Helpmarq – Submit any project, get structured feedback from real users
Structured feedback templates prevent vague 'looks great' responses that waste founders' time.

https://github.com/backnotprop/plannotator
Plannotator Code Review works for any local or PR changes, jj, and p4. You can conduct a code review on your own or integrate it with your agents and submit feedbacks to create an automated iteration loop.
Guided reviews works just like linear, except it also summarizes all file changes for you. The most important code changes are surface to the top, provided with a semantic overview & grouped diffs. It does not need to rely on advanced model intelligence or high reasoning efforts. Open source models work great at this task! Providers enabled include Claude Code, Codex, OpenCode, Pi, Cursor, and Copilot.
Structured feedback templates prevent vague 'looks great' responses that waste founders' time.
There’s nothing magical about the calculators themselves — they’re practical, bite-sized tools (SE tax, loan amortization, cash flow forecast, invoice generator) that you can use without signing up. The project's claim that an AI agent built and deployed the site is the only thing that makes this stand out to developers; if the repo and agent workflow are documented it’ll be a nice demo of automating a static site pipeline, but as a user product it’s largely a competent, familiar toolkit.
Book principles as AI-agent prompts, but needs a working workflow to prove value.
Adapts accessibility-agents hook architecture to enforce voice instead of WCAG compliance.
Wraps Codex /review in MCP to separate review from implementation context.
Interactive simulations explain cooperative auctions for rent splitting and resource allocation.