Claude Code: Keeping It Running for Hours
How I use todo lists and agents to keep Claude Code running autonomously for over an hour, processing entire task lists within the 200k token context window.
How I use todo lists and agents to keep Claude Code running autonomously for over an hour, processing entire task lists within the 200k token context window.
When agents were released, the documentation was too vague for me to understand what they were for. One effective way to use them is as a more powerful form of slash commands.
Ever start a long-running Claude Code task and walk away, only to come back later and find it finished ages ago? I solved this by configuring Claude Code to send notifications to my phone when it completes tasks.
Building on my workflow with /todo and /commit, I've created the /worktree
command to enable parallel development on multiple tasks using Git worktrees.
Utility commands I use with Claude Code for code maintenance and cleanup, particularly for handling the LLM's tendency to over-comment code.
I've written two slash commands for Claude Code that form the core of my development workflow: /todo
implements one task and /commit
commits it.
Simon Willison wrote "I'm disappointed at how little good writing there is out there about effective prompting."
I worked hard on these prompts and think they're effective. This post covers how I configure claude
using CLAUDE.md
files and settings.json
to control the behavior of the Claude code CLI.
Simon Willison wrote "I'm disappointed at how little good writing there is out there about effective prompting."
I spent a lot of time writing and tweaking my prompts, so I'm sharing what works for me.