These aren’t magic words. They’re real features.
Every code below is a built-in Claude feature, keyword, or shortcut that changes what you get back. Nothing made up. Most of them are one word or one keystroke, and you don’t need to be technical to use them.
There are three Claudes, and a code might work in one, two, or all three. Each card is tagged so you can skip what isn’t for you:
- App the chat you already use
- Cowork Claude working inside a folder
- Code access to your actual computer
🧠 The Thinking Codes
Make Claude smarter before it answers.
- 1. ultrathink
The escalation ladder. Type think, think hard, think harder, or ultrathink and each one gives Claude a bigger thinking budget before it responds. ultrathink is the max. Use it on hard problems where the first answer usually is not good enough.
Code
Try this: "ultrathink. Here’s my pricing model. Find the flaw I’m not seeing: [paste]"
- 2. /effort max
Type this once in Claude Code and it stays in deep-thinking mode for the whole session, not just one message. Set it to max before a complex build and every response gets the full reasoning budget.
Code
Try this:
/effort max, then start your hard task. (Max reasoning costs more, so save it for what matters.) - 3. Say "I don’t know"
The anti-hallucination line. Add "if you’re not sure, just say I don’t know" to a prompt, or drop it into your global instructions so it’s always on, and Claude stops confidently making things up.
App · Cowork · Code
Try this: Paste a document: "Answer only from this doc. If it’s not in here, say I don’t know."
- 4. Ask me one question at a time
Stops Claude from guessing what you want. Say this before a big task and instead of a generic answer, it interviews you one question at a time until it actually understands the job.
App · Cowork · Code
Try this: "I want to write a sales page. Don’t write anything yet. Ask me one question at a time until you have what you need."
- 5. Extended Thinking
The app version of ultrathink. Flip the thinking toggle near the message box and Claude reasons through the problem before answering, and you can watch it think. Leave it on for anything analytical.
App
Try this: Toggle it on, paste a dense report, ask for the three things that actually matter.
🔨 The Build Codes
Make Claude make things, not just talk about them.
- 6. ARTIFACT
Stop getting walls of text. Ask Claude to build something "as an artifact" and instead of describing it, it builds a live, working version in a panel next to the chat: a calculator, a tool, a one-page app, a doc you can edit.
App
Try this: "Build me a tip calculator I can actually use, as an artifact."
- 7. Projects
Your own custom Claude. Create a Project, upload your docs as its knowledge, and add instructions. Now every chat inside it already knows your context. No re-explaining yourself every time.
App
Try this: Make a "My Business" Project, upload your offer doc, tell it to always answer in your voice.
- 8. Styles
Make Claude write like you instead of like a robot. Pick a built-in style (Concise, Explanatory, Formal) or create a custom one trained on your own writing. Set it once and every response matches your voice.
App
Try this: Create a custom style, paste in 3 things you’ve written you’re proud of, let it learn your tone.
- 9. Research mode
For the big questions. Turn on Research and Claude goes off and reads dozens of sources, then comes back with a real, cited answer instead of a quick guess. Use it when being right actually matters.
App
Try this: "What are the best-reviewed CRMs for a solo consultant in 2026, and what do real users complain about?"
- 10. Connectors (MCP)
Plug your actual tools into Claude. Connectors let Claude reach into Gmail, Google Drive, your calendar, Notion, and hundreds of other apps directly. It’s not guessing, it’s working with your real stuff.
App · Cowork · Code
Try this: Connect your Drive, then ask Claude to find a file and summarize it without uploading anything.
🎛️ The Control Codes
Run Claude like you’ve done it for years.
- 11. /clear
The reset button. Wipes the conversation so Claude starts fresh, but keeps every file change it already made. When a session goes off the rails, /clear and re-ask cleanly instead of fighting the context.
Code
- 12. Double-tap Esc
The undo button for AI. Tap Escape twice and you get a rewind menu. Jump back to any earlier point and restore the conversation, your code, or both. Claude broke something? Rewind instead of starting over.
Code
- 13. @file
Type @ and start the filename, and Claude instantly loads that exact file into the conversation. No copy-pasting, no "here’s my code." Just @filename and it’s in context.
Code · Cowork
Try this:
@notes.md summarize the action items in here - 14. Shift + Tab
Plan Mode. Make Claude plan before it touches anything. Hit Shift+Tab to cycle into Plan Mode and Claude maps out exactly what it’s going to do, then waits for your okay before changing a single file. Essential for big or risky tasks.
Code
- 15. Voice mode
Stop typing. Tap the mic and just talk. It’s faster than your thumbs, and you explain messy, complicated stuff way better out loud than in a tidy little text box.
App · Code
Try this: Hit the mic and ramble through what you’re stuck on. Let Claude untangle it.
♾️ The Compounding Codes
Set these up once. They pay off forever.
- 16. Custom instructions
The one-time setup almost nobody does. In settings there’s a box for what Claude should always know about you and how to respond. Fill it in once and every chat starts already knowing your job, your style, your preferences.
App
Try this: "I run a solo business. Keep answers direct and skip the disclaimers."
- 17. CLAUDE.md (+ /init)
Same idea as Custom instructions, but for Cowork and Code. A file Claude reads at the start of every session: your standards, your context, how you like things done. Write it once and stop re-explaining yourself. Type /init and Claude drafts the first version by reading your project.
Cowork · Code
Try this: "Drill me with questions about how I work, then write a CLAUDE.md that knows everything about me and my project."
- 18. #
Save a memory mid-task. Start a line with # and Claude saves whatever you type straight into your CLAUDE.md. No stopping to edit files. Teach it something once and it remembers from then on.
Code
Try this:
# always use British spelling - 19. Use subagents (+ /agents)
Turn one Claude into a whole team. Add "use subagents" to a big task and Claude spins up multiple agents that work in parallel. Hours of work compressed into minutes. Run /agents to build your own specialized ones.
Code
Try this: "Audit all my pages for broken links. Use subagents to check them in parallel."
- 20. Turn this into a skill
The forever button. After Claude nails a task, have it save the whole workflow as a Skill: a reusable command you can run anytime with one word. Build it once, run it forever.
Cowork · Code
Try this: After Claude does something you’ll repeat: "Turn this exact process into a skill I can run again."
The one that changes everything
If you only act on one of these, make it the tell-Claude-who-you-are move: Custom instructions in the app, CLAUDE.md in Cowork and Code.
Every other code is a single better response. This one is every response getting better, automatically, forever, because Claude finally knows who you are and how you work. Start there. Then add the rest one at a time.