blog
Updates, deep-dives, and design notes.
Claude Code stops on a permission prompt when you are away. How to fix it.
An agent that sat on an approval prompt for an hour has a fix: change the permission mode, pre-approve the commands, and route the ones that still wait.
Is there a desktop app or GUI for managing multiple Claude Code sessions in different projects?
Yes, several. Anthropic's own desktop app, VS Code's Agents window, JetBrains Air, Claude Squad, and crystl, with what each one is good at.
Meta-orchestration: the layer above your agent orchestrator
Orchestration is one agent splitting work and running workers in a project. Meta-orchestration is the layer above: watching every project, routing work.
The best AI agent orchestration tools for coding in 2026
Comparing tools that run multiple AI coding agents at once: Conductor, Vibe Kanban, Claude Squad, crystl, Cursor cloud agents, Sculptor, and plain tmux.
Agent communication protocols: A2A, ACP, and MCP
A2A is agent to agent, MCP is agent to tool, and two different things are both called ACP. What each is, who governs it, and where the confusion starts.
Running an agent team in tmux
A pane per role, send-keys to dispatch, a shared file as the channel, a polling loop for idle. The real wiring for a tmux agent team, and what it skips.
How do you get AI agents to talk to each other?
Two coding agents, neither can see the other. Four real options for agent to agent communication, worst to best, and what each one actually guarantees.
Claude Code Subagents: Best Practices
Scope a subagent to one question, state the return shape, never delegate work you'd want to watch. Subagent tasks that work, and ones that waste tokens.
Cursor background agents vs crystl
Cursor's cloud agents run Cursor's own agent in isolated VMs and hand back a pull request. crystl runs any CLI agent locally, across all your projects.
Git: Cannot Delete Branch Used by a Worktree
Git refuses to delete a branch a worktree has checked out, even with -D. Find the worktree with git worktree list, remove it, then delete the branch clean.
git worktree add: Every Form of the Command
git worktree add with a new branch, an existing branch, a remote branch, a commit, or a detached HEAD. Every flag that matters, with examples and errors.
Git Worktree vs Branch (vs Multiple Clones)
A branch moves one working copy. A worktree adds a second, on the same history. A clone is a separate repo entirely. The commands, and when to use each.
A Git Worktree Workflow That Stays Tidy
Where to put worktrees, how to name them, what to do about node_modules and .env, and when to remove them. The habits that keep worktrees from sprawling.
Git Worktrees in Cursor, Zed, and IntelliJ
Yes. IntelliJ's Worktrees tab in the Git tool window handles them natively. Where to find it, plus how Cursor and Zed handle worktrees instead.
How Many Agents Can You Actually Run at Once?
The ceiling on parallel agents isn't your machine. It's tokens, rate limits, and your own review capacity. What binds first, and how to pick a number.
How to manage multiple projects when every project has an agent in it
Managing several projects used to be about your own time. With a coding agent in each one, the constraint moves to your attention. Six rules that hold up.
Agent orchestration, when what you actually have is too many tabs open
Agent orchestration is code deciding which agent runs when, inside a program you write. Searched it over nine terminal tabs? That's a different problem.
How to Remove a Git Worktree
git worktree remove deletes a directory and its metadata in one step. git worktree prune cleans up what you deleted by hand. Neither touches the branch.
Can You Run Multiple Instances of Claude Code?
Yes. Claude Code has no cap on concurrent instances. What two sessions share, what breaks when they share a directory, and the real limit you'll hit first.
Skills vs Subagents in Claude Code
A skill loads instructions into the conversation you're already having. A subagent runs where you can't see it and returns a summary. The real difference.
The tmux setup people build for parallel agents, and what it can't do
Claude Code ships a --worktree --tmux flag that covers one agent. Running several converges on the same hand-built setup, and where it stops working.
Claude Code has GUIs now. Here's what one should actually do.
Claude Code has a desktop app, a web app, IDE extensions, and community GUIs. Almost all build the same thing: a prettier chat window. The easy problem.
Warp vs. crystl: Cloud Agent Platform or Local Fleet Cockpit
Warp vs. crystl for running AI coding agents: where Warp's cloud, enterprise, and platform strengths differ from crystl's local, own-your-costs approach.
How to Use Git Worktrees with Claude Code
Claude Code worktree commands explained: the --worktree flag, what it does, real parallel-agent workflows, the gotchas, and how to automate it.
What the heck is a "footgun" and other things Claude says
A footgun is a feature that makes it easy to hurt yourself by accident. Real Claude Code quotes using the word, plus a glossary of its other dev slang.
Introducing roundtable agent orchestration
Most multi-agent orchestration hides the agents inside one controller's head. Roundtable orchestration, the model behind crystl quest, makes it visible.
How to Optimize Claude Code's Context Window (Without Just Buying a Bigger One)
Practical tactics for stretching Claude Code's context window: what to compact, what to delegate to subagents, and which plugins to disable first.
Do You Need a Code Editor to Build with Claude Code?
Claude Code runs in the terminal, reads your files, and writes your code. So do you still need VS Code open? The pros and cons of both setups.
Voice, Loops, and the Slow Disappearance of the Command Line
Claude Code's March 2026 features hint at something bigger than incremental updates. The relationship between developer and tool is shifting.
Claude Can Use Your Computer Now. That's a Stranger Sentence Than It Sounds.
Anthropic's computer use feature lets Claude control your Mac: clicking, typing, opening apps. What that actually means depends on who you are.
The Agentic Coding Workflow Nobody Talks About: Managing the Agents Themselves
The bottleneck in agentic coding isn't AI capability. It's managing multitask workflows where multiple AI agents are working simultaneously.
Why Your Terminal Wasn't Built for AI Pair Programming (And What To Use Instead)
Terminals were designed for human-typed commands, not for supervising AI agents. AI pair programming needs a different kind of tool.
Claude Code in iTerm2 vs. crystl: What Changes When You Use a Purpose-Built Terminal
Claude Code runs fine in iTerm2. Here's where the integration gets awkward: approvals, parallel sessions, scrollback, notifications, feature by feature.
From Terminal Chaos to Crystal Clarity: Migrating Your Claude Code Workflow
A step-by-step guide to organizing your Claude Code setup on macOS. Move from scattered terminal sessions to a structured workflow.
Test Suite Broken? Run Claude Code on the Fix While You Keep Building
How to multitask with parallel Claude Code sessions: fix a broken test suite in one session while continuing feature work in another.
How I Use Claude Code to Ship a PR Every Hour
A workflow for structuring parallel Claude Code tasks across sessions so you always have something ready to review and merge.
Managing Claude Code API Keys Across Multiple Projects
How to avoid leaking API keys across projects when using Claude Code, and a cleaner approach to per-project key management.
My Claude Code Workflow for Refactoring a Legacy Codebase
How I used Claude Code to refactor a legacy codebase by breaking the work into parallel tracks and merging incrementally.
Per-Project MCP Server Configs for Claude Code: Why and How
How to manage different MCP server configurations for each Claude Code project, and why a per-project setup prevents config headaches.
Organizing 10+ Claude Code Projects Without Drowning in Terminal Windows
How to multitask with Claude Code across many projects without losing track of sessions. The gems and shards mental model for terminal organization.
Running Claude Code in the Background: A Workflow Guide
How to run Claude Code agents in the background, check their status, and structure tasks for async AI workflows.
How to Monitor Multiple Claude Code Agents Without Losing Your Mind
Monitoring parallel Claude Code agents: telling which is blocked, which finished, which went off the rails, without clicking through every tab.
The Tab-Hunting Problem: Finding Which Claude Code Session Needs Your Attention
Running 5+ Claude Code sessions? Why you can't find the one waiting for approval, and how to fix it.
Why Your Claude Code Agents Keep Overwriting Each Other's Files
Running multiple Claude Code agents on the same repo? Why they conflict and how to fix it with isolated worktrees.
Fix a Bug and Build a Feature at the Same Time with Claude Code
A walkthrough of running two Claude Code sessions in parallel, one fixing a bug and one building a feature, in separate git worktrees.
How to Run Two Claude Code Agents on the Same Repo Without Destroying Your Git History
Multitasking with two Claude Code agents on the same branch causes merge conflicts. The fix is git worktrees, and you can automate it.
The Case for a Persistent Claude Code Session Log
Why your Claude Code session history should be persistent and browsable, not trapped in terminal scrollback that disappears when you close the tab.
What Did Claude Do While I Was Gone? Reviewing Agent Work After the Fact
Kicked off a Claude Code task and stepped away? How to review what your agent did, what it changed, and what it asked while you were gone.
I Closed My Terminal and Lost Everything: How to Never Lose a Claude Code Session Again
Lost a Claude Code conversation after closing your terminal? Why it happens and how to preserve your session history.