# Prove2Me for software: a contract protocol so agent swarms build code with no human review (the repo built itself)

**URL:** <https://forum.cursor.com/t/prove2me-for-software-a-contract-protocol-so-agent-swarms-build-code-with-no-human-review-the-repo-built-itself/171643>\
**Category:** Built with Cursor\
**Tags:** multitask, cloud-agents, review\
**Created:** [September 14, 2026, 4:43pm UTC](https://forum.cursor.com/t/prove2me-for-software-a-contract-protocol-so-agent-swarms-build-code-with-no-human-review-the-repo-built-itself/171643 "2026-09-14T16:43:35Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![vance](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/vance/32/111546_2.png) [@vance](https://forum.cursor.com/u/vance)\
**Post date:** [September 14, 2026, 4:43pm UTC](https://forum.cursor.com/t/prove2me-for-software-a-contract-protocol-so-agent-swarms-build-code-with-no-human-review-the-repo-built-itself/171643/1 "2026-09-14T16:43:35Z")

</div>

Prove2Me worked because it moved trust from human review to a checker — immutable statements plus the Lean compiler. That’s the footing that let a swarm of Claude agents formalize Fermat’s Last Theorem in 11 days, 30,300 theorems, with nobody reviewing proofs mid-run.

I’ve been experimenting with the obvious follow-up: **what plays the compiler’s part in ordinary software?** Because if you’ve pointed several agents at one codebase in parallel — Cursor background agents included — you’ve hit the exact two walls the Prove2Me authors hit first:

1. **They collide.** Two agents editing the same module at once is a merge disaster.
2. **Everything queues behind you.** The agents are fast, but every diff still needs your eyes — so _you_ are the bottleneck.

build2me’s answer: **every unit of work is a contract that carries its own acceptance command.**

- A **contract** states _what must be true_, stays silent about _how_, and ships with the shell command that decides it.
- Agents pull contracts off a ranked **frontier** — no claiming, no assigned owners, no coordination between agents at all.
- A **verifier** is the only judge. Acceptance command passes → Done. No PR review.
- Contracts are **versioned** : when understanding changes mid-build, the statement gets revised and downstream contracts reopen automatically.

The receipt: the repo was built by a swarm of Claude agents operating under the protocol itself — 14 of 16 contracts Done, two contract statements revised live during the run, verification green in CI.

It’s agent-agnostic: anything that can edit files and run shell commands can participate — Cursor agents included. Plain files plus a few node scripts, no framework to adopt.

Repo (protocol spec, rendered DAG, one-command scaffolder): [GitHub - ■■■■■■■■■■■■■■■■■■■■■ A prove2me-style protocol for building software with swarms of parallel agents: immutable contract DAG, lock-free coordination, cascade verification. · GitHub](https://github.com/shitianfang/build2me)

Two things I’d genuinely like this crowd’s take on: where does “acceptance command as the compiler” break down — Lean’s checker is complete, a shell command isn’t, and I want to know where that gap bites in practice? And has anyone found a different way to run parallel agents without becoming the review bottleneck yourself?