I stopped reviewing my coding agent's diffs file by file

Description and use

The author replaced manual diff review of AI‑generated code with an automated HTML report, enabling quick assessment of structure and correctness.

Rapid code changes from a coding agent make manual diff review difficult and time‑consuming.

The author can now review rapid agent‑generated changes efficiently, focusing on correctness rather than reconstructing code structure.

1. Install task‑view binary via curl or PowerShell
2. Add a skill for the agent to write a review file after each task
3. Agent completes a task and outputs a command like task-view open .review/change-<task>.json
4. Run the command to open the offline HTML page and review the change at a glance

Now a coding agent writes most of the code. A change that took an afternoon lands in minutes, then the next one, then the next.

task-view checks every file, line and commit in it against Git, then turns it into one offline HTML page

Now I open one page, see the whole change at a glance, and spend my attention on the question that matters: is this code right?