commit

A helper for creating a Git commit, a saved snapshot of code changes, with a standard Japanese message format.

In plain words
What is it for?
It helps inspect changes, choose files to stage, classify the change as a feature, fix, documentation update, test, or other type, and create the commit.
Why use it?
It finds the repository with changes and helps decide what belongs in the commit when files are not yet staged.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nanasess/eccube-dev-agents/commit
Any agent
npx skills add nanasess/eccube-dev-agents --skill commit
Clone the repo
git clone --depth 1 https://github.com/nanasess/eccube-dev-agents

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.00989
Opus 5 $0.00006 $0.00495
Sonnet 5 $0.00002 $0.00198
Haiku 4.5 $0.00001 $0.00099

Measured yesterday against content hash c28db220591c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit 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 yesterday.

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.

plugins/eccube-dev-agents/skills/commit/SKILL.md · 76 lines

What it actually says

自動コミットメッセージ生成

Conventional Commits v1.0.0 形式の日本語コミットメッセージを自動生成してコミットします。 複数リポジトリの親ディレクトリから実行した場合、変更のあるリポジトリを自動検出します。

手順

1. リポジトリ検出

  1. git rev-parse --is-inside-work-tree でカレントディレクトリが git リポジトリか確認
  2. git リポジトリの場合:
    • git status --porcelain で変更を確認
    • 変更がある場合はそのリポジトリで作業を続行
  3. git リポジトリでない場合、または変更がない場合:
    • find . -maxdepth 2 -name ".git" -type d でサブディレクトリ内の git リポジトリを走査し、その親ディレクトリ(リポジトリルート)を特定
    • 各リポジトリルートで git -C <dir> status --porcelain を実行して変更の有無を確認
    • 変更のあるリポジトリをリストアップ
  4. 変更のあるリポジトリが複数の場合:
    • 一覧を表示してユーザーに選択を求める
  5. 変更のあるリポジトリがない場合:
    • 「変更のあるリポジトリが見つかりません」と報告して終了

2. ステージング確認

  1. 対象リポジトリで git -C <dir> status を実行
  2. git -C <dir> diff --staged でステージング済みの変更を確認
  3. ステージングされたファイルがない場合:
    • git -C <dir> diffgit -C <dir> status --porcelain で未ステージの変更を表示
    • ユーザーに追加するファイルを確認
    • 承認後 git -C <dir> add <files> でステージング

3. 変更分析とコミットメッセージ生成

  1. git -C <dir> diff --staged で変更内容を分析
  2. Conventional Commits タイプを判定:
    • 新規ファイル追加: feat:
    • バグ修正: fix:
    • ドキュメント: docs:
    • リファクタリング: refactor:
    • テスト: test:
    • パフォーマンス改善: perf:
    • ビルド・依存関係: build:
    • その他: chore:
  3. スコープを判定(影響を受けるファイル/ディレクトリから括弧付きで追加)
  4. 破壊的変更がある場合は ! を追加
  5. 日本語でメッセージ本文を作成
  6. $ARGUMENTS に追加コンテキストがあれば考慮する

4. コミット実行

HEREDOC 形式でコミットメッセージを渡す:

git -C <dir> commit -m "$(cat <<'EOF'
feat(scope): メッセージ本文

Co-Authored-By: Claude <[email protected]>
EOF
)"

5. 結果確認

git -C <dir> log --oneline -1 でコミット結果を表示して成功を確認。

エラーハンドリング

  • ステージングされたファイルがない場合: ユーザーに通知してファイルのステージングを提案
  • コミットが失敗した場合: エラーメッセージを表示して解決策を提案
  • pre-commit hook が失敗した場合: エラー内容を表示し、修正後に新しいコミットを作成(amend しない)
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. yesterday First seen · 76 lines · 12 tokens per session scan A c28db220591c

Subscribe to this mod's changes

commit is a skill published in the GitHub repository nanasess/eccube-dev-agents (2 stars, last pushed 26d ago), licensed MIT. It adds 12 tokens to every session and 989 once invoked, about $0.0001 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

a0-review-plugin

Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.

agent0ai/agent-zero · 64 tokens

execution-grounded-review

Execution-grounded review: run tests first, trace each acceptance criterion to execution evidence. Use when verifying an implementation meets spec.

laurigates/claude-plugins · 30 tokens

multi-model-delegation

Multi-model design consults via PAL (kimi, glm, gemini, gpt). Use when asking other models to brainstorm a design or reconciling their split answers.

laurigates/claude-plugins · 41 tokens

exclusive-lock-dispatch

Pre-dump-then-dispatch for tools holding an exclusive lock (Ghidra, migrations, single-writer caches). Use when fanning out parallel agents needing a non-concurrent resource.

laurigates/claude-plugins · 44 tokens

api-testing

HTTP API testing with Supertest (TS) and httpx/pytest (Python). Use when the user mentions API testing, Supertest, httpx, REST/GraphQL validation, or HTTP response errors.

laurigates/claude-plugins · 45 tokens

dev-environment-bootstrapping

Use this skill when the user asks to bootstrap, set up, create, or initialize a Shopware development environment from scratch — phrases like "set up a Shopware dev environment", "clone and install Shopware", "initialize a Shopware plugin project", "bootstrap Shopware and a new plugin called X", "get a fresh Shopware…

shopwareLabs/ai-coding-tools · 144 tokens