I Cut My OpenCode Token Usage by 96% - Here's How
I reduced my token usage from 7,000 to just 300 tokens per request in Opencode — a 96% reduction. In this video, I walk through exactly how I did it and how you can too. If you're using Opencode (or any AI coding assistant), you're probably burning through tokens faster than you need to. I'll show you the specific changes I made to slash my token consumption without sacrificing quality or context. GitHub: https://github.com/agardnerIT/opencod... What you'll learn: Why most Opencode setups waste tokens The settings and workflows that cut my usage by 96% How to maintain code quality while using a fraction of the tokens Tools mentioned: Opencode #AI #Coding #Opencode #Tokens #AIProductivity #SoftwareEngineering #DevTools #CodingTips

▶︎
Agents are being poisoned...

▶︎
OpenCode Tutorial for Beginners: Setup, Agents, Skills & MCP

▶︎
This NEW Japanese AI System Matches Fable 5?

▶︎
GLM 5.2 on Dual Strix Halo (256GB): Worth it?

▶︎
This will make sense

▶︎
What Nobody Tells You About Being a Quant

▶︎
I stopped using /grill-me for coding. Here’s what I use instead:

▶︎
Fugu AI just BEAT Fable and Mythos...

▶︎
Full Walkthrough: Workflow for AI Coding — Matt Pocock

▶︎
"Got any hobbies?"

▶︎
L8 Principal's Agentic Engineering Workflow

▶︎
Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

▶︎
I asked Claude Code to make me as much money as possible

▶︎
Stop Prompting Claude. Use Karpathy's Method Instead.

▶︎
Finally. Agent Loops Clearly Explained.

▶︎
Leave Windows 11 Idle for 24 Hours and Watch What Happens

▶︎
This Open Source Repo Just Solved Claude Code's #1 Problem

▶︎
Can a Local LLM Actually Replace Claude or Codex for Coding?

▶︎
MIT Just Revealed the AI Bubble's Fatal Flaw

▶︎
