Agentic coding, open-weight LLMs, benchmarks, deployment costs.https://notes.hasanarief.dev/https://notes.hasanarief.dev/notes/max-plan-1m-context-value/https://notes.hasanarief.dev/notes/max-plan-1m-context-value/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.Fri, 17 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/mobile-agent-steering-vs-remote-control/https://notes.hasanarief.dev/notes/mobile-agent-steering-vs-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.Wed, 15 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/tmux-agent-orchestration/https://notes.hasanarief.dev/notes/tmux-agent-orchestration/Why a plain terminal multiplexer beats bespoke agent frameworks for long generation runs, and five tmux practices each learned from a real failure.Mon, 13 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/skipping-permission-prompts-safely/https://notes.hasanarief.dev/notes/skipping-permission-prompts-safely/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.Sat, 11 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/llm-wiki-knowledge-base/https://notes.hasanarief.dev/guides/llm-wiki-knowledge-base/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.Fri, 10 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/ai-bubble-good-thing/https://notes.hasanarief.dev/notes/ai-bubble-good-thing/Trillions committed, Nvidia the most valuable company ever, and the measured productivity gains are tiny. Notes on using the overbuild and surviving the crash.Thu, 09 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/autoresearch-parameter-optimization/https://notes.hasanarief.dev/notes/autoresearch-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.Thu, 09 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/codex-cloud-vs-cli/https://notes.hasanarief.dev/notes/codex-cloud-vs-cli/Where OpenAI Codex cloud tasks actually run, what the CLI keeps that cloud cannot, and a decision split for routing work between them.Tue, 07 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/codex-skills-discovery/https://notes.hasanarief.dev/notes/codex-skills-discovery/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.Sun, 05 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/claude-code-reference/https://notes.hasanarief.dev/guides/claude-code-reference/A maintained third-party reference to Claude Code: the agentic loop, built-in tools, context window behavior, environments, safety model, and extension layer.Sun, 05 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/fable-5-vs-opus-48-goal-loop/https://notes.hasanarief.dev/notes/fable-5-vs-opus-48-goal-loop/Fable 5 returned at double the price of Opus 4.8, with days-long autonomy as the headline capability. A comparison with Claude Code's /goal loop, sourced.Sat, 04 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/open-weight-llms-for-coding/https://notes.hasanarief.dev/guides/open-weight-llms-for-coding/Open-weight coding LLMs as of July 2026, GLM-5.2, Kimi K2.7, DeepSeek-V4, with the VRAM math, GPU rental prices, and when self-hosting beats an API.Sat, 04 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/openai-codex-reference/https://notes.hasanarief.dev/guides/openai-codex-reference/A maintained third-party reference to OpenAI Codex: the CLI, IDE, cloud and app surfaces, AGENTS.md configuration, skills, MCP support, plans and access.Sat, 04 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/claude-code-setup/https://notes.hasanarief.dev/guides/claude-code-setup/Practical Claude Code setup for 2026: install on Mac, Linux or Windows, authenticate, run /init, add skills and hooks, and stay safe with git.Wed, 01 Jul 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/agent-orchestration-patterns/https://notes.hasanarief.dev/guides/agent-orchestration-patterns/A map of agent orchestration in 2026: five coordination levels from a single session to agent teams, with failure modes and selection criteria.Sat, 27 Jun 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/codex-cli-vs-claude-code/https://notes.hasanarief.dev/guides/codex-cli-vs-claude-code/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.Wed, 24 Jun 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/agents-md-best-practices/https://notes.hasanarief.dev/guides/agents-md-best-practices/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.Fri, 19 Jun 2026 00:00:00 GMThttps://notes.hasanarief.dev/guides/agentic-coding-best-practices/https://notes.hasanarief.dev/guides/agentic-coding-best-practices/Field-tested agentic coding best practices from daily Claude Code and Codex work: verification loops, context discipline, hooks, and review gates.Mon, 15 Jun 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/mcp-servers-i-use-daily/https://notes.hasanarief.dev/notes/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.Tue, 09 Jun 2026 00:00:00 GMThttps://notes.hasanarief.dev/notes/why-this-notebook-exists/https://notes.hasanarief.dev/notes/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.Wed, 03 Jun 2026 00:00:00 GMT