cursorrules: Command for Claude Code

.cursor/commands/commit-only.md

commit-only is a command for Claude Code, Cursor from kinopeee/cursorrules. It costs 0 tokens per session (543 once invoked), scanned A, original, MIT.

A command template for committing local changes to the current Git branch. A commit is a saved checkpoint in a project's change history.

In plain words
What is it for?
Use it when you want to review, stage, and save local code changes as a commit.
Why use it?
It standardises staging changes and writing a commit message without pushing anything to a remote repository.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

This is kinopeee/cursorrules's own configuration. It tells Claude Code and Cursor how to work on cursorrules itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cursorrules configures →

About the project

cursorrules is a collection of custom instructions and workflow commands for the Cursor coding editor. Developers copy its rule and command files into a project to guide coding practices, commits, pull requests, testing, tool use, and security-related behavior.

kinopeee/cursorrules · 1,107 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to kinopeee/cursorrules. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kinopeee/cursorrules/main/.cursor/commands/commit-only.md
Clone the repo
git clone --depth 1 https://github.com/kinopeee/cursorrules

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for commit-only

README.md
[![agentmods](https://agentmods.dev/badge/commands/kinopeee/cursorrules/commit-only/github.svg)](https://agentmods.dev/commands/kinopeee/cursorrules/commit-only)
Your own site
<a href="https://agentmods.dev/commands/kinopeee/cursorrules/commit-only"><img src="https://agentmods.dev/badge/commands/kinopeee/cursorrules/commit-only/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for commit-only

Your own site · 80×15
<a href="https://agentmods.dev/commands/kinopeee/cursorrules/commit-only"><img src="https://agentmods.dev/badge/commands/kinopeee/cursorrules/commit-only.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00543
Opus 5.5 $0.00000 $0.00217
Sonnet 5.5 $0.00000 $0.00109
Haiku 4.5 $0.00000 $0.00054

Measured 1mo ago against content hash a8ae2c549e24, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit-only scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/commands/commit-only.md · 55 lines

What it actually says

コミットのみ(現在のブランチ)

概要

現在のブランチに対して、ローカルの変更をコミットだけ行うためのシンプルなコマンドです。
リモートへのプッシュやブランチ戦略(main 直コミット禁止など)は扱わず、コミットメッセージ規約に沿ったコミットだけを行います。

前提条件

  • 変更済みファイルが存在すること
  • コミットメッセージの具体的な書き方は、.cursor/rules/commit-message-format.mdc などで定義された規約に従うこと

実行手順(対話なし)

  1. 未コミット差分を確認し、コミットメッセージの内容を検討する(例:git diff や git diff --cached)
  2. 変更のステージング(git add -A)
  3. コミット(環境変数または引数でメッセージを渡す)

A) 安全な一括実行(メッセージ引数版)

MSG="<Prefix>: <サマリ(命令形/簡潔に)>" \
git add -A && \
git commit -m "$MSG"

例:

MSG="fix: 不要なデバッグログ出力を削除" \
git add -A && \
git commit -m "$MSG"

B) ステップ実行(読みやすさ重視)

# 1) 差分を確認
git status
git diff

# 2) 変更をステージング
git add -A

# 3) コミット(メッセージを編集)
git commit -m "<Prefix>: <サマリ(命令形/簡潔に)>"

ノート

  • コミットメッセージのフォーマットやメッセージ生成の原則は、.cursor/rules/commit-message-format.mdc のルールに従ってください。
  • ブランチ戦略(例:main 直コミット禁止、作業用ブランチ運用)やリモートへのプッシュ (git push) は、このコマンドの対象外です。必要に応じて、プロジェクトごとの README / CONTRIBUTING / 別コマンドで定義してください。
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 55 lines · 0 tokens per session scan A a8ae2c549e24

Subscribe to this mod's changes

commit-only is a command published in the GitHub repository kinopeee/cursorrules (1,107 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 543 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.