Claude Code Workflows
Daily-driver tricks, hidden commands, and productivity patterns for power users of Claude Code. Includes /compact, /btw, /simplify, /batch, effort levels, opus plan mode, token hacks, git worktrees, auto mode, buddy easter egg.
Time Horizons Benchmark Numbers Are Understated by ~35% — Here's the Statistical Reason Why
Using a fixed-slope logistic fit — arguably more valid — pushes the published Time Horizons numbers up 35%. The co-author explains the methodology gap.
Claude Code Found a UTC Timezone Bug by Reading Conversation Transcripts — No API Logs Required
Claude Code read turn 16 of a voice agent transcript and identified a Cal.com UTC bug the developer never spotted. Here's how it works.
Claude Code /ultra review: 5 Things You Need to Know Before Running It ($5–$20 Per Run)
Ultra review spins parallel reviewer agents but costs $5–$20 per run and requires a Claude account, not just an API key. What to know first.
What Is the Ultra Review Command in Claude Code? How to Catch Bugs Before They Ship
Claude Code's /ultra review spins up parallel reviewer agents to independently verify bugs before you merge. Here's how it works and when to use it.
Claude Code Remote Routines: Run Automations on Anthropic's Cloud While Your Laptop Is Closed
Claude Code remote routines run on Anthropic's cloud (4 vCPUs, 16GB RAM) against a GitHub repo — no laptop required, no .env files, no token limits.
How to Build an Agentic Operating System: 9 Components You Need
An agentic OS is just clever context management. Learn the 9 components—identity files, memory, skills, and more—that make AI tools actually work.
OpenAI Codex vs Claude Co-work in 2026 — Which AI Agent Platform Wins for Knowledge Workers?
Codex now has built-in image gen and consumer onboarding. Claude Co-work has Blender, Adobe, and Ableton connectors. Here's how to choose.
How to Use OpenAI Codex for Everyday Work: 10 Use Cases Beyond Coding
OpenAI Codex isn't just for developers. Discover 10 practical use cases for knowledge workers including workflow audits, form creation, and slide deck drafting.
What Is the PIV Loop? The Core Methodology for AI-Assisted Software Development
The PIV loop—Plan, Implement, Validate—is the repeatable process for handling individual coding tickets with AI agents. Here's how to apply it to any project.
How to Build a Minimal Agent Harness in Python: Step-by-Step with Session Persistence
Build a working agent harness in under an hour using append-only JSON session logs and dynamic system prompt assembly from agents.md files.
What Is MCP (Model Context Protocol)? The Standard for AI Tool Integrations
MCP is the open standard that lets AI agents connect to apps like Notion, Slack, and HubSpot. Here's how it works and why it matters for automation.
32 Claude Code Tricks That Actually Change How You Ship
From /compact and plan mode to git worktrees and ultrathink, these Claude Code techniques reduce token waste and improve output quality at every level.
How to Run Parallel AI Coding Agents With Git Worktrees
Run multiple Claude Code sessions simultaneously without conflicts. This guide covers git worktrees, database branching, and port isolation for parallel agents.
Claude Code Desktop App: The Features That Change How You Work
Claude Code's desktop app now shows file structure, renders markdown, and runs parallel sessions. Here's what changed and why it matters for builders.
Git Worktrees for AI Coding: How to Run Multiple Agents Without Conflicts
Git worktrees give each AI coding agent its own isolated codebase so parallel sessions never overwrite each other's changes. Here's how to set it up.
How to Build a Spec-Driven App with a Real Backend, Database, and Auth
Spec-driven development compiles a plain-language spec into full-stack apps with real backends and databases — no drag-and-drop, no prompt-and-hope.
How to Deploy AI Agents to Production: 7 Things You Must Get Right
Before shipping a multi-user AI agent, lock down model control, prompt versioning, guardrails, budget limits, MCP auth, tracing, and evals.
MCP Servers Explained: What They Are and Why Every AI Agent Needs Them
MCP servers give AI agents structured access to tools, APIs, and data sources. Learn what they are, how authentication works, and when to use them.
The 3 Levels of AI Proficiency: From Answers to Autonomous Agents
Most people jump from basic AI use to autonomous agents and fail. This framework explains the progression from AI for answers to AI working for you.
The 3-Level AI Progression Framework: From Answers to Autonomous Agents
Most people skip Level 2 and fail at agents. This framework explains how to progress from AI for answers to AI as a daily partner to AI working for you.
What Is Context Management in AI Agents and Why It Determines Output Quality
Context rot degrades agent outputs as sessions grow. Learn how to segment memory layers, use reference files, and keep context lean for better results.
Claude Code Parallel Sessions: How to Work on Multiple Projects Simultaneously
Claude Code now supports parallel sessions with split-panel views and a built-in terminal. Here's how to use them to ship faster across multiple repos.
What Is a Dark Factory Codebase? The Future of Autonomous Software Development
A dark factory is a codebase where AI agents plan, implement, test, and ship code with no human review. Here's how it works and whether it's ready.
What Is a Dark Factory? The AI Coding Pattern That Ships Code Without Human Review
A dark factory is a codebase managed entirely by AI agents. Learn the five levels of AI coding autonomy and how to build one responsibly.