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

How to review agent diffs line by line and send comments back with Acryl

Comment on an agent's diff in ACRYL and send those comments straight back to the agent.

Who it is forA developer who lets an agent edit code and wants to review the changes before accepting them, without copying notes into a separate chat.

The problemFeedback on agent changes usually lives in a separate chat or an external review tool, so the agent often misses the exact lines you flagged.

The outcomeYou review diffs inside the canvas, attach line-by-line comments, and send them to the agent in the same session.

What you need first

  • macOS, Windows, or Linux machine
  • Installed coding agent such as Claude Code, Codex, or Gemini CLI, if you want to launch it from ACRYL
  • Node.js ^22.19.0 or >=24.0.0 and Corepack, only for running from source

Steps

  1. Open the project in ACRYL and let an agent session make changes in a git worktree.
  2. Open the diff for the changed files in a canvas tab.
  3. Add review comments on the specific lines that need work.
  4. Send the comments back to the agent from the diff view.
  5. Check the updated diff and repeat until the changes are accepted.

Prompt for your agent

Using the acryl repo at github.com/acryldev/acryl, open the diff for the worktree at <worktree-path> in ACRYL, add a review comment on one changed line, and send it to the agent. Report the line number and the agent's reply, and verify the comment appears in the session.

Caveat. The README describes the diff review feature in general terms only, so confirm the exact send-back behavior in the documentation for your release.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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