Claude Code
85 articles about claude code.
Anthropic Subscription Auth Warning: Third-Party Usage Draws From Extra Usage, Not Your Plan
What the 'anthropic subscription auth is active, third-party usage now draws from extra usage' warning means, why it appears, and how to manage your extra usage credits.
Claude Third-Party Apps: Complete List, How They Work, and Billing Explained
Every third-party app that connects to Claude, how OAuth authentication works, billing under the new extra usage system, and how to manage your credits across Cursor, Claude Code, Windsurf, and more.
Route Claude API Through a Custom Endpoint with ANTHROPIC_BASE_URL
How to point Claude Code or a macOS AI agent at a custom Anthropic-compatible endpoint (corporate proxy, GitHub Copilot bridge, or self-hosted gateway).
"Tip: $20 in Extra Usage, on Us" for Third-Party Apps on Claude
Seeing 'tip: $20 in extra usage, on us' with third-party apps and /extra-usage? Here's what the $20 credit is, who gets it, how to claim it, and how to avoid running out.
"Tip: $200 in Extra Usage, on Us" for Third-Party Apps on Claude
Got the 'tip: $200 in extra usage, on us' message for third-party apps and /extra-usage? Here's what the $200 credit is, who qualifies, how to claim it, and how to manage it.
Third-Party Apps Now Draw From Your Extra Usage, Not Your Plan Limits
What Anthropic's billing change means for Cursor, Claude Code, and VS Code users. How the extra usage pool works, which apps are affected, and how to manage your credits.
Best AI Workflow for React Native Expo Apps
How to set up CLAUDE.md and AI agent workflows for React Native Expo projects - common pitfalls, project structure tips, and getting agents to write mobile
The Better Claude Code Becomes, the Less I Want to Use It
As Claude Code gets more opinionated and capable, it removes the flexibility that made it useful. When tools think for you, you stop thinking.
Breaking Down Complex Projects for AI Coding Agents
Handing an AI coding agent a full PRD never works. Learn how to decompose complex projects into agent-sized tasks that actually get completed correctly.
Bridging AI Chat and Coding Agents with Shared Context Files
There is a wall between AI chat interfaces and coding agents. CLAUDE.md files and shared context documents break down that wall and make both tools more
I Bought the $200 Claude Code Plan So You Don't Have To
Two months on the $200 Claude Max plan running multiple parallel agents. Here is whether it is worth the money for serious development work.
Claude Code as the Brain for Desktop Automation Workflows
Claude Code is not just a coding tool - it is the ideal orchestration brain for desktop automation. Here is how to use it as the central controller for
Make Claude Code See Your Browser DevTools with Playwright MCP
Connect Claude Code to your browser DevTools using the Playwright MCP server. Get screenshots, console logs, and network access directly in your coding
Why Claude Code Understands But Does Not Listen
The frustrating gap between an AI agent understanding your instructions and actually validating its output against them - and how to fix it with explicit
AI Coding Agents for Personal Automation Beyond Software Development
Claude Code isn't just for writing software. From automating 30-click tasks to scheduling launchd jobs, here are personal use cases that save hours every week.
Skills vs Sub-Agents in Claude Code - When to Use Each Pattern
How to structure Claude Code skills vs sub-agents - splitting by type, managing 10+ skills, and choosing the right pattern for each workflow.
Claude Code Subagents in Parallel - Safety Lessons from Real Codebases
Running multiple Claude Code agents on the same codebase sounds productive until two agents edit the same file. Practical lessons on file conflicts
Claude Code Writes Your Code, but Do You Know What's in It?
AI coding agents restructure modules in unexpected ways. The code works but the architecture drifts from your mental model unless you actively review
Tell Your Coding Agent to Ship Small Chunks
Large AI-generated PRs are unreviewable. Ship features in small chunks with per-feature CLAUDE.md specs and separate agent sessions for each piece.
The Coolest AI Coding Setup Uses Skills, Hooks, and Automation Triggers
The best AI coding setups are not about hardware. They use Claude Code skills as reusable automation modules and hooks as deterministic triggers - here is how to build yours.
Where to Start with AI Tools in 2026 - Skip the Courses, Build Something
The best way to learn AI agents in 2026 is to skip the courses and build something real. MCP, Claude Code, and desktop agents click when you use them.
Good AI Rule Files to Share - Writing Effective CLAUDE.md Files
How to write a CLAUDE.md file that actually improves AI agent output. Mandatory testing rules, coding standards, and project context that make Claude Code
macOS Menu Bar App to Track Claude Code Usage
Build a macOS menu bar utility to monitor AI agent token usage, costs, and session activity. Keep Claude Code spending visible without context switching.
Most Impressive Claude Code Session - Agent Refactored Its Own Posting Skill
An AI agent analyzed its own engagement data and refactored its social media posting skill to improve performance. When agents optimize themselves.
Building a Desktop Agent in Go with Neo4j Memory - Why the Architecture Choices Matter
OpenLobster takes a different approach to desktop agent architecture: Go instead of Python, Neo4j graph database instead of flat files. Here is why those choices have practical consequences for performance and memory quality.
Opus for UI Work with Clear Constraints
Claude Opus excels at UI design tasks when given clear constraints. A Superpowers plugin designed a connection stats UI that was better than what manual
Orchestrator Implementor Review Loop - Code Review with tmux Claude Code Sessions
How to implement a code review loop using tmux-based Claude Code orchestration with separate orchestrator, implementor, and reviewer sessions.
How to Prevent AI-Generated Spaghetti Code with CLAUDE.md and Detailed Specs
AI coding agents produce cleaner code when given detailed specifications and CLAUDE.md constraints. Here's how to prevent goop code before it starts.
How Developers Actually Use AI in Their Coding Workflow
What real AI-assisted development looks like vs the demo version. Five agents doing heavy lifting while you architect - the workflow nobody shows on Twitter.
Run 10+ Claude Code Agents Without Chaos
How to run 10+ AI coding agents in parallel without chaos - configuration, coordination, and CLAUDE.md strategies that prevent conflicts.
How Do You Agent - Running 5-8 Claude Code Agents in tmux
Practical guide to running 5-8 AI coding agents simultaneously on one codebase using tmux - session management, task decomposition, and real-world parallel
Vibecoded App with Claude Code
Vibecoding with CLAUDE.md architecture rules turns Claude Code from a code generator into a system-aware development partner. Here is how the approach works.
Has AI Ruined Software Development? No - It Shifted the Work to Specs
Developers now spend 80% of their time writing specs and constraints to contain AI agents, not coding. AI didn't ruin development - it changed what the hard
How to Design App Icons with Claude Code - No Figma Required
A practical guide to designing app icons using Claude Code and SVG - with hard constraints, iterative refinement, and multi-size export without design tools.
Autonomous Multi-Session AI Coding Without Worktrees
Skip git worktrees entirely. Run 5 Claude Code instances on the same repo with CLAUDE.md as the shared spec and each agent handling a discrete task.
The Developer Career Bet - Writing Specs Not Code in the AI Age
72% of tech leaders plan to reduce entry-level developer hiring while increasing AI tool investment. The developers who thrive run 5 Claude agents in parallel and spend their day writing CLAUDE.md files, not code.
Claude $20 Plan Limits Are Genuinely Confusing - Session vs Weekly Explained
The Claude $20 plan limit error message says 'limit' without specifying session vs weekly. Here is how session limits, weekly caps, and parallel agents
Why Explicit CLAUDE.md Specs Beat Auto-Memory for Parallel Agents
Auto-memory causes parallel AI agents to diverge. Explicit specs in CLAUDE.md files keep multiple agents deterministic and consistent.
Claude Code Burned All My Tokens in 30 Minutes - Why Narrow Scoping Fixes This
Running 5 agents in parallel on your codebase without narrow scoping burns through tokens in minutes. Each agent needs a very specific scope to be
Why CLAUDE.md Is the Entire Game for Parallel Claude Code Agents
CLAUDE.md is the most important file when running parallel Claude Code agents. Without detailed specs, 5 agents on the same codebase will overwrite each other.
Claude Code's Real Advantage Is the Harness, Not the Model
The harness is what makes Claude Code powerful. Running 5 agents in parallel on the same repo with CLAUDE.md as the orchestration layer changes everything.
Claude Code Agents Gave Me a Healthier Life - When the Hard Part Is Specs
Running 5 Claude Code agents in parallel means the hardest part of your day is writing good CLAUDE.md specs. The rest of the time? Exercise, cooking, and
Parsing Claude Code's JSONL Format for macOS Dev Tools
Building developer tools that read Claude Code's local conversation logs means figuring out the JSONL format - conversation turns, tool calls, and file
Turning Claude Code into a Personal Agent with Memory and Goals
Claude Code out of the box is stateless. Adding persistent memory with CLAUDE.md files and goal tracking turns it into an agent that knows your preferences
Accessing Claude Code Previous Sessions via JSONL Transcripts
Where Claude Code stores previous session transcripts as JSONL files, how to find them in ~/.claude/projects/, and practical tips for parsing and reusing
Running Claude Code Over SSH on a Mac Mini M4 with tmux
A Mac Mini M4 running 24/7 with tmux sessions handles PR reviews, automation, and agent tasks. SSH in from any thin client to manage everything remotely.
When Claude Files Bug Reports Against Its Own Code - And They Are Real
Running 5 parallel Claude agents with CLAUDE.md as the single source of truth leads to agents finding real bugs in each other's code. Here is how it works.
Making Claude Code Skills Repeatable - 30 Skills Running Reliably
Running 30 Claude Code skills reliably for a macOS agent. The key to repeatability is explicit frontmatter, narrow scope per skill, and clear input/output
Using Claude to Submit Apps to the App Store - Provisioning Profiles Are Still Hard
Even after shipping multiple macOS apps with Claude's help, provisioning profiles and code signing remain the hardest part of App Store submission. Here is
Claude Code Subscription Tiers - Why the $100 Plan Is Your Second Rent Payment
The $20 Claude plan lasts about a day when running multiple agents in parallel. Here's why the $100 plan is worth it and how to manage costs with parallel
Adding Co-Authored-By Claude to Every Git Commit
Why putting Co-Authored-By: Claude in your CLAUDE.md for automatic commit attribution matters for AI transparency. When the AI has more credits than your
Codex vs Claude Code for macOS Desktop Development
Why Claude Code wins over OpenAI Codex for native macOS app development - from SwiftUI debugging to Xcode integration and local-first workflows.
Context Engineering - Why CLAUDE.md Is the Most Important File in Your Project
The CLAUDE.md file is the most important file in any Claude Code project. Here is why context engineering matters more than prompt engineering.
Context Management Is 90% of the Skill in AI-Assisted Coding
The real skill in AI-assisted coding is not prompting - it is context management. Persistent memory, CLAUDE.md files, and layered context separate productive developers from frustrated ones.
Cowork vs Claude Code: Why Terminal Gives You More Control
Claude Code in the terminal offers more control than GUI alternatives like Cowork - especially when running 5 parallel instances on the same codebase.
Custom Skills vs Marketplace Skills in Claude Code - Why Building Your Own Wins
After trying dozens of marketplace skills, we ended up with mostly custom ones for specific recurring tasks. Here is why building your own skills works
Building a Rust + Tauri Desktop App with Zero Coding Skills Using Claude Code
How a designer built a Rust and Tauri desktop app with zero coding experience using Claude Code. The design-to-prompt pipeline that actually works.
Developers Are Becoming Their Own Business Analysts in the AI Era
The most productive developers now spend their day writing detailed requirements and acceptance criteria, then handing them to Claude. Writing specs is the
Explicit Acceptance Criteria in CLAUDE.md to Stop Premature Victory
How adding explicit acceptance criteria to CLAUDE.md stops Claude Code from declaring victory prematurely. Tests must pass, files must exist, no regressions.
Running 5 AI Agents on the Same Codebase Without Branch Isolation
Lessons from running 5 Claude Code agents in parallel on a Swift, Rust, and Flutter desktop app. Same repo. Same branch. No isolation.
From Copilot to Claude Code - Why a 200-Line CLAUDE.md Changed Everything
How switching from GitHub Copilot to Claude Code with a 200-line CLAUDE.md running 5 parallel agents transformed a solo developer's entire workflow.
Free AI Tools for Daily Use - How Claude Code with MCP Servers Replaces Paid SaaS
Claude Code with MCP servers can replace many paid SaaS tools. Combined with macOS accessibility APIs, you get a free desktop agent that handles daily
Building a Gateway Daemon for Claude Code Multi-Agent Scheduling
Using tmux sessions with individual agents plus launchd for scheduling. The hardest part of multi-agent orchestration is knowing when to intervene.
Large SaaS Claude Workflow - Five Agents Running Off the Same CLAUDE.md Spec
How to write everything in CLAUDE.md and run 5 parallel Claude agents off the same spec for large SaaS projects. A practical workflow guide.
Learn AI Workflows or Find an AI-Safe Career? Why Going All-In Is the Bet
Should you learn AI workflows or find something AI can not replace? Here is why going all-in on parallel AI agents and specs is the better career bet in 2026.
Running Claude Code Locally - Free and Private Setup Guide
How to run Claude Code locally so your conversation history, file edits, and tool outputs never leave your machine.
Managing 5+ Parallel Claude Code Agents Without Losing Track
Practical strategies for running multiple Claude Code agents in parallel - git worktrees for isolation, shared CLAUDE.md coordination, session naming, dependency mapping, and when to stop adding agents.
How MCP Servers Changed My Coding Workflow After 10 Years of Backend Dev
MCP servers eliminated copy-pasting between apps. Direct tool interaction from Claude Code changed how a backend developer writes and ships code.
The 1M Context Trap: Why More Context Makes Claude Lazier
Research on 18 frontier models confirms every one degrades with more context. The 'lost-in-the-middle' effect causes 30%+ accuracy drops. The counterintuitive fix: use less context, not more.
Building Persistent Memory for Claude Code Agents with CLAUDE.md
Why CLAUDE.md is the only memory that survives across Claude Code sessions. How to build persistent context for 5 parallel agents working on the same repo.
Using Playwright MCP with Claude Code for Daily Browser Automation
How Playwright MCP with Claude Code handles daily browser tasks like scraping engagement data, filling forms, and automating repetitive web workflows.
Building a Production iOS App in 35 Hours with Claude Code
A real experience building a production-quality iOS app with Claude Code in 35 hours. The logic was easy - SwiftUI styling was the hardest part by far.
Reading Extended Thinking from 5 Parallel Claude Code Agents
What it feels like reading extended thinking from 5 parallel Claude Code agents. It is like having 5 coworkers all privately judging your code at the same time.
Why Removing Unused MCP Servers Speeds Up Claude Code More Than Removing Skills
Trimming unused MCP servers made way more difference than removing skills. MCP servers are actual processes that all have to handshake on startup.
Schedule Claude Code Sessions With launchd to Use Your Token Quota Automatically
Set up launchd jobs that kick off Claude Code sessions on a schedule for automated PR reviews, stats updates, and maintenance tasks. Put your token quota to
Organize SKILL.md Files Per Folder for Parallel Agent Isolation
How maintaining 30+ skill specs with clean per-folder isolation gives each parallel agent the exact context it needs without noise.
Skills vs MCP vs Plugins - What's the Difference?
Skills inject instructions into conversations. MCP servers give agents new tools. Plugins are platform-specific integrations. Most people confuse all three
When Developers Stop Writing Code and Start Reviewing AI Agents
Going from writing code to mass-reviewing output from 5 parallel Claude agents. Haven't typed a function in weeks. The new developer workflow is review, not
Building a Visual Wrapper for Claude Code - Why Native macOS Beats the Terminal for Agent Debugging
Claude Code's terminal UI is fast but opaque. Here is why some developers build SwiftUI wrappers to surface tool calls, file diffs, and decision trees as navigable UI instead of scrolling logs.
From Writing Code to Reviewing Code - The AI Shift
The job changed from writing code to mass-reviewing AI-generated code from parallel agents and writing CLAUDE.md specs. Here is what that transition looks
Multiplayer Claude Code and the Context Hydration Problem
Running 5+ parallel Claude Code agents creates a context hydration problem. Shared CLAUDE.md files, git worktrees, and coordination patterns that actually work.
The HANDOFF.md Pattern - How to Keep Claude Code Productive Across Sessions
Context window management matters more than prompt quality once your project grows. How the HANDOFF.md pattern and post-edit hooks keep AI coding agents
Using Claude as an Execution Layer - Markdown Specs, MCP Tools, No Traditional Code
What happens when your entire app is markdown specs that Claude executes, with MCP servers as the only real code. A year of building this way.
Writing CLAUDE.md Files That Actually Help (Not Hurt) Your AI Agents
The ETH Zurich paper says CLAUDE.md files hurt agent performance. Our experience with 5 parallel agents says the opposite. The difference is what you put in
I Installed 20 MCP Servers and Everything Got Worse - Why Fewer Is Better
More MCP servers means hundreds of tool definitions competing for attention. Stripping down to 3 servers made Claude pick the right tool on the first try.
Browse by Topic
How did this page land for you?
React to reveal totals
Comments (••)
Leave a comment to see what others are saying.Public and anonymous. No signup.