JP Caparas

Eigent: The Open-Source Answer to Claude Cowork

Why you don’t need $200/month for an AI that can use your computer

How to use SWE-1.7 and SWE-1.7 Lightning in Devin CLI

Cognition’s newest model runs at a blazing 1,000 tokens per second in Devin CLI. Here’s how to install it, configure it, and put it to…

Superpowers explained: the popular Claude plugin that enforces TDD, subagents, and planning

A surgical look at how one developer systematised coding agent workflows

OpenCode’s creator on model freedom, Anthropic blocks, and the “double miracle” of open source

Highlights from Dax Raad’s interview with Nuno Maduro of Laravel and Pest fame; al

Vercel Launches Skills — “npm for AI Agents” with React Best Practices Built-in

An easy-to-follow guide to teaching your AI coding assistant 40+ performance patterns in one command

Codex Skills Are Just Markdown, and That’s the Point (A Jira Ticket Example)

Get rid of AGENTS.md bloat and speed up iteration by leveraging Codex CLI “skills”

Run GLM 5.2 in Codex CLI with OpenRouter

Keep your default Codex model intact, add GLM 5.2 as an opt-in profile, and verify routing in OpenRouter logs

Claude Code, but cheaper (and snappy): MiniMax M2.1 with a tiny wrapper

Keen to use Claude Code a lot but want more options on price? Here is a quick swap that keeps the workflow intact.

Claude Code — Use Hooks to Enforce End-of-Turn Quality Gates

Use CC’s lesser-known hooks to run deterministic, automated quality checks at the end of each turn and save precious time.

Devin CLI beyond the defaults

Most developers stop at the REPL. Here’s what the extensibility layer unlocks: hooks, skills, subagents, MCP servers, and fine-grained…

The modern VA’s survival guide to AI

Your practical, no-jargon guide to the tools that will keep you employed and thriving in the age of automation

Inside Claude Code’s agent teams and Kimi K2.5’s agent swarm

Give your coding agent browser superpowers with agent-browser

A friendly-yet-comprehensive guide to Vercel’s popular agent-browser CLI that works with Claude Code, OpenCode, and more!

Writing OpenCode agent skills: a practical guide with examples

Everything you need on your toolbelt to create reusable AI capabilities

The tiny library that gives AI agents eyes on your codebase

Inside element-source, the library that exploits dev-mode metadata to connect your UI to your source code

A guide to strict AI engineering in the agentic era

A practical, harness-agnostic playbook for using stop hooks, pre-push hooks, and strict defaults to force every generated line through a…

Claude Code’s task primitives: from single-threaded assistant to parallel powerhouse

A practical guide to Tasks, subagents, and parallel execution, with examples you can test yourself

How Laravel Boost works under the hood

Dissecting the MCP server that gives AI agents eyes into your Laravel app

CLAUDE.md lookup patterns explained: a bookmarkable guide

A bookmarkable guide to organising your CLAUDE.md files so Claude actually finds (and uses) them

Meta’s Muse Spark is the comeback nobody expected

After the Llama 4 debacle, Meta rebuilt its entire AI stack from scratch in nine months. The first result is promising.

Claude Code with Z.ai Vision MCP: Master the full toolbelt

The moment you start caring about screenshots, charts, or diagrams is the moment you realise this MCP server’s invaluability.

OpenCode: Auto-Lint Your AI Agent’s Code with a Post-Turn Biome Hook

AI coding agents are fast. They’ll scaffold a feature, refactor a module, and wire up tests before you’ve finished your coffee. But they’re…

How to Evaluate AI Agent Skills Without Relying on Vibes

A practical, platform-agnostic guide to skill evaluation, from first test case to production pipeline

What the Grok Build CLI leak means for your codebase

A step-by-step guide to checking whether your local-first coding tool stays local.

Qwen3.6-Plus is fast, cheap, but benchmarked against yesterday’s competition

Inside the release, the closed-source pivot, and the pricing play behind Alibaba’s newest frontier model