Agent is an open-source self-evolving AI agent framework open-sourced by Nous Research at the end of February 2026. As of early May, it had already surpassed 100,000 stars on GitHub, making it one of the fastest-growing open-source projects of 2026. This lightweight Python-based framework's standout feature is that it "gets smarter with use" — it automatically learns from each task, creates and improves its own skills, and builds long-term memory.

Matt Pocock's Skills project is an engineering skill library for AI coding assistants (such as Claude Code). By modularizing standard software development workflows, it addresses the core pain point of inconsistent quality in AI-generated code.