DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to review what an agent actually did in a session with Canny

Reads the ledger and re-derives every Stop verdict from the recorded facts.

Who it is forA reviewer or team lead who needs to check an agent's claims on a finished task before merging its output.

The problemAfter an agent reports done, there is no record of which commands it ran or whether the checks passed.

The outcomeA list of recorded events with exit codes and verdicts, plus confirmation that each Stop verdict replays to the same result.

What you need first

  • git installed
  • Node.js 22 or newer
  • Claude Code or Codex CLI installed in the project
  • A terminal to run the install commands
  • Repository is not on npm, so install is a git clone

Steps

  1. Install Canny and run node ~/.canny/src/dist/cli.js init in the project.
  2. Complete an agent session on the task you want to review.
  3. Run node ~/.canny/src/dist/cli.js status to list recorded sessions and their events.
  4. Run node ~/.canny/src/dist/cli.js replay on the session to re-derive every Stop verdict and report any mismatch. (inferred, check the README)

Prompt for your agent

Using the Canny repository at https://github.com/qkal/canny installed in ~/.canny/src, run `node ~/.canny/src/dist/cli.js status` and then `node ~/.canny/src/dist/cli.js replay` for the most recent session in <project-path>, and report each Stop verdict and whether any mismatch was found.

Caveat. The ledger stores only paths and outcomes, not file contents, so the review shows what happened but not the full text of every edit.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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