By using this site, you agree to the Privacy Policy and Terms of Use.
Accept
World of SoftwareWorld of SoftwareWorld of Software
  • News
  • Software
  • Mobile
  • Computing
  • Gaming
  • Videos
  • More
    • Gadget
    • Web Stories
    • Trending
    • Press Release
Search
  • Privacy
  • Terms
  • Advertise
  • Contact
Copyright © All Rights Reserved. World of Software.
Reading: Inside the Development Workflow of Claude Code’s Creator
Share
Sign In
Notification Show More
Font ResizerAa
World of SoftwareWorld of Software
Font ResizerAa
  • Software
  • Mobile
  • Computing
  • Gadget
  • Gaming
  • Videos
Search
  • News
  • Software
  • Mobile
  • Computing
  • Gaming
  • Videos
  • More
    • Gadget
    • Web Stories
    • Trending
    • Press Release
Have an existing account? Sign In
Follow US
  • Privacy
  • Terms
  • Advertise
  • Contact
Copyright © All Rights Reserved. World of Software.
World of Software > News > Inside the Development Workflow of Claude Code’s Creator
News

Inside the Development Workflow of Claude Code’s Creator

News Room
Last updated: 2026/01/10 at 4:32 PM
News Room Published 10 January 2026
Share
Inside the Development Workflow of Claude Code’s Creator
SHARE

Claude Code’s creator Boris Cherny described how he uses it at Anthropic, highlighting practices such as running parallel instances, sharing learnings, automating prompting, and rigorously verifying results to compound productivity over time.

Cherny does not customize Claude Code, as he finds it works great out of the box, and runs many sessions in parallel, including five locally in his MacBook’s terminal and 5-10 on Anthropic’s website. To avoid conflicts, each local session uses its own git checkout, rathen than branches or worktrees. He starts remote sessions with & from the CLI and often uses --teleport to move them back an forth. However, 10-20% of those sessions are abandoned due to unexpected scenarios.

Cherny prefers using Opus 4.5 with thinking for all coding, valuing its higher quality and reliability over Sonnet despite its slower speed. He also finds Opus better at tool use and notes that it is ultimately faster overall than the smaller model.

Each team at Anthropic maintains a CLAUDE.md in git to document mistakes, so Claude can improve over time, and best practices, such as style conventions, design guidelines, PR template, and so on. Cherny often uses the @.claude tag on coworkers’s PRs to add learnings to CLAUDE.md, ensuring knowledge from each PR is preserved. Currently, Cherny says, their CLAUDE.md is 2.5k tokens.

One key aspect of his workflow is starting with a plan and refine it iteratively before switching to auto-editing:

If my goal is to write a Pull Request, I will use Plan mode, and go back and forth with Claude until I like its plan. From there, I switch into auto-accept edits mode and Claude can usually 1-shot it. A good plan is really important!

Cherny executes daily workflows like commits, PRs, simplification, and verification using slash commands to start sub-agents. All commands are stored in .claude/commands/, which also helps reduce the need for explicit prompting.

For example, Claude and I use a /commit-push-pr slash command dozens of times every day. The command uses inline bash to pre-compute git status and a few other pieces of info to make the command run quickly and avoid back-and-forth with the model.

While Claude’s code is usually well formatted, inconsistencies can sometimes cause CI failures. To prevent this, Cherny runs a PostToolUse hook to clean up the code:


"PostToolUse" : [
    "matcher": "WritelEdit",
    "hooks": [
        {
            "type": "command",
            "command": "bun run format || true"
        }
    ]

For security, Cherny almost never uses --dangerously-skip-permissions. Instead, he enables commonly used bash commands that are safe in his environment via /permissions. This spares him unnecessary permission prompts on commands like bun run build:*, bun run test:*, cc:* and many others. The only case when he uses --dangerously-skip-permissions is for running long-running tasks inside a sandbox to prevent Claude from stopping repeatedly.

The most important tip is to give Claude a way to verify its work through a feedback loop, such as running a bash command, or a test suite, or testing the app through the browser or a simulator. This can improve the quality of the final result by a factor of 2–3:

Claude tests every single change I land to claude.ai/code using the Claude Chrome extension. It opens a browser, tests the UI, and iterates until the code works and the UX feels good.

Overall, Cherny explains, this workflow lets his team focus on code review and steering, noting that when an engineer reads a PR, the code is already in good shape.

Cherny’s tweets sparked an extended discussion on X.com, including some useful clarifications we have included here, but be sure to read the original for full detail.

Sign Up For Daily Newsletter

Be keep up! Get the latest breaking news delivered straight to your inbox.
By signing up, you agree to our Terms of Use and acknowledge the data practices in our Privacy Policy. You may unsubscribe at any time.
Share This Article
Facebook Twitter Email Print
Share
What do you think?
Love0
Sad0
Happy0
Sleepy0
Angry0
Dead0
Wink0
Previous Article Former Amazon execs raise M for agentic commerce startup that uses AI to generate custom storefronts Former Amazon execs raise $15M for agentic commerce startup that uses AI to generate custom storefronts
Next Article I Built a Poor Man’s Pixar Using Python, Gemini, and My Sense of Humor | HackerNoon I Built a Poor Man’s Pixar Using Python, Gemini, and My Sense of Humor | HackerNoon
Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Stay Connected

248.1k Like
69.1k Follow
134k Pin
54.3k Follow

Latest News

China’s Zeekr says first hybrid EV won’t have all-electric variant · TechNode
China’s Zeekr says first hybrid EV won’t have all-electric variant · TechNode
Computing
Origami-style Mars home that deploys ‘with single pull of a string’ revealed
Origami-style Mars home that deploys ‘with single pull of a string’ revealed
News
NIO’s Onvo L90 SUV starts at game-changing ,000 price · TechNode
NIO’s Onvo L90 SUV starts at game-changing $27,000 price · TechNode
Computing
NFL Wild Card Weekend: TV Schedule, Playoff Matchups, How to Watch and More
NFL Wild Card Weekend: TV Schedule, Playoff Matchups, How to Watch and More
News

You Might also Like

Origami-style Mars home that deploys ‘with single pull of a string’ revealed
News

Origami-style Mars home that deploys ‘with single pull of a string’ revealed

10 Min Read
NFL Wild Card Weekend: TV Schedule, Playoff Matchups, How to Watch and More
News

NFL Wild Card Weekend: TV Schedule, Playoff Matchups, How to Watch and More

14 Min Read
Volkswagen looks to deliver advanced infotainment and connectivity capabilities | Computer Weekly
News

Volkswagen looks to deliver advanced infotainment and connectivity capabilities | Computer Weekly

5 Min Read
The Week in AI: Physical AI Vaporware, ChatGPT Health, Grok Gets Inappropriate
News

The Week in AI: Physical AI Vaporware, ChatGPT Health, Grok Gets Inappropriate

11 Min Read
//

World of Software is your one-stop website for the latest tech news and updates, follow us now to get the news that matters to you.

Quick Link

  • Privacy Policy
  • Terms of use
  • Advertise
  • Contact

Topics

  • Computing
  • Software
  • Press Release
  • Trending

Sign Up for Our Newsletter

Subscribe to our newsletter to get our newest articles instantly!

World of SoftwareWorld of Software
Follow US
Copyright © All Rights Reserved. World of Software.
Welcome Back!

Sign in to your account

Lost your password?