How do I run multiple threads in Claude at the same time?
I don't want to wait on one Claude Code thread before starting the next — here's what's actually available today for running several at once on the same project.
Posts
Longer reflections and practical guides from using AI tools.
Is Claude getting worse (at least compared to Codex)?
A trending question, a 100-hours-vs-20-hours comparison, and my own recent experience that Codex has been unusually solid.
Why can a $20 Claude plan show hundreds of dollars of API usage?
Why a Claude subscription can appear to deliver hundreds of dollars of API-token value, and why that does not mean the numbers are directly comparable.
How I track Claude Code and Codex usage in real time
A practical look at local tools for tracking live usage, tokens, sessions, and history across Claude Code and Codex.
How do I run a fleet of coding agents?
I've got more work than one agent session can handle, and I want a manager layer that farms it out and tracks it cross models
Fleet of agents: a survey of orchestration tools (WIP)
Optio, Paperclip, Gas Town, or Claude's own Agent Teams — which one actually manages a fleet of agents instead of just watching them? A field survey with a verdict.
Give AI work a next action
A simple checkpoint pattern for resuming AI work across sessions and repos.
Can I schedule Claude Code for when my usage resets?
How to schedule cloud and local Claude Code tasks for when the next subscription usage window begins.
Can Stripe Projects remove the credential dance from AI deployments?
A hands-on look at using Stripe Projects to provision Cloudflare services and credentials for coding agents.
Skills are to AI what libraries were to software
Why reusable agent skills resemble software libraries, and how the emerging package ecosystem compares with npm.
The Future Is Apps Inside AI, Not AI Inside Apps
From AI-powered tools to AI as the operating system.
Breaking Up with Beads
Notes and commands from migrating a project from Beads to Taskgraph.
The Design Repo Pattern: Keep Your Inspiration Separate from Your Code
A simple way to keep design research and experiments separate from an application's implementation repository.
OpenClaw: What It Is, Why It Matters, and Early Lessons on Security
An introduction to OpenClaw agents and early lessons about deploying them securely.
