DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to hand a coding task to a built-in coding agent with Wu

Use Wu's agent workspace with Claude Code or Codex to draft changes inside your project.

Credentials. The agent needs your own Claude Code or Codex access, so keep API keys and tokens out of shared project files.

Who it is forA developer with a bug fix or small feature they want an agent to draft inside the project they already have open.

The problemSwitching between an editor and a separate agent tool breaks flow and makes it harder to review the proposed changes in context.

The outcomeThe agent proposes an edit inside Wu, and you review the changed lines in the same workspace before keeping them.

What you need first

  • A desktop computer running macOS, Linux, or Windows
  • Permission to install a desktop app
  • Optional: access to Claude Code or Codex for the agent use case

Steps

  1. Install Wu with the Download section, or on macOS or Linux run curl -fsSL https://wu.dstrml.org/install.sh | sh.
  2. Install and sign in to Claude Code or Codex separately, since the README names them as built-in but does not describe setup. (inferred, check the README)
  3. Open your project folder in Wu and start the agent from the agent workspace. (inferred, check the README)
  4. Describe the task to the agent and point it at the file it should change.
  5. Read the proposed changes line by line and keep only what you want.

Prompt for your agent

In the dstrml/wu repo context, open <project-path> in Wu and use the built-in Claude Code or Codex agent to make this change: <task>. Expected output: a proposed edit to <file-path>. Verify by reading every changed line before saving.

Caveat. The README names built-in support for Claude Code, Codex, and OpenCode but does not explain how agent setup or sign-in works, so check the docs first.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page