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

How to check what an agent read before it edited a file with Agentplay

Replay a session to see which files the agent opened before changing code, and which it never opened.

Who it is forA developer reviewing an agent's pull-ready changes who wants to confirm it looked at the right code first.

The problemA diff shows the final edit but not the investigation that led to it, so a reviewer cannot tell whether the agent read the relevant files.

The outcomeA clear list of files read, edited, and skipped in the session, with the order they were touched.

What you need first

  • Python 3.11 or newer
  • uv, pipx, or pip to run agentplay
  • Existing session transcripts from a supported agent such as Claude Code, Codex, or Cursor on the same machine

Steps

  1. Run uvx agentplay in a terminal to build maps and open the local viewer.
  2. Open the session you want to review from the session list in the viewer.
  3. Use the map to find the edited file and check which files were seen or read before it.
  4. Press Space to play the timeline and watch the order of reads and edits.

Prompt for your agent

In the agentplay repo at https://github.com/Entelligence-AI/agentplay, run `uvx agentplay` and open the session that edited <target file path>. Report which files the agent read before the first edit to that file and which related files it never opened. Verify by confirming each listed read appears earlier than the first edit on the timeline.

Caveat. The map shows files and actions, not the agent's reasoning or the text of its prompts, so you still need the diff to judge the change itself.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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