Six months of trial-and-error compressed into one page. For small business owners using AI as a daily tool.
ChatGPT and Claude.ai talk about doing things. Claude Code does them.
Since Opus 4.6 dropped in early 2026, Claude Code went fully agentic. It executes tasks on your computer, you supervise. For an operator, that means real automations, running on your machine, with your tools.
The catch: it's a terminal app. Looks intimidating. The learning curve is real but short. Most operators are functional within a week.
Work through these in order. None take more than 10 minutes.
So claude works in any window, not just the one where you installed it.
Tell Claude who you are, what you do, and how you like to work. It reads this at every session start.
Stop the constant "Approve this command?" prompts. Keep the deny list for dangerous stuff.
Gives Claude access to current documentation instead of hallucinating from stale training data.
Claude can drive a real browser. Fill forms, click buttons, take screenshots, scrape pages.
Gets you /session-handoff, /investigate, and structured workflows.
Git without learning git. /commit saves your work. That's it.
Shows context window % and session cost. You'll know when to /clear before performance tanks.
Every one of these cost me real time. Learn from my pain.
One long session, multiple topics, no /clear. Claude gets confused, you waste tokens, you blame the tool. One topic per session. Clear when switching.
Jumping into "build this" without writing what you're actually building. Claude fills the gaps with its own assumptions. Two hours later you have something neither of you wanted.
Claude says "I tested it, it works." You trust it. The next morning you find out it never worked. Always run it yourself. Evidence before assertions.
More plugins does not mean more useful. Each one adds noise to Claude's decision-making. Start with five. Add more when you hit the specific problem they solve.
Sessions fill up. Performance craters. New users don't know to /clear. Watch the percentage in your status line and clear around 70%.
Three models, three jobs. Don't overthink it.
| Sonnet 4.6 | Opus 4.7 | Haiku 4.5 |
|---|---|---|
| Daily work | Brainstorming | High-volume simple tasks |
| File edits | Stuck on a tough bug | Batch summarization |
| Quick research | Planning a new project | Bulk classifications |
| Browsing | High-stakes changes | (skip on Day 1) |
Opus is ~5× the cost of Sonnet. Use it when you need the extra horsepower, not as a daily driver.
Most lists tell you to install 50 things. Don't. Add one when you hit the problem it solves.
/session-handoff, /investigate, structured workflows
claude works in one window, fails in the next. Set it in your system environment variables.pbcopy and osascript don't exist on Windows./clear when switching. Mixed sessions produce mixed results.
5 minutes of "what are we building" saves hours of "wait, that's not what I meant."
/session-handoff before closing. Future-you picks up right where present-you left off.
Claude Code isn't free like ChatGPT. Know what you're spending.
/cost to check your spend.Go deeper: From 4 Rules to 50+ Automated Phases — the full evolution story of what happens when you take CLAUDE.md seriously.
90-minute Strategy Session. We look at your business, find the highest-ROI automations, and you walk away with a written plan.