bergen, norwayvol. i · no. 20 · July 17, 2026rss feed

Hasan Arief

A lab notebook on agentic coding, open-weight models, and what they cost to run

Section

Agentic Coding

Working practice for coding with agents: harness setup, verification loops, context discipline, and what holds up in daily use.

Note

1M-context Opus on the $200 Max plan: what is included and what is capped

The $200 Max plan is not unlimited, Anthropic says so plainly. Yet 1M-context Opus is included, and at six concurrent agents I have yet to hit a cap.

Note

Steering agents from my phone: a terminal stack vs Claude Code Remote Control

Tailscale, tmux, mosh, and a mobile terminal let me steer long agent runs from my phone. Why that plain stack still outperforms Remote Control for me, for now.

Note

tmux as a transparent orchestrator for long agent sessions

Why a plain terminal multiplexer beats bespoke agent frameworks for long generation runs, and five tmux practices each learned from a real failure.

Note

When skipping Claude Code permission prompts is safe, and when it is not

Claude Code users approve 93% of permission prompts, so manual mode and bypass converge. What prevents catastrophe is the environment I run in, not the flag.

Guide

Karpathy's LLM wiki: a knowledge base your coding agent maintains

Karpathy's LLM wiki: point a coding agent at a markdown folder and let it maintain the knowledge base. What it is, why it earns its place, and how to set it up.

Note

The AI capex bubble, and what I am building while it lasts

Trillions committed, Nvidia the most valuable company ever, and the measured productivity gains are tiny. Notes on using the overbuild and surviving the crash.

Note

Karpathy's autoresearch, and its loop for parameter optimization

Karpathy's autoresearch runs an AI agent in a keep-or-discard loop. I examined its techniques, then applied the loop to parameter search where a grid stalls.

Note

Codex cloud vs Codex CLI: which surface for which work

Where OpenAI Codex cloud tasks actually run, what the CLI keeps that cloud cannot, and a decision split for routing work between them.

Note

How Codex CLI discovers skills: the .agents filesystem layout

Where OpenAI Codex looks for skills on disk, in what order, how SKILL.md files load, and how the same format ports between coding agents.

Guide

Setting up Claude Code in 2026: install, CLAUDE.md, skills, hooks, memory

Practical Claude Code setup for 2026: install on Mac, Linux or Windows, authenticate, run /init, add skills and hooks, and stay safe with git.

Guide

Agent orchestration patterns in 2026: subagents, teams, and pipelines

A map of agent orchestration in 2026: five coordination levels from a single session to agent teams, with failure modes and selection criteria.

Guide

Codex CLI vs Claude Code: what I learned running both daily

An honest Codex CLI vs Claude Code comparison from running both daily on one codebase: strengths, config interop, and the two-model workflow that emerged.

Guide

AGENTS.md and CLAUDE.md best practices: one instruction file for every coding agent

How to write AGENTS.md and CLAUDE.md files: what to include, the 200-line size target, monorepo precedence, imports, and one-source-of-truth setup.

Guide

Agentic coding best practices: what works in 2026

Field-tested agentic coding best practices from daily Claude Code and Codex work: verification loops, context discipline, hooks, and review gates.

Note

The two MCP servers I use daily

Two MCP servers remain in my daily agentic coding configuration: Playwright MCP and mobile-mcp. Notes on the selection rule that filters the rest.

Note

Why this notebook exists

Opening note: what I research, why these notes are public, and the rules this site follows, dated entries, sourced numbers, no sponsors.