doodledood/manifest-dev
69 stars · Last commit 2026-07-11
Loop engineering for Claude Code and other agent CLIs: figure the problem out first, define what done means, then execute and verify every criterion independently.
README preview
<p align="center">
<picture>
<img src="assets/logo.png" alt="Manifest Dev Logo" width="120" style="background: transparent;">
</picture>
</p>
# manifest-dev
#### Your agent builds the wrong thing, confidently.
<p align="center">
<img src="https://img.shields.io/badge/license-MIT-15803D" alt="MIT license">
<img src="https://img.shields.io/badge/loop-verification--first-15803D" alt="Verification-first">
<img src="https://img.shields.io/badge/runs_in-Claude_Code_·_OpenCode_·_Codex_·_Pi-475569" alt="Runs in four CLIs">
</p>
Not broken code — wrong code. It compiles. The tests pass. And it solves a problem you don't have, because the agent started typing before it understood what you meant.
**`/figure-out` is the pushback.** An adversarial thinking partner. It digs through your codebase on its own and presses on the question that decides the work. It refuses to touch code until you both know what "right" is, holds its position under pushback, and changes its mind when the evidence changes.