"Plan mode was useful, and is no longer useful." - Boris Cherny (@bcherny), creator of Claude Code Plan Mode is a mode in Claude Code that doesn't write code. It takes in your prompt and makes a plan for you to review and agree on before it builds anything. I used to use Plan Mode as my default way of working. But recently I found that I no longer use it at all. My reason is that the models have gotten so much better that I don't need Plan mode anymore. This puts into words something I've been feeling: models like Fable and Opus, especially Opus 5.5 in Claude Code, have gotten to the point where you don't need Plan Mode anymore. Instead of Plan mode, I've adopted the @steipete method of "Just Talk To Your Agent". I have a set of Skills which facilitate a conversation and help get clear on the goals, constraints, and verification criteria before we kick off the build

/create-issues is a simple Skill that makes my building process much more structured and scalable. /create-issues takes in a project spec or other input and creates issues in GitHub or Linear. I mainly use it in 3 ways: (1) From a project spec: you get a bunch of issues, plus the dependencies between them, so you know which to build first. (2) From a feature spec: you get one issue you can build. (3) From a chat message: you don't even need a spec. Dump a bunch of screenshots and say, "Here are the bugs in the app. Please create issues to capture all of these bugs, and let's tackle them in a next session." This makes it easy to create a bunch of issues at once. One of the most important parts of the issue template is the acceptance and verification criteria, which tell your Agent how to verify that the feature actually works as intended.

Models I use the most: 1. Opus 5.5 (on medium / extra high effort) 2. GPT-6 Astra (medium / ultra) 3. Everything else

"I could have learned Claude Code on my own, but it would have taken much longer to reach the same level of confidence." - Mario, ML Ops Engineer Claude Code 2 Day Launchpad starts this Friday. It's a live building experience for people who want a better system for their work with Claude Code. How it works: - You'll build a project of your choice with Claude Code through a series of mini-projects. (It can be a new app or a workflow for your job / business) - You'll learn a repeatable system for building and Claude Code fundamentals that will make every future project easier. - You'll get live help from me, plus a supportive group of peers also building live. - You'll walk away with real confidence to use Claude Code in your work, whether its building products with AI or AI-enabled workflows. Learn more and grab your spot here: claudecode101.ai

Once you're clear about what you want to build, you could jump straight into building. But for big projects or complex featureas, you might still need to make big decisions so that your agent of choice (be it Claude Code, Codex, Cursor etc) builds exactly what you want, the way you want it. And so I find that you still need a way to align with your agents on product requirements, engineering design, and verification criteria. My Skill /create-spec helps me do that and then encodes those decisions in a document we can use to build. Here's how it works:

I’m excited to announce Claude Code: 2 Day Launchpad. It's a live building experience for people who want a better system for their work with Claude Code. How it works: - You'll build a project of your choice with Claude Code through a series of mini-projects. It can be a new app or a workflow for your job / business. - You'll learn a repeatable system for building and Claude Code fundamentals that will make every future project easier. - You'll get live help from me, plus a supportive group of peers also building live. - You'll walk away with real confidence to use Claude Code in your work, whether its building products with AI or AI-enabled workflows. The next live cohort is happening Friday 23 October. Learn more (and secure a spot): claudecode101.ai

I'm not sure if I agree with spec-driven development as a whole, but I do find creating specs useful for capturing key product, engineering and verification decisions before building. My /create-spec skill explores your codebase and interviews you to get clear on key decisions. Then it writes a project spec (for a new project or large initiative) or a feature spec (for a change to an existing project). I walk through the spec template /create-spec fills out in the demo below. If you have your own new project, product requirements doc, or engineering design doc template, you can easily swap that in instead.

One of the Skills I use the most is /get-clarity. It helps breakthrough complexity whenever I'm stuck or just need to think through a decision, plan or problem. /get-clarity interviews me to figure out what I am actually trying to do, what's the real goal, and what's the best way to proceed. It always gives you options to pick from. I find that having this contrast lets you make better decisions: At each step, it proposes something and you react: "these are the parts I like", "this is not it", "this is what I want you to change." Every round gets you closer to a clear decision, until you reach a breakthrough. The /get-clarity skill can also output a decision document, which you can then use as a record of your breakthrough, or to handoff to your agent to start a build session. I demo an example of me using /get-clarity below: