agentmods.dev

git-commit-comment-rule

git-commit-comment-rule is a skill for Claude Code, Codex from eaglesakura/agent-skills. It costs 188 tokens per session (2,167 once invoked), scanned A, original, MIT.

A set of rules for writing Git commit messages. It defines the message structure, allowed prefixes, language, bullet format, and automatic issue-reference handling.

In plain words
What is it for?
Use it when creating, amending, or proposing commit messages, including commits made through GitHub command-line operations.
Why use it?
Commit histories become harder to understand when messages use inconsistent wording or duplicate issue references. These rules make each commit’s purpose and reason easier to read.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Cursor.

not rated 2repo 1mo ago A scan 188 tokens original MIT

Good fit Use it when creating, amending, or proposing commit messages, including commits made through GitHub command-line operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eaglesakura/agent-skills/git-commit-comment-rule
View source ↗ eaglesakura/agent-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add eaglesakura/agent-skills --skill git-commit-comment-rule
Clone the repo
git clone --depth 1 https://github.com/eaglesakura/agent-skills

Made for: Claude Code, Codex.

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 git-commit-comment-rule

README.md
[![agentmods](https://agentmods.dev/badge/skills/eaglesakura/agent-skills/git-commit-comment-rule/github.svg)](https://agentmods.dev/skills/eaglesakura/agent-skills/git-commit-comment-rule)
Your own site
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/git-commit-comment-rule"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/git-commit-comment-rule/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 git-commit-comment-rule

Your own site · 80×15
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/git-commit-comment-rule"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/git-commit-comment-rule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,167 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 $0.00188 $0.02167
Opus 5.5 $0.00075 $0.00867
Sonnet 5.5 $0.00038 $0.00433
Haiku 4.5 $0.00019 $0.00217

Measured 2mo ago against content hash 2d009ab7630b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-commit-comment-rule 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 2mo 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.

packages/ohitorisama/.apm/skills/git-commit-comment-rule/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Comment Rule

AI Agent が git commit や gh 経由のコミットを行うとき、リポジトリ慣習に沿った日本語メッセージを書く。

いつ使うか

  • ユーザーがコミットを依頼したとき（メッセージの考案を含む）
  • 差分を見てコミットメッセージを提案・確定するとき
  • 複数コミットに分割するとき、各コミットの文案を付けるとき
  • git commit --amend でメッセージを直すとき

いつ使わないか

  • PR のタイトル／本文だけを書くとき（コミットメッセージが不要な場合）
  • ブランチ名の決定だけ（workspace-git-branch-rule を使う）
  • git log の閲覧・履歴調査だけ
  • ユーザーが「メッセージは自分で書く」と明示したとき

全体ルール

  • 言語: 1 行目・箇条書きは 日本語 で書く
  • refs # は書かない: feature/id/{Issue番号}/... ブランチでは .hooks/commit-msg が 1 行目末尾へ refs #{Issue番号} を自動付与する。Agent がメッセージに含めると重複する
  • Agent 署名: 本文末尾に Git trailer 形式の署名を付ける（後述）

メッセージ構造

{prefix}: {変更内容を一文で要約}

- {何を変えたか}（{なぜ変えたか}）
- {追加の変更や理由があれば続ける}

Co-authored-by: Cursor Agent
  • 1 行目と箇条書きの間、箇条書きと署名の間には 空行 を 1 行入れる
  • 1 行目は 50 文字前後を目安に簡潔に（厳密上限はないが冗長にしない）
  • 箇条書きは - で始める。各項目で「何を」「なぜ」の両方が読み取れるようにする

1 行目の prefix

先頭は次のいずれか 1 つ を選び、{prefix}: の直後から日本語要約を書く。

prefix 使う場面 例
add: 新規追加（機能・ファイル・公開 API・テストの新設など） add: ログイン画面の ViewModel を追加
chg: 既存の振る舞い・仕様・依存関係の変更（ユーザー体験や API 契約が変わる） chg: freezed を 4.0.0 stable に更新
fix: バグ修正・クラッシュ・誤動作の是正 fix: 未初期化の Repository で落ちる問題を修正
mod: 構造変更・リファクタリング・設定・CI・ドキュメント整備など、上記以外の改修 mod: CI ワークフローの対象ブランチを拡張
del: 機能・ファイル・不要コードの削除 del: 未使用の legacy 認証モジュールを削除

prefix の選び方

  1. バグを直した → fix:
  2. 新しいものを足した（機能・テスト・型定義の新設）→ add:
  3. 既存の意味・振る舞いを変えた（ライブラリ更新で生成コードが変わる、UX 変更）→ chg:
  4. コードを削除した → del:
  5. 上記に当てはまらない内部整理（リファクタ、CI 設定、コメント、import 整理）→ mod:

迷ったときは「レビュアーがこの PR を読むとき、新機能なのか修正なのかバグ直しなのか」を基準に選ぶ。

使わない prefix

feat: test: ci: docs: など Conventional Commits の別表記は 使わない。意味に近いものは上表へマッピングする。

箇条書き（2 行目以降）

  • 必須: 変更が自明でない限り、1 行目だけのコミットにしない
  • 各 - 行は 1 つの論点に絞る
  • 「何を」だけでなく「なぜ」を括弧や続きの句で明示する
  • 複数ファイルにまたがる場合は、関心ごと（例: Domain / Repository / UI）で分けてもよい

良い例:

fix: 通知 Permission 未許可時にクラッシュする

- Permission 拒否後も subscribe を呼んでいたため、結果をチェックして早期 return する（再現クラッシュの防止）
- 拒否パスの Unit Test を追加（回帰防止）

Co-authored-by: Cursor Agent

Read the full file on GitHub · 159 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 159 lines · 188 tokens per session scan A 2d009ab7630b

Subscribe to this mod's changes

git-commit-comment-rule is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 188 tokens to every session and 2,167 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-04.

CommitsGit and workflow
Related

git-commit-comment-rule compared with skills from other repositories

git-commit-comment-rule next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
git-commit-comment-ruleeaglesakura/agent-skillsSkill21mo agoMITA188Claude Code, Codex
create-prprisma/ormSkill48k2d agoApache-2.0A48Claude Code, Codex
git-commitThinkInAIXYZ/deepchatSkill6.4ktodayApache-2.0A15Claude Code, Codex
repo-syncdavidondrej/skillsSkill4.3ktodayMITA25Claude Code, Codex
engineer-bot-opsmakecindy/cindySkill9.5ktodayApache-2.0A57Claude Code, Codex
mcore-split-prNVIDIA/skillsSkill3.9k2d agoApache-2.0A25Claude Code
contributingHugoRCD/evlogSkill1.9kyesterdayMITA68Claude Code, Codex