backthread

Add Reasoning To PRs — Git skill for Claude Code

Git community

Claude Code hook that writes a forward-only why-block (decisions, trade-offs, assumptions, limitations) into your PR description or commit message at PR-create / direct-push time.

How to install Add Reasoning To PRs

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

What Add Reasoning To PRs does

Claude Code hook that writes a forward-only why-block (decisions, trade-offs, assumptions, limitations) into your PR description or commit message at PR-create / direct-push time.

Alternatives in Git

Bulletproof Quick Start Guide — Target Audience: Complete beginners Never used Python/git before 11.1k ★
Contributing To Context-mode — This project is licensed under the Elastic License 2.0 (ELv2) and moves forward with your support 5.6k ★
CCometixLine — A high-performance Claude Code statusline tool written in Rust with Git integration and real-time usage tracki 2.4k ★

README

**English** · [简体中文](docs/i18n/README.zh-CN.md) · [繁體中文](docs/i18n/README.zh-TW.md) · [日本語](docs/i18n/README.ja.md) · [한국어](docs/i18n/README.ko.md) · [Español](docs/i18n/README.es.md) · [Português](docs/i18n/README.pt-BR.md) · [Русский](docs/i18n/README.ru.md)

add-reasoning-to-prs

**Self-documenting PRs.** A [Claude Code](https://docs.claude.com/en/docs/claude-code) hook that writes the *why* — decisions, trade-offs, assumptions, limitations — into every pull request, automatically. Composed by your own agent, on your own machine.

[![npm](https://img.shields.io/npm/v/add-reasoning-to-prs.svg)](https://www.npmjs.com/package/add-reasoning-to-prs) [![CI](https://github.com/backthread/add-reasoning-to-prs/actions/workflows/ci.yml/badge.svg)](https://github.com/backthread/add-reasoning-to-prs/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE) [![Claude Code](https://img.shields.io/badge/Claude%20Code-compatible-8A63D2.svg)](https://docs.claude.com/en/docs/claude-code)

![Before and after: a PR titled "update auth flow" with an empty description, next to the same PR with a generated Decisions / Trade-offs / Assumptions / Limitations block.](assets/demo.gif)

AI writes your code. Nobody writes down *why*. Three weeks in, your git history is a pile of decisions you technically own but never actually made — the diff says *what* changed, `git blame` says *who*, and the reasoning is just… gone.

This is a hook that fixes that at the source: right before your agent opens a PR (or lands a commit on your default branch), it writes a short **"why" block** — the decisions it made, the trade-offs it weighed, what it assumed, and what it knowingly left — straight into the description. From the actual session. Not the diff.