AgentCheck

Run a human acceptance checklist before merging AI-written code

Problem

People using AI coding agents keep hitting the same issues: messy formatting, almost no comments, ignored AGENTS.md rules, over-defensive code and low-fidelity frontend output. They judge agent output by gut feel with no executable, repeatable acceptance standard, so they end up reading every diff line by line.

Solution

A CLI and CI tool that takes a repo or diff and checks team conventions automatically: formatting, required comments, AGENTS.md rule hits, excessive try/catch, out-of-scope edits and more. It emits a shareable acceptance report and can compare how different models or agents performed on the same task.

Users

Solo developers and small engineering teams that ship AI-agent code

MVP

Read git diff or a target folder; 10 configurable built-in rules; HTML/Markdown acceptance report; compare two agent runs; GitHub Actions integration

Revenue

Free CLI; team subscription hosting rules and report history at $8/seat/month and up

Why now

Agent-written code is now normal but review standards are not, and existing code review tools target human PRs, a niche too small for incumbents