- The most effective way to use Claude Code is by following an "explore, plan, code, and commit" workflow, which helps structure the development process and minimize errors.
- Leveraging "plan mode" is crucial for early course correction, allowing Claude to research and propose a plan without writing code, preventing extensive revisions later.
- To maximize Claude's efficiency and reliability, integrate tools like browser extensions for testing UIs and provide a robust test suite as a source of truth for validation.
The Explore → Plan → Code → Commit workflow in Claude Code
- Adopt the Workflow: Always follow the "explore, plan, code, commit" workflow when working with Claude Code to ensure a structured and efficient development process.
- Utilize Plan Mode: Enter "plan mode" (Shift+Tab) to let Claude read files, conduct web searches, and devise an action plan before any code is written, facilitating crucial early-stage adjustments.
- Thoroughly Review Plans: Review Claude's generated plan and revise it as needed before approval; this is the optimal point for course correction and ensures alignment with your requirements.
- Define Success Criteria: Clearly specify what Claude should consider "correct" within its plan to enhance its confidence in results and minimize back-and-forth interactions.
- Integrate Relevant Tools: Incorporate tools such as the Claude and Chrome extension for UI testing or a project-specific test suite to enable Claude to validate its work and achieve goals more effectively.
- Leverage Tests as Source of Truth: Ensure your test suite is reliable and consider having Claude write tests, but always validate them yourself to avoid false positives.
- Save Recurring Solutions: If Claude frequently encounters the same issues, instruct it to save the solution to its
Claude.mdfile for future reference. - Automate Pre-Commit Steps: Before committing, run a "sub agent code reviewer" through Claude and then have Claude generate a commit message in your preferred style.
Claude Code — An AI coding assistant or environment designed to help developers with various programming tasks.
plan mode — A specific operational mode within Claude Code where the AI analyzes files and researches to formulate an implementation strategy without modifying any code.
workflow — A defined sequence of steps or a structured process to achieve a specific outcome, in this context, how to effectively use Claude Code.
course correct — To make necessary adjustments or modifications to a plan or ongoing task to guide it back toward the desired objective.
dependencies — External software components, libraries, or modules that a project relies on to function correctly.
test suite — A collection of programmed tests used to verify the functionality, performance, and correctness of a software application.
sub agent code reviewer — An automated tool or AI module that examines source code for potential errors, style inconsistencies, or areas for improvement.
commit message — A descriptive text that accompanies a code commit in a version control system, explaining the changes made and their purpose.
image upload pipeline — A series of automated processes that handle, transform, and manage image files from the point of user upload to final storage or display.
webp conversion — The process of transforming an image file format into WebP, a modern format known for superior compression and quality on the web.
If you take one thing away from Claude Code, let it be this workflow. Explore, plan, code, and commit. Without this, most people jump straight to asking Claude to write code, which means more course correcting later on. The fastest way to handle step one and two is with plan mode. With plan mode, Claude can't edit files. It just reads files to gather research on how to tackle its implementation. To enter plan mode, hit shift and tab until you see the plan mode under the text input. I need to add webp conversion to our image upload pipeline. Figure out where the pipeline should happen, whether we need new dependencies and how to approach it and claude will read relevant files, do some web searches, and give you a plan of action. Make sure you review it and determine if it meets your criteria. Otherwise, I can ask it to add on or revise some areas. Perfect. And this right here is the best place to course correct because it's before any code is written. You can also use explore without being in plan mode by just asking Claude to explore your codebase. Now, once the plan looks good, you can select approve to accept the plan and let Claude tackle all the list items it provided. You can determine if you want Claude to auto accept the file edits or ask every single time. Claude will do its best to troubleshoot your codebase before considering the plan finished, but at times you'll need to course correct. This is the benefit of working with plan mode because after the plan is finished, we also have the context of how it got to the results to help it guide its next decision. In order for Claw to be confident in its results, it has to be clear on what it deems correct. When writing your plan, make this explicit. Adding tools that will help Claude complete its goals will remove a lot of back and forth. For example, if you're building web UIs, make sure you have the Claude and Chrome extension so that Claude code can control a tab and test out the UI before deeming it finished. In your project, include a test suite that Claude can continuously validate on. Claude can even write tests for you. Before passing this off to Claude, make sure that the tests are a source of truth for you and your team to avoid any false positives. Quick tip. If you find Claude keeps running into these same issues, ask Claude to save the solution to his Claude MD file. Now, once you have tested for yourself and are happy with the results, it's time to push your code. A tip before you commit, run a sub agent code reviewer to look at your code. Then you get Claude to generate a commit message for you in your style. Rinse and repeat. If you want to be effective with Claude Code, follow the explore, plan, code, and commit workflow. Exploration will give the relevant context Claude needs for your project. Plan will create a plan of action that Claude will use to determine if they are successful. Code is the back and forth that you and Claude do before settling on the final outcomes of the plan. Commit helps you review and push your code so you can start on your next feature.
TL;DR
- The most effective way to use Claude Code is by following an "explore, plan, code, and commit" workflow, which helps structure the development process and minimize errors.
- Leveraging "plan mode" is crucial for early course correction, allowing Claude to research and propose a plan without writing code, preventing extensive revisions later.
- To maximize Claude's efficiency and reliability, integrate tools like browser extensions for testing UIs and provide a robust test suite as a source of truth for validation.
Takeaways
- Adopt the Workflow: Always follow the "explore, plan, code, commit" workflow when working with Claude Code to ensure a structured and efficient development process.
- Utilize Plan Mode: Enter "plan mode" (Shift+Tab) to let Claude read files, conduct web searches, and devise an action plan before any code is written, facilitating crucial early-stage adjustments.
- Thoroughly Review Plans: Review Claude's generated plan and revise it as needed before approval; this is the optimal point for course correction and ensures alignment with your requirements.
- Define Success Criteria: Clearly specify what Claude should consider "correct" within its plan to enhance its confidence in results and minimize back-and-forth interactions.
- Integrate Relevant Tools: Incorporate tools such as the Claude and Chrome extension for UI testing or a project-specific test suite to enable Claude to validate its work and achieve goals more effectively.
- Leverage Tests as Source of Truth: Ensure your test suite is reliable and consider having Claude write tests, but always validate them yourself to avoid false positives.
- Save Recurring Solutions: If Claude frequently encounters the same issues, instruct it to save the solution to its
Claude.mdfile for future reference. - Automate Pre-Commit Steps: Before committing, run a "sub agent code reviewer" through Claude and then have Claude generate a commit message in your preferred style.
Vocabulary
Claude Code — An AI coding assistant or environment designed to help developers with various programming tasks.
plan mode — A specific operational mode within Claude Code where the AI analyzes files and researches to formulate an implementation strategy without modifying any code.
workflow — A defined sequence of steps or a structured process to achieve a specific outcome, in this context, how to effectively use Claude Code.
course correct — To make necessary adjustments or modifications to a plan or ongoing task to guide it back toward the desired objective.
dependencies — External software components, libraries, or modules that a project relies on to function correctly.
test suite — A collection of programmed tests used to verify the functionality, performance, and correctness of a software application.
sub agent code reviewer — An automated tool or AI module that examines source code for potential errors, style inconsistencies, or areas for improvement.
commit message — A descriptive text that accompanies a code commit in a version control system, explaining the changes made and their purpose.
image upload pipeline — A series of automated processes that handle, transform, and manage image files from the point of user upload to final storage or display.
webp conversion — The process of transforming an image file format into WebP, a modern format known for superior compression and quality on the web.
Transcript
If you take one thing away from Claude Code, let it be this workflow. Explore, plan, code, and commit. Without this, most people jump straight to asking Claude to write code, which means more course correcting later on. The fastest way to handle step one and two is with plan mode. With plan mode, Claude can't edit files. It just reads files to gather research on how to tackle its implementation. To enter plan mode, hit shift and tab until you see the plan mode under the text input. I need to add webp conversion to our image upload pipeline. Figure out where the pipeline should happen, whether we need new dependencies and how to approach it and claude will read relevant files, do some web searches, and give you a plan of action. Make sure you review it and determine if it meets your criteria. Otherwise, I can ask it to add on or revise some areas. Perfect. And this right here is the best place to course correct because it's before any code is written. You can also use explore without being in plan mode by just asking Claude to explore your codebase. Now, once the plan looks good, you can select approve to accept the plan and let Claude tackle all the list items it provided. You can determine if you want Claude to auto accept the file edits or ask every single time. Claude will do its best to troubleshoot your codebase before considering the plan finished, but at times you'll need to course correct. This is the benefit of working with plan mode because after the plan is finished, we also have the context of how it got to the results to help it guide its next decision. In order for Claw to be confident in its results, it has to be clear on what it deems correct. When writing your plan, make this explicit. Adding tools that will help Claude complete its goals will remove a lot of back and forth. For example, if you're building web UIs, make sure you have the Claude and Chrome extension so that Claude code can control a tab and test out the UI before deeming it finished. In your project, include a test suite that Claude can continuously validate on. Claude can even write tests for you. Before passing this off to Claude, make sure that the tests are a source of truth for you and your team to avoid any false positives. Quick tip. If you find Claude keeps running into these same issues, ask Claude to save the solution to his Claude MD file. Now, once you have tested for yourself and are happy with the results, it's time to push your code. A tip before you commit, run a sub agent code reviewer to look at your code. Then you get Claude to generate a commit message for you in your style. Rinse and repeat. If you want to be effective with Claude Code, follow the explore, plan, code, and commit workflow. Exploration will give the relevant context Claude needs for your project. Plan will create a plan of action that Claude will use to determine if they are successful. Code is the back and forth that you and Claude do before settling on the final outcomes of the plan. Commit helps you review and push your code so you can start on your next feature.