Y — Development skill for Claude Code

y

**y** is a malleable desktop coding-agent app.

It is built around a simple idea: software should become malleable while you use it. The main interface is a chat, but the app can reshape its own UI through a protected Modify surface. You can ask y to change how y itself works, keep the change if it renders safely, or roll it back if it does not.

y is not a new agent model. It is a local, chat-first workspace for the coding agents you already use: Claude Code, OpenAI Codex, and other CLI-native agents over time.

Privacy at a glance

y does not collect your chat data. Project files, terminal commands, chat contents, and agent prompts are not collected or stored by y.

y only uses product analytics for basic app health and usage signals, like sign-in state, feature usage, feedback, and missing-brick requests. "Local" means Claude Code and Codex run on the user's machine through their official CLIs. Login supports account-based product features and basic usage analytics.

Things to try

• Run Claude Code and Codex side by side from one desktop app.
• Let your coding agent run git init, then start separate chats in isolated workspaces so agents can work in parallel without touching the same checkout.
• Ask Modify to change y's interface live, then review the generated diff before keeping it.
• Add or adjust app UI controls, layout, copy, and local workflow affordances through Modify.
• Open the file tree, terminal, and diff views while an agent is working.
• Revert a Modify change if the new UI is not what you wanted.

What Modify is

Modify is the part of y that e