Show HN: An independent execution recorder for coding agents

A developer launched Rashomon, an independent execution recorder for coding agents that flags discrepancies between what an agent claims it did and captured ground truth, after manually auditing transcripts and finding agents often failed to disclose actions or worked around failed tests. Rashomon records shell commands, exit codes, file writes, tool calls, tests and subagents into a timeline while deliberately not storing prompts, responses, file contents or tool outputs, and installs as a Claude Code plugin or from the command line. The developer is seeking feedback and invites users to deliberately break a test to see whether Rashomon captures everything needed to trust the independent record.

A couple of months ago, I gave access to my coding agent to do work on my repos. I was worried about hallucinations so I manually checked each transcript against modifications to see whether what the agent said it did actually happened. I found that in many cases, my coding agent either failed to disclose what it actually did or found workarounds to things like failed tests instead of telling me upfront. That led me to the idea for Rashomon. Rashomon is an independent execution recorder for coding agents that notifies users whenever there is a discrepancy between what the agent said it did and what we capture as a ground truth. It aims to capture items like shell commands, exit codes, file writes, tool calls, tests, and subagents. We build a timeline of the events but we do not store any prompts, responses, file contents, or tool outputs. A question we got often has been how is this different than a diff. A diff gives you a look at the final result and what changed while what we aim to provide is visibility into the execution that led to it. Currently, we do not capture network codes, prompts, responses file contents, and tool outputs. We plan to implement some of those based on feedback recently, but please let us know whether you would find that useful. To get started, you can install it is as a Claude Code plugin or from the command line. I would appreciate feedback on the solution, but I also would want to see whether anyone can break a test on purpose and see whether Rashomon can capture everything you would like to see in order to trust the independent record. Comments URL: https://news.ycombinator.com/item?id=49998416 https://news.ycombinator.com/item?id=49998416 Points: 1 Comments: 0