Coding agents rewrite code you never asked them to touch, and the tests still pass. Sonah reads the agentβs Claude Code or Codex session along with the code, then shows on one page: whether each ask was done, what the agent decided on its own, which of its claims its own results contradict, and what is wrong in the code. Every quote is checked word for word. Runs locally through your own Claude login. No account, no telemetry. Free for individuals.
Software EngineeringDeveloper ToolsGitHub







Advertisement (Responsive)
π¬ Comments
π Details
Launched
October 26, 2026
Upvotes
9
Comments
2
Source
Public data
Advertisement (Responsive)






This tool has 2 comments on Product Hunt.
View comments on Product Hunt β