Blog · September 25, 2026 · 7 min read · by Vilva Athiban P B

Exercise While Coding: Turn Claude Code Wait Time Into Micro-Workouts

Add up the minutes you spent today waiting on Claude Code. Every "refactor this module", every "fix the failing tests", every plan-mode run — each one is a few minutes where the agent works and you don't. For a heavy user that easily adds up to an hour or more a day.

Most of that hour goes to watching the terminal, checking Slack, or scrolling a phone. This post is about spending some of it on something better: short bursts of movement, sometimes called exercise snacks or micro-workouts, timed to your AI's work instead of to a calendar reminder you'll dismiss.

What is an exercise snack?

An exercise snack is a very short bout of physical activity — typically one to a few minutes — done several times a day instead of (or in addition to) one long workout. Think a set of squats, a minute of marching in place, or a few push-ups against your desk. A movement break is the gentler cousin: a stretch or a walk to break up a long period of sitting.

Neither is a replacement for proper training if you have specific fitness goals. But public health guidance such as the World Health Organization's physical activity guidelines encourages adults to be active regularly and to limit long, uninterrupted stretches of sedentary time — and the guidance is clear that some activity is better than none. For people who sit at a desk all day, frequent small breaks are one of the easiest ways to move more.

Why AI coding breaks are the perfect trigger

The reason most "stand up every 30 minutes" reminders fail is timing. The reminder fires when you're in the middle of a hard problem, so you snooze it. Then you snooze it again.

Waiting on an AI agent flips that. When Claude Code is working:

  • You're already interrupted. Your train of thought has been handed to the agent. There's no flow state to protect.
  • The break has a natural length. Most agent runs last a few minutes — about the length of one or two sets.
  • It repeats all day. Ten, twenty, thirty prompts a day means ten, twenty, thirty chances to move, without scheduling anything.
  • There's a clear end signal. The agent finishes or asks for permission — that's your cue to sit back down.

In habit terms, the prompt you send becomes the cue, the exercise is the routine, and getting back to a finished task is the reward. You don't have to invent a trigger; your workflow already has one.

A simple system: one prompt, one set

Keep it boring and repeatable. The rule we use: every time you send a prompt you expect to take more than a minute, do one set.

  1. Keep a short list of moves. Five to ten exercises that need no equipment and no changing clothes. Our 15 desk exercises for programmers is a good starting menu.
  2. Rotate by body area. Alternate upper body, lower body and mobility so nothing gets overworked and you cover everything by the end of the day.
  3. Use a timer or a rep count. 30–45 seconds, or 8–15 reps. Stopping points matter; open-ended exercise is how breaks turn into distractions.
  4. Return when the agent needs you. Not when you get curious. Checking the terminal every twenty seconds defeats the purpose.
  5. Track streaks, loosely. A count of sets per day is surprisingly motivating. Don't punish yourself for a heads-down day with few prompts.

Making it work without hurting your focus

Keep the intensity low to moderate

You want to come back to the keyboard ready to review code, not gasping. Squats, wall or incline push-ups, marching and mobility work are ideal. Save burpees for the gym.

Don't let notifications cut you off mid-rep

If your AI finishes halfway through a set, finishing the set first is fine — thirty more seconds won't matter to your code. What matters is that you do find out it finished, instead of discovering it five minutes later. That's why pairing movement breaks with Claude Code notifications works so well: you can fully look away from the screen.

Watch for permission prompts

Claude Code often pauses to ask permission before running a command or using a tool. If you miss that, the agent sits blocked while you stretch. A notification that distinguishes "done" from "needs permission" lets you decide whether to finish the set or go approve it now.

Have an off switch

Some days you're debugging production and don't want to see a squat prompt. That's fine. The goal is a default, not a rule you have to obey.

What a micro-workout day looks like

A realistic example for a day with a couple of dozen agent runs:

  • Morning: neck tilts, arm circles and cat-cow while Claude reads the codebase and makes a plan.
  • Late morning: squats and wall push-ups while it implements the first chunk of a feature.
  • After lunch: a high-knee march or step jacks while the tests run — the post-lunch slump is the best time for a little cardio.
  • Afternoon: incline push-ups, calf raises and hip circles between review rounds.

None of it feels like a workout, yet by evening you may have done well over a hundred reps and broken up your sitting many times.

Automating it with NotchFit

The system above works with a sticky note and a phone timer. But the friction adds up: picking the next move, timing it, and checking whether Claude is done. So we built NotchFit, a Mac app that runs micro-workouts in your MacBook's notch while Claude Code or Codex works.

  • When your AI starts working, the notch expands: an animated exercise with a countdown ring on the left, the agent's live progress on the right.
  • Sets only start when you tap Start set, with rest timers between sets — so it never runs ahead of you.
  • When Claude or Codex is done or needs permission, you get told. If you're mid-set, that notification waits until the set ends.
  • Run /notchfit:plan in Claude Code (or $notchfit-plan in Codex) and your AI writes a weekly plan from your goal, fitness level, equipment, available time and injuries.
  • Streaks, a history heatmap and a bit of confetti keep the habit visible. A Hide workout toggle turns it into a pure AI status panel on heads-down days.

The bottom line

AI agents gave developers something new: dozens of short, idle windows every day. You can spend them watching text scroll, or you can spend them moving. Pick a handful of desk-friendly exercises, tie one set to every prompt, and let a notification — not your eyes — tell you when to come back. Stop if anything hurts, keep it easy, and let consistency do the rest.

Keep reading

Desk Exercises for Programmers: 15 Moves to Do While Your AI Agent Codes

7 min read

Claude Code Notch Notifications on Mac: See When Claude Is Done Without Watching the Terminal

7 min read

Claude Code Tips and Tricks: 12 Ways to Use Claude Code Effectively

8 min read

Claude Code Multiple Sessions: How to Run Agents in Parallel Without Losing Track

6 min read

A Claude Code Workflow That Doesn't Involve Watching the Terminal

5 min read

Claude Code Hooks: A Practical Guide to Automating Your Agent Workflow

7 min read

Claude Code Auto Mode: Fewer Permission Prompts Without Living Dangerously

7 min read

Claude Code Subagents: How to Delegate Work to Specialized Agents

7 min read

Claude Code Context Management: Treat the Context Window Like a Budget

6 min read

Per-Subagent Model Selection: Route the Grunt Work Down, Keep the Judgment Up Top

7 min read

Skills and Plugins: How to Teach Claude Code Your Way of Working

7 min read

Claude Code Background Tasks: Run Long Commands Without Blocking Your Session

6 min read

Codex CLI Notifications: How to Get a Ding When Codex Is Done or Needs Input

7 min read

Cursor Notification When Done: Every Way to Get Notified When Cursor Finishes

6 min read

Claude Code Notifications: How to Get Notified When Claude Code Finishes or Needs Your Input

6 min read

Want to Be Notified When Claude Responds? How Claude Notifications Work on Web, Desktop, and Mobile

5 min read

Claude Code Notification Scripts: Copy-Paste Recipes for Every Platform

6 min read

Get a Ding the Moment Codex Needs Your Response

6 min read

Get Notified the Moment Claude Code Is Waiting for Your Input

6 min read

“Notifications Are Turned Off for Claude” — Here Is the Fix

6 min read

Codex Sound When Done: Make Codex CLI Play a Sound When It Finishes

6 min read

terminal-notifier + Claude Code: Native macOS Alerts When Your Agent Finishes

6 min read

Gemini CLI Notifications: How to Get a Sound or Alert When Gemini Finishes

6 min read

Get Claude Code Notifications on Your Phone

6 min read

Claude Code Remote Control, Explained

7 min read

preferredNotifChannel: Claude Code's Built-In Notification Setting

6 min read

Claude Code Notifications in tmux and Over SSH

7 min read

Claude Code Effort Levels: Why Your Setting Keeps Getting Ignored

8 min read

Codex vs Claude Code Notifications: How Each One Tells You It Is Done

8 min read

Claude Code Notifications Not Working: A Diagnostic Checklist

10 min read

Claude Code Notifications Inside Your Editor's Terminal

7 min read

CLAUDE_CODE_DISABLE_BACKGROUND_TASKS Explained

7 min read

CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP Explained

8 min read

Cursor Alerts Explained: Every Alert Cursor Raises, and How to Control Them

7 min read

Claude Code Environment Variables: The Groups That Actually Matter

10 min read

Claude Code Notifications on WSL and Windows

9 min read

Claude Code Checkpoints and /rewind

8 min read

Claude Remote Control: How It Works, Turning It Off, and Auto Mode

7 min read

Claude Code /loop: Poll a Deploy, Babysit a PR, and Get Told When It's Done

8 min read

Setting Up NotchFit With OpenAI Codex CLI: Hooks, $notchfit-plan, and the Daily Flow

7 min read

Claude Mods Explained: What the New Plugin Layer Can Do, and How to Turn On 'You Should Know'

9 min read

NotchFit vs Mac Break Reminder Apps: A Clock or a Signal From Your Coding Agent?

8 min read

Claude Code Headless Mode: Running claude -p in Scripts and CI, and the Three Signals That It Finished

10 min read

Building a Movement Habit at a Desk: Use the Agent Run as the Cue, One Set as the Unit, and Streaks Carefully

8 min read

Claude Code MCP Servers Explained: Adding Servers, Choosing a Scope, Handling Secrets, and Why Long Tool Calls Go to the Background

10 min read

/notchfit:plan Explained: How Claude Code or Codex Writes a Weekly Workout Plan the Notch Can Actually Run

8 min read

Claude Code Spinner Verbs Explained: What “Pondering” and “Brewing” Mean, How to Change Them, and Why You Should Stop Watching the Spinner

7 min read

Why NotchFit's Done and Permission Alerts Wait Until Your Set Ends, When That Costs You, and How to Turn the Workout Off

7 min read

How to Resume a Claude Code Session: --continue vs --resume, Naming Sessions, the Session Picker, Branching, and What Comes Back

9 min read

NotchFit on a Mac Without a Notch: How Pill Mode Works on Mac mini, iMac, Mac Studio and a MacBook With the Lid Closed

6 min read

How to Run a Claude Code Session in the Background: /background, claude --bg, Agent View, and Getting Back to It

9 min read

What a Notch App Can See: NotchFit's Local-First Design, What the Claude Code and Codex Hooks Send, and What Stays on Your Mac

7 min read

Why Codex CLI Asks for Permission Every Time, and How to Tune the Sandbox and Approval Policy Without Going Full Access

8 min read

What to Do While Claude Code or Codex Works: A Simple Protocol for the Two-to-Twenty-Minute Gap in Every Agent Run

7 min read

Is It Possible to Get a Notification When Claude Code or Codex Hits a Reset? Yes for Claude Code: the quota_auto_resume Hooks, Explained

8 min read

What a MacBook Notch App Can Actually Do: The Five Kinds of Notch Utility, Their Trade-offs, and Where NotchFit Fits

7 min read

How to Make MCP Servers Not Take Up as Much Context in Claude Code: Tool Search, alwaysLoad, Scopes and Output Caps

8 min read

The notchfit Command Line: Drive Your Workout, Read Status as JSON, Validate Plans and Test the Notch Without Leaving the Terminal

7 min read

How to Audit MCP Tool Calls Made by Claude Code: A Five-Minute Hook Audit Log, OpenTelemetry Tool Events, and the Transcript for Investigations

9 min read

Exercise Snacks: What the Research Actually Says About One-Minute Vigorous Breaks, What It Does Not, and How NotchFit's Agent-Run Sets Compare

8 min read

How Long Until a Claude Code MCP Tool Call Times Out? The Four Timers (Startup, Two-Minute Backgrounding, Idle, Wall-Clock), Their Defaults, and Which One to Change

8 min read

Sitting Too Long as a Developer: The Posture Problems Coding Agents Made Worse, What the Research Says About Breaking Up Sitting, and How NotchFit Turns an Agent Run Into the Break

8 min read

Claude Code .mcp.json Explained: Where Project-Scoped MCP Servers Are Read From, What Happens in Subfolders and Monorepos, and Why a Committed Server Shows Pending Approval

8 min read

Standing Desk Exercises for Developers: Why Standing Still Is Not the Goal, Eight Movements That Fit a Thirty-Second Agent Run, and How NotchFit Cues Them From the Notch

8 min read

The claude mcp Command Reference: add Syntax by Transport, What --scope local, project and user Actually Mean, add-json and add-from-claude-desktop, list, get, remove, login and serve

9 min read

Your First Week With NotchFit: Install and Simulate, Run Real Tasks, Write a Smaller Plan Than You Want, Tune the Alerts, Survive the First Skipped Day, and Decide What Stays

8 min read

How to Stop a Running Claude Code Task: Esc vs Ctrl+C, Background Tasks, Subagents, and Disconnecting Remote Control

8 min read

Pomodoro vs Agent-Driven Breaks: Timing Movement to Claude Code and Codex Runs Instead of a Timer

7 min read

Claude Desktop MCP Configuration: claude_desktop_config.json, Logs, Extensions, and the Difference From Claude Code

9 min read

The 20-20-20 Rule for Developers: Eye Strain, the Evidence, and Agent Runs as the Cue

8 min read

Claude Agent SDK + MCP Servers: mcpServers, allowedTools, Status Checks and Auth

9 min read

Discreet Desk Exercises for an Open-Plan Office While Claude Code Runs

7 min read

claude remote-control Server Mode: Run Claude Code as a Session Server

9 min read

Wrist and Forearm Stretches for Developers: A 60-Second Routine for Every Claude Code Run

7 min read

Claude Remote Control vs Claude Code on the Web: Which to Use and How They Differ

9 min read

Neck and Shoulder Stretches for Developers: A 90-Second Routine Between Agent Runs

7 min read

What Happens When You Step Away From a Claude Code Session: Prompt Cache Expiry, Idle Compaction, and When to Come Back

8 min read

Hip Flexor and Lower Back Stretches for Developers: A Two-Minute Standing Routine Between Agent Runs

7 min read

Claude Code's Monitor Tool: Watch Logs, CI Runs and PRs (Even a WebSocket) and Let Claude React While You Keep Working

7 min read

Hunched Over the Keyboard? Upper-Back (Thoracic) Stretches for Developers: A Two-Minute Seated Routine Between Agent Runs

6 min read

Claude Code Ultrareview: The 15–25 Minute Cloud Review, What to Do While It Runs, and How the Findings Come Back

8 min read

Why Your Legs Go Dead After a Long Claude Code Session: A Two-Minute Standing Calf, Glute and Hamstring Routine Between Agent Runs

7 min read

claude --teleport: Pull a Cloud Session Into Your Terminal, Start One With --cloud, Send Follow-Ups From the CLI, and the Requirements That Trip People Up

8 min read

Rounded Shoulders From Typing? A Two-Minute Chest Opener, Chair Twist and Wall Press Desk Routine for Developers Between Agent Runs

7 min read

Claude Code ultrathink Explained: It Now Runs the Turn at xhigh Effort, How It Differs From /effort, What It Costs in Time, and What to Do While It Runs

7 min read

Best Break Reminder Apps for Mac in 2026: Time Out, Stretchly, BreakTimer, LookAway and NotchFit Compared

7 min read

Claude Code 2.1.319: denyInsteadOfPrompting, MCP Background Tasks and What Changes for Unattended Runs and Notifications

8 min read

Drink Water and Stand Up Cues for Developers: Use Claude Code Agent Runs as Hydration and Standing Reminders

7 min read

Claude Code 2.1.323: Code Mode, Progress Heartbeat, Auto-Mode Fallback and 1M Context — What Changed for Unattended Runs

9 min read

Notch Media Controls on a Mac: What the MacBook Notch Can and Cannot Do, Dynamic Island-Style Apps vs NotchFit

7 min read