TaskForceNow

Noomoo — Git skill for Claude Code

Git community

noomoo Claude Code plugin: deterministic checks and lifecycle gates from specification to a verified pull request.

How to install Noomoo

This entry records only its repository, not the path inside it, so there is no exact command to give. Open TaskForceNow/noomoo and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Noomoo does

noomoo Claude Code plugin: deterministic checks and lifecycle gates from specification to a verified pull request.

Alternatives in Git

Worktree Deliver — Commit all work, push, and create a pull request from the current worktree 23.4k ★
Yeet — Stage, commit, push code, and open a GitHub pull request via CLI 14.6k ★
Generate PR Description — You are tasked with generating a comprehensive pull request description following the repository's standard te 10k ★

README

noomoo

[![license: Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE) ![platforms: Windows | macOS | Linux](https://img.shields.io/badge/platforms-Windows%20%7C%20macOS%20%7C%20Linux-blue) ![languages: 8](https://img.shields.io/badge/languages-8-brightgreen) ![Claude Code: plugin](https://img.shields.io/badge/Claude%20Code-plugin-D97757)

**English** · [Русский](README.ru.md) · [Deutsch](README.de.md) · [Español](README.es.md) · [Français](README.fr.md) · [Português](README.pt-BR.md) · [中文](README.zh-CN.md) · [日本語](README.ja.md)

Don't trust the agent. Trust the system.

**noomoo is an engineering harness for agentic software development.**

Let coding agents plan, build, test, review, and ship software inside rules your team can actually enforce.

Instead of trusting what an agent says it did, noomoo checks what happened in the repository.

Built for teams moving from AI-assisted coding to autonomous software delivery.

AI made coding cheap. Verification is the new bottleneck.

Coding agents can already implement features, fix bugs, run tests, open pull requests, and respond to review. The question is no longer: **Can the agent write the code?** The real questions are:

Did it understand the requirement?
Did it stay inside the task?
Did it follow the architecture?
Did it actually add the tests?
Did those tests really run?
Is the review still valid after the latest change?
Is “done” a fact — or just something the agent said?

The agent cannot talk its way around the gate.

Agent	noomoo
“All tests pass.”	Show the test result for this exact revision.
“I reviewed the change.”	Show a fresh review artifact for the current code.
“I only changed what the task required.”	Show the diff and prove the scope.
“The task is done.”	Prove it.